google ads
Deep Learning: Deep Learning and the Pancreas Imaging Pearls - Educational Tools | CT Scanning | CT Imaging | CT Scan Protocols - CTisus
Imaging Pearls ❯ Deep Learning ❯ Deep Learning and the Pancreas

-- OR --


  •  Preoperative Prediction of Lymph Node Metastases in Nonfunctional Pancreatic Neuroendocrine Tumors Using a Combined CT Radiomics-Clinical Model.  
    Ahmed TM, Zhu Z, Yasrab M, Blanco A, Kawamoto S, He J, Fishman EK, Chu L, Javed AA.
    Ann Surg Oncol. 2024 Aug 23. doi: 10.1245/s10434-024-16064-4. Epub ahead of print. 
  • Background: When determining the initial chemotherapy regimen for advanced or metastatic pancreatic cancer, various factors must be evaluated. The decision between FOLFIRINOX and Gemcitabine/Nab-paclitaxel (GnP) is challenging, as patient survival hinges on the efficacy and toxicity profiles of these treatments, alongside individual patient characteristics and vulnerabilities. This study aims to guide the selection of an appropriate first-line chemotherapy regimen for advanced or metastatic pancreatic cancer by leveraging machine learning (ML) methods to predict survival outcomes.
    Conclusions: We developed the ML models that can compute the probability of OS based on the routinely collected data from patients with advanced or metastatic pancreatic cancer. To the best of our knowledge, this is the first ML solution aimed at aiding clinicians in the selection of the first-line chemotherapy regimen for pancreatic cancer.
    Predicting chemotherapy response in patients with advanced or metastatic pancreatic cancer using machine learning.
    Moonho Kim, Gyucheol Choi, Jamin Koo
    American Society of Clinical Oncology. Sept 2024
  • Results: The median age of the patients was 66 years, with 62.3% being male. The MLnmodels achieved the ROC-AUC of 0.81 when predicting OS after 12 months following the initial administration of FOLFIRINOX (n=61) or GnP (n=47). Five (peritoneal metastases, other metastases, bilirubin level, white blood cell counts, and retroperitoneal lymph node metastases) or four (age, tumor location, sex, and metastatic status) covariates were used to achieve the predictive accuracy for the two regimens, respectively. The median OS of the high versus low risk groups of FOLFIRINOX predicted by the ML models were significantly different (7 vs 18 months, P, 0.01), recording the hazard ratio (HR) of 2.79 (95% CI, 1.47-5.26). Similarly, the median OS of the high and low risk groups of GnP were significantly different (8 vs 16 months,P , 0.001, HR 3.50, 95% CI, 1.60-7.66).
    Predicting chemotherapy response in patients with advanced or metastatic pancreatic cancer using machine learning.
    Moonho Kim, Gyucheol Choi, Jamin Koo
    American Society of Clinical Oncology. Sept 2024
  • “The overall risk of malignancy in pancreatic cysts may be as low as 0.5 to 1.5%, and the annual risk of progression is 0.5%.7,15 Conversely, studies estimate that 15% of all pancreatic adenocarcinomas originate from mucinous cysts, and these cysts are the sole recognizable precursors of malignant transformation that can be identified on cross-sectional imaging.16-18 Thus, identification of cysts at risk for progression provides an opportunity for prevention or early detection of cancer. Although surgical resection is the only curative treatment option, it carries a risk of major complications, despite technical advances.”
    Pancreatic Cysts
    Tamas A. Gonda,  Djuna L. Cahen, and James J. Farrell
    N Engl J Med 2024;391:832-43.
  • “There are more than 20 types of epithelial and nonepithelial pancreatic cysts, but the majority belong to the six most common histologic categories. The two most prevalent benign lesions, pseudocysts and serous cystadenomas, account for 15 to 25% of all pancreatic cysts. The two types of mucinous cysts, intraductal papillary mucinous neoplasms (IPMNs) and mucinous cystic neoplasms (MCNs), are the predominant premalignant cystic lesions and account for approximately50% of cysts that are found incidentally on imaging for other indications. Solid pseudopapillary neoplasms and cystic pancreatic neuroendocrine tumors are two less common malignant cystic neoplasms.”
    Pancreatic Cysts
    Tamas A. Gonda,  Djuna L. Cahen, and James J. Farrell
    N Engl J Med 2024;391:832-43.

  • Pancreatic Cysts
    Tamas A. Gonda,  Djuna L. Cahen, and James J. Farrell
    N Engl J Med 2024;391:832-43.
  • Pancreas Cysts: Key Points
    • Pancreatic cysts are common and are being discovered at an increasing rate on cross-sectional imaging, but only a minority progress to cancer.
    • The most important goal is to identify the small percentage of cystic lesions associated with a substantialrisk of cancer, and this should be done through a multidisciplinary evaluation based on an algorithmic approach.
    • In many cases, imaging, symptom assessment, and laboratory tests can help distinguish benign cysts from those associated with a low, intermediate, or high risk of malignant transformation.
    • Endoscopic ultrasonography should be considered for equivocal findings or intermediate-risk cysts.
    • Endoscopic ultrasonography and fluid aspiration for cytologic and molecular analysis may help in risk stratification for patients with intermediate-risk cysts.
    • Surgical evaluation is warranted for high-risk cysts and for intermediate-risk cysts with multiple risk features, whereas surveillance is used for low-risk cysts
  • “Serous cystadenomas are benign, slow-growing lesions that predominantly affect women innthe fifth to seventh decades of life.25 These cystsncommonly have a microcystic (honeycomb) appearancenbut may be manifested as solid, macrocysticnor unilocular lesions. A central scar on computed tomography (CT) or magnetic resonance imaging (MRI) is a pathognomonic feature, but it is observed in only 30% of cases. In the absence of typical morphologic features, further evaluation may be necessary to confirm the diagnosis. Although most cases are asymptomatic,large serous cystadenomas can cause abdominal pain, pancreatitis, and biliary obstruction.”
    Pancreatic Cysts
    Tamas A. Gonda,  Djuna L. Cahen, and James J. Farrell
    N Engl J Med 2024;391:832-43.
  • “MCNs are the less common type of mucinous cysts. They characteristically contain ovarian like stroma and almost exclusively affect women in the fourth to sixth decades of life. MCNs are single, thick-walled, mostly unilocular cysts that are generally situated in the distal pancreas. In contrast to intraductal papillary neoplasms, which are much more common, MCNs have no communication with the pancreatic ducts. Although rare, the presence of peripheral (eggshell) calcifications is a diagnostic hallmark. The risk of advanced neoplasia (high-grade dysplasia or cancer) in patients with MCNs was previously reported to be as high as 30 to 40%, but when the presence of pathognomonic ovariantype stroma is confirmed, only 5 to 15% of MCNs contain invasive cancer.”
    Pancreatic Cysts
    Tamas A. Gonda,  Djuna L. Cahen, and James J. Farrell
    N Engl J Med 2024;391:832-43.
  • “IPMNs are the most common type of mucinous cystic lesions, with an equal sex distribution and a peak incidence between the fifth and seventh decades of life. These neoplasms, which arise from the ductal cells, are often multifocal and located throughout the pancreas. IPMNs are classified according to ductal involvement as main-duct, branch-duct, or mixedtype IPMNs. Main-duct IPMNs, which are less common than the branch-duct and mixed-duct types, are characterized by diffuse or segmental dilatation of the main duct (often due to excessive intraductal mucin production) in the absence of a cystic lesion.”
    Pancreatic Cysts
    Tamas A. Gonda,  Djuna L. Cahen, and James J. Farrell
    N Engl J Med 2024;391:832-43.

  • Pancreatic Cysts
    Tamas A. Gonda,  Djuna L. Cahen, and James J. Farrell
    N Engl J Med 2024;391:832-43.
  • “The risk of malignant transformation depends on the histologic and anatomical subtypes and ranges from 1 to 38% for branchduct IPMNs and 33 to 85% for main-duct or mixed-type IPMNs. These estimates are mostly from surgical series, and more recent data suggest the risk may be lower. The probable field defect responsible for the multifocality also provides a small concomitant risk of pancreatic cancer, separate from the cyst of interest.”  
    Pancreatic Cysts
    Tamas A. Gonda,  Djuna L. Cahen, and James J. Farrell
    N Engl J Med 2024;391:832-43.
  • “Solid pseudopapillary neoplasms most often develop in women in their second or third decade of life. These lesions, which can be located throughout the pancreas, have a well demarcated, heterogeneous appearance, with both solid and cystic components and, in some cases, irregular calcifications. The majority of solid pseudopapillary neoplasms are associated with a low risk of metastasis, and 10 to 15% are classified on histologic evaluation as solid pseudopapillary carcinoma.”  
    Pancreatic Cysts
    Tamas A. Gonda,  Djuna L. Cahen, and James J. Farrell
    N Engl J Med 2024;391:832-43.
  • “Cystic pancreatic endocrine neoplasms arise from the pancreatic endocrine cells and are essentially a cystic degeneration of pancreatic neuroendocrine tumors, often with thick, enhancing walls on radiologic imaging Although most of these neoplasms are sporadic and nonfunctioning, up to 10% arise in patients with multiple endocrine neoplasia type 1. More than 80% of cystic pancreatic endocrine neoplasms express somatostatin receptors, which can be detected by means of positron-emission tomography with octreotide or dotatate tracers. Features associated with a poor prognosis, which are similar to those for solid pancreatic endocrine tumors, include a high histologic grade, a diameter of 2 cm or more, symptoms, a Ki-67 proliferation index of 3% or higher, and lymphovascular invasion.”
    Pancreatic Cysts
    Tamas A. Gonda,  Djuna L. Cahen, and James J. Farrell
    N Engl J Med 2024;391:832-43.
  • “A subsequent evaluation of symptoms can aid in risk stratification, although a minority of cysts are symptomatic. Jaundice that is caused by biliary obstruction is considered a high-risk feature. Pancreatitis (due to obstruction of the pancreatic duct by the cyst or produced mucin) and abdominal pain are considered intermediate- risk factors when they are related to the cyst, which is often difficult to confirm. With respect to laboratory testing, an elevation in levels of the serum marker CA 19-9 has been associated with an increased risk of malignant transformation. Similarly, new-onset diabetes is associated with an increased risk of advanced neoplasia. Therefore, an elevation in CA 19-9 and newly abnormal levels of glycated hemoglobin are both associated with an intermediate risk.”  
    Pancreatic Cysts
    Tamas A. Gonda,  Djuna L. Cahen, and James J. Farrell
    N Engl J Med 2024;391:832-43.
  • “DNA can be isolated from cyst fluid, and the detection of mutations associated with specific neoplasms can be helpful, particularly when other findings are inconclusive and the amount of fluid obtained is small (≤0.5 ml). The presence of a VHL mutation is nearly 100% specific for serous cystadenoma but is identified in only 25 to 50% of cases.The KRAS mutation,which is considered a founder mutation, is more than 95% specific for either type of mucinous cyst, with a sensitivity of 60 to 70%. Mutations in GNAS are specific for IPMNs (but not MCNs). and are detected in 30 to 60% of cases. The absence of a VHL mutation combined with the presence of a KRAS or GNAS mutation is nearly 100% specific for mucinous cysts, with an accuracy of 97%. Detection of a CT NB1 mutation has high specificity for solid pseudopapillary tumors, and the presence of a MEN1 mutation has high specificity for cystic pancreatic endocrine neoplasms.”
    Pancreatic Cysts
    Tamas A. Gonda,  Djuna L. Cahen, and James J. Farrell
    N Engl J Med 2024;391:832-43. 
  • “ For most low-risk cysts, surveillance is recommended, with its intensity depending on thebaseline risk. Follow-up every 6 months is advised in the first year, with yearly follow-up thereafter, but the interval can be lengthened with continued stability of the lesion. Surveillance is typically performed with cross-sectional imaging (preferably MRI with magnetic resonance cholangiopancreatography or, if that is unfeasible, with contrast-enhanced CT) or, for larger cysts and cysts with worrisome features, MRI and endoscopic ultrasonography on analternating schedule or combined.”
    Pancreatic Cysts
    Tamas A. Gonda,  Djuna L. Cahen, and James J. Farrell
    N Engl J Med 2024;391:832-43.
  • “Cyst stability is typically defined as less than a 20% increase in the greatest diameter or growth of less than 2.5 mm per year. Faster growth or the development of new intermediate-risk or highrisk features should warrant reconsideration of endoscopic ultrasonography, with or without guided fine-needle aspiration or biopsy, or surgical resection. Current data do not unequivocally support discontinuing surveillance. However, for low-risk lesions that have remained stable for years, the risk of progression is minimal, and cessation of surveillance becomes a reasonable option. Also, a patient’s health status needs to be reevaluated regularly, since a change in health status may warrant adjustment of surveillance goals.”
    Pancreatic Cysts
    Tamas A. Gonda,  Djuna L. Cahen, and James J. Farrell
    N Engl J Med 2024;391:832-43.
  • “Current data do not unequivocally support discontinuing surveillance. However, for low-risk lesions that have remained stable for years, the risk of progression is minimal, and cessation of surveillance becomes a reasonable option. Also, a patient’s health status needs to be reevaluated regularly, since a change in health status may warrant adjustment of surveillance goals.”
    Pancreatic Cysts
    Tamas A. Gonda,  Djuna L. Cahen, and James J. Farrell
    N Engl J Med 2024;391:832-43.
  • “Pancreatic cysts are strikingly common, mostly incidental findings. Although the majority of these cysts are associated with a very low risk of malignant transformation, a minority may offer an opportunity to recognize and eliminate highrisk precursors of pancreatic cancer. Several guidelines provide recommendations for evaluation, treatment, and surveillance, but they are based on expert opinion rather than solid evidence. Fortunately, an initiative to develop a unified global guideline in the next 1 to 2 years is widely endorsed.”
    Pancreatic Cysts
    Tamas A. Gonda,  Djuna L. Cahen, and James J. Farrell
    N Engl J Med 2024;391:832-43.
  • “An important goal in the management of pancreatic cysts is to reduce the surveillance burden for low-risk lesions while improving the recognition of malignant and premalignant cysts. To accomplish this, prospective studies are needed to determine the true predictive value of known risk factors for cancer. Also, advances in our understanding of the molecular evolution of cystic precursors will lead to the identification of increasingly sensitive biomarkers derived from either cyst fluid, pancreatic juice, or blood. The integration of radiomics (machine learning and artificial intelligence) and advances in endoscopic imaging, such as needle-based, intracystic confocal microscopy, may enhance the sensitivity of risk stratification. Although surgery has become much safer, alternative and less invasive techniques are needed, especially for prophylactic interventions.”  
    Pancreatic Cysts
    Tamas A. Gonda,  Djuna L. Cahen, and James J. Farrell
    N Engl J Med 2024;391:832-43.
  • “The current approach to management relies on identifying the cyst type and conducting a multimodal assessment of the risk of cancer, an assessment that is mostly noninvasive, with selective use of endoscopic ultrasonography and tissue sampling. The best personalized approach will be provided by models that combine risk factors, clinical variables, imaging characteristics, and molecular markers. Treatment and surveillance decisions should follow an algorithmic framework that is overseen by a multidisciplinary team and that incorporates shared decision making with the patient.”  
    Pancreatic Cysts
    Tamas A. Gonda,  Djuna L. Cahen, and James J. Farrell
    N Engl J Med 2024;391:832-43.
  • “Between June 2012 and December 2022, a total of 4039 patients’ multiphase (arterial phase and portal venous phase) contrastenhanced CT images from six hospitals were included under the following inclusion criteria: Patients (1) were eighteen years or older; (2) did not have a history of hepatectomy, transarterial chemotherapy (TACE), or radiofrequency ablation (RFA) before CT imaging; (3) had pathologically confirmed malignant tumors; and (4) had benign tumors confirmed either by consensus among three radiologists or by follow-up of at least six months using two imaging modalities. The method used for retrospective data collection and basic patientinformation including sex and age are depicted in Fig. 1a and Table 1, respectively. Furthermore, clinical testing was conducted on two real world clinical evaluation queues (Fig. 1b): West China Tianfu Center and Sanya People’s Hospital. At Tianfu Center, we examined 184 cases, while at Sanya People’s Hospital, 235 cases were assessed. Gender andAge assignment was based on government-issued IDs.”
    Focal liver lesion diagnosis with deep learning and multistage CT imaging
    Yi Wei et al.
    Nature Communications | ( 2024) 15:7040
  • Background/objectives: Pancreatic cyst management can be distilled into three separate pathways -- discharge, monitoring or surgery based on the risk of malignant transformation. This study compares the performance of artificial intelligence (AI) models to clinical care for this task.
    Methods: Two explainable boosting machine (EBM) models were developed and evaluated using clinical features only, or clinical features and cyst fluid molecular markers (CFMM) using a publicly available dataset, consisting of 850 cases (median age 64; 65 % female) with independent training (429 cases) and holdout test cohorts (421 cases). There were 137 cysts with no malignant potential, 114 malignant cysts, and 599 IPMNs and MCNs.
    Performance of explainable artificial intelligence in guiding the management of patients with a pancreatic cyst.
    Lavista Ferres JM, Oviedo F, Robinson C, Chu L, Kawamoto S, Afghani E, He J, Klein AP, Goggins M, Wolfgang CL, Javed AA, Dodhia R, Papadopolous N, Kinzler K, Hruban RH,  Weeks WB, Fishman EK, Lennon AM.  
    Pancreatology. 2024 Sep 2:S1424-3903(24)00730-0. doi: 10.1016/j.pan.2024.09.001. Epub ahead of print. PMID: 39261223.
  • Results: The EBM and EBM with CFMM models had higher accuracy for identifying patients requiring monitoring (0.88 and 0.82) and surgery (0.66 and 0.82) respectively compared with current clinical care (0.62 and 0.58). For discharge, the EBM with CFMM model had a higher accuracy (0.91) than either the EBM model (0.84) or current clinical care (0.86). In the cohort of patients who underwent surgical resection, use of the EBM-CFMM model would have decreased the number of unnecessary surgeries by 59 % (n=92), increased correct surgeries by 7.5 % (n=11), identified patients who require monitoring by 122 % (n=76), and increased the number of patients correctly classified for discharge by 138 % (n=18) compared to clinical care.
    Conclusions: EBM models had greater sensitivity and specificity for identifying the correct management compared with either clinical management or previous AI models. The model predictions are demonstrated to be interpretable by clinicians.
    Performance of explainable artificial intelligence in guiding the management of patients with a pancreatic cyst.
    Lavista Ferres JM, Oviedo F, Robinson C, Chu L, Kawamoto S, Afghani E, He J, Klein AP, Goggins M, Wolfgang CL, Javed AA, Dodhia R, Papadopolous N, Kinzler K, Hruban RH,  Weeks WB, Fishman EK, Lennon AM.  
    Pancreatology. 2024 Sep 2:S1424-3903(24)00730-0. doi: 10.1016/j.pan.2024.09.001. Epub ahead of print. PMID: 39261223.
  • “Conclusions: EBM models had greater sensitivity and specificity for identifying the correct management compared with either clinical management or previous AI models. The model predictions are demonstrated to be interpretable by clinicians.”
    Performance of explainable artificial intelligence in guiding the management of patients with a pancreatic cyst.
    Lavista Ferres JM, Oviedo F, Robinson C, Chu L, Kawamoto S, Afghani E, He J, Klein AP, Goggins M, Wolfgang CL, Javed AA, Dodhia R, Papadopolous N, Kinzler K, Hruban RH,  Weeks WB, Fishman EK, Lennon AM.  
    Pancreatology. 2024 Sep 2:S1424-3903(24)00730-0. doi: 10.1016/j.pan.2024.09.001. Epub ahead of print. PMID: 39261223.
  • “The management of patients with pancreatic cysts can be distilled into three separate pathways based on the risk of malignant transformation. Cysts with pancreatic cancer or high-grade dysplasia, such as cystic degeneration of pancreatic adenocarcinoma, an IPMN with high-grade dysplasia or associated invasive adenocarcinoma, should be surgically resected . Patients harboring an IPMN or MCN with low grade dysplasia are recommended for surveillance. Patients with a pancreatic cyst with no malignant potential, such as a pseudocyst or a serous cystadenoma (SCA), require no follow-up and these patients can be discharged.”  
    Performance of explainable artificial intelligence in guiding the management of patients with a pancreatic cyst.
    Lavista Ferres JM, Oviedo F, Robinson C, Chu L, Kawamoto S, Afghani E, He J, Klein AP, Goggins M, Wolfgang CL, Javed AA, Dodhia R, Papadopolous N, Kinzler K, Hruban RH,  Weeks WB, Fishman EK, Lennon AM.  
    Pancreatology. 2024 Sep 2:S1424-3903(24)00730-0. doi: 10.1016/j.pan.2024.09.001. Epub ahead of print. PMID: 39261223.
  • “Correctly preoperatively classifying patients into these three different management pathways is challenging, with large surgical series finding that 25 % of cyst patients who undergo surgical resection have cysts with no malignant potential , while up to 73 % of patients with IPMNs who undergo surgical resection have low-grade dysplasia and in hindsight did not require surgery.”  
    Performance of explainable artificial intelligence in guiding the management of patients with a pancreatic cyst.
    Lavista Ferres JM, Oviedo F, Robinson C, Chu L, Kawamoto S, Afghani E, He J, Klein AP, Goggins M, Wolfgang CL, Javed AA, Dodhia R, Papadopolous N, Kinzler K, Hruban RH,  Weeks WB, Fishman EK, Lennon AM.  
    Pancreatology. 2024 Sep 2:S1424-3903(24)00730-0. doi: 10.1016/j.pan.2024.09.001. Epub ahead of print. PMID: 39261223.
  • “Artificial intelligence (AI) models are uniquely equipped to handle a large number of diverse and complex features, potentially aiding physicians and patients in making informed decisions. One early example of this is Multivariate Organization of Combinatorial Alterations (MOCA) model, which used combinatorial feature transformations and random sampling with iterative optimization to engineer a subset of composite markers with high predictive power. This machine learning model was applied to 862 patients with pancreatic cysts who underwent surgical resection, and was found to be more accurate than conventional clinical and imaging criteria alone for classifying patients into the three management groups of surgery, surveillance, or discharge.”
    Performance of explainable artificial intelligence in guiding the management of patients with a pancreatic cyst.
    Lavista Ferres JM, Oviedo F, Robinson C, Chu L, Kawamoto S, Afghani E, He J, Klein AP, Goggins M, Wolfgang CL, Javed AA, Dodhia R, Papadopolous N, Kinzler K, Hruban RH,  Weeks WB, Fishman EK, Lennon AM.  
    Pancreatology. 2024 Sep 2:S1424-3903(24)00730-0. doi: 10.1016/j.pan.2024.09.001. Epub ahead of print. PMID: 39261223.

  • Performance of explainable artificial intelligence in guiding the management of patients with a pancreatic cyst.
    Lavista Ferres JM, Oviedo F, Robinson C, Chu L, Kawamoto S, Afghani E, He J, Klein AP, Goggins M, Wolfgang CL, Javed AA, Dodhia R, Papadopolous N, Kinzler K, Hruban RH, Weeks WB, Fishman EK, Lennon AM.  
    Pancreatology. 2024 Sep 2:S1424-3903(24)00730-0. doi: 10.1016/j.pan.2024.09.001. Epub ahead of print. PMID: 39261223.

  • Performance of explainable artificial intelligence in guiding the management of patients with a pancreatic cyst.
    Lavista Ferres JM, Oviedo F, Robinson C, Chu L, Kawamoto S, Afghani E, He J, Klein AP, Goggins M, Wolfgang CL, Javed AA, Dodhia R, Papadopolous N, Kinzler K, Hruban RH, Weeks WB, Fishman EK, Lennon AM.  
    Pancreatology. 2024 Sep 2:S1424-3903(24)00730-0. doi: 10.1016/j.pan.2024.09.001. Epub ahead of print. PMID: 39261223.

  • Performance of explainable artificial intelligence in guiding the management of patients with a pancreatic cyst.
    Lavista Ferres JM, Oviedo F, Robinson C, Chu L, Kawamoto S, Afghani E, He J, Klein AP, Goggins M, Wolfgang CL, Javed AA, Dodhia R, Papadopolous N, Kinzler K, Hruban RH, Weeks WB, Fishman EK, Lennon AM.  
    Pancreatology. 2024 Sep 2:S1424-3903(24)00730-0. doi: 10.1016/j.pan.2024.09.001. Epub ahead of print. PMID: 39261223.
  • “The results are even more striking when compared with clinical care. In this test cohort of patients, all of whom underwent surgical resection, use of the EBM with CFMM model decreases the number of unnecessary surgeries by 59 % (n=92), increases the number of correct surgeries by 7.5 % (n=11), better identifies patients who truly require monitoring by 122 % (n=76), and increases the number of patients correctly classified as being safe to discharge by 138 % (n=18) compared to clinical care. Overall, in this cohort of patients the use of the EBM with CFMM could have changed the management of at least 25 % of patients.”
    Performance of explainable artificial intelligence in guiding the management of patients with a pancreatic cyst.
    Lavista Ferres JM, Oviedo F, Robinson C, Chu L, Kawamoto S, Afghani E, He J, Klein AP, Goggins M, Wolfgang CL, Javed AA, Dodhia R, Papadopolous N, Kinzler K, Hruban RH,  Weeks WB, Fishman EK, Lennon AM.  
    Pancreatology. 2024 Sep 2:S1424-3903(24)00730-0. doi: 10.1016/j.pan.2024.09.001. Epub ahead of print. PMID: 39261223.
  • “This study shows the potential of an AI model to incorporate multiple features and its ability to generate a correct management plan which can help guide care for patients and their physicians. In this study, the performance of the EBM model was superior to clinical management in correctly identifying which patients required surveillance or should be referred for surgery. The impact of the CFMM can be seen when we look at the global feature importance score, where 6 of the top 9 features used by the model are CFMMs. Overall, the use of EBM with CFMM model couldhave changed the management of at least 25 % (n=105) of the patients compared with clinical management.”  
    Performance of explainable artificial intelligence in guiding the management of patients with a pancreatic cyst.
    Lavista Ferres JM, Oviedo F, Robinson C, Chu L, Kawamoto S, Afghani E, He J, Klein AP, Goggins M, Wolfgang CL, Javed AA, Dodhia R, Papadopolous N, Kinzler K, Hruban RH,  Weeks WB, Fishman EK, Lennon AM.  
    Pancreatology. 2024 Sep 2:S1424-3903(24)00730-0. doi: 10.1016/j.pan.2024.09.001. Epub ahead of print. PMID: 39261223.
  • “The EBM model has a number of features which are very attractive for use in clinical care. First, it has an explainable aspect which provides a transparent understanding of the features that are used to generate the prediction. In contrast with other machine learning models, such as deep neural networks, the feature contributions used to generate predictions of the EBM model are easy to quantify and isolate. This transparency allows health care providers to understand how features were used in the model and confirm that they make clinical and biological sense. Furthermore, instead of providing a positive or negative output, the EBM model outputs a calibrated probability vector for each predicted outcome for an individual patient. Both feature explanations and calibrated probabilities affords clinicians and patients a richer perspective of model operation and uncertainty when determining clinical management.”
    Performance of explainable artificial intelligence in guiding the management of patients with a pancreatic cyst.
    Lavista Ferres JM, Oviedo F, Robinson C, Chu L, Kawamoto S, Afghani E, He J, Klein AP, Goggins M, Wolfgang CL, Javed AA, Dodhia R, Papadopolous N, Kinzler K, Hruban RH,  Weeks WB, Fishman EK, Lennon AM.  
    Pancreatology. 2024 Sep 2:S1424-3903(24)00730-0. doi: 10.1016/j.pan.2024.09.001. Epub ahead of print. PMID: 39261223.
  • “Future work should validate the model in a prospective cohort of patients including patients who undergo surgical resection and those undergoing surveillance. Finally, the feature contributions and explanations are predictive but not necessarily casual, in the sense that observed trends could be affected by interaction with unknown confounders or variables not captured as clinical features. As models are retrained in larger datasets is important to verify that overall feature importance is comparable across models, and prospectively evaluate explanations and the high uncertainty/error-prone probability thresholds with clinical judgement.”
     Performance of explainable artificial intelligence in guiding the management of patients with a pancreatic cyst.
    Lavista Ferres JM, Oviedo F, Robinson C, Chu L, Kawamoto S, Afghani E, He J, Klein AP, Goggins M, Wolfgang CL, Javed AA, Dodhia R, Papadopolous N, Kinzler K, Hruban RH,  Weeks WB, Fishman EK, Lennon AM.  
    Pancreatology. 2024 Sep 2:S1424-3903(24)00730-0. doi: 10.1016/j.pan.2024.09.001. Epub ahead of print. PMID: 39261223.
  • “In conclusion, we have developed and evaluated two AI models for patients with pancreatic cysts, using clinical features alone or combined with CFMM, which demonstrate greater accuracy for identifying the correct management recommendation of discharge, monitoring or surgery compared with either clinical management or prior AI models. These models allow health care providers and patients to understand the probability of a management recommendation and interpret the impact of features used to make predictions.”  
    Performance of explainable artificial intelligence in guiding the management of patients with a pancreatic cyst.
    Lavista Ferres JM, Oviedo F, Robinson C, Chu L, Kawamoto S, Afghani E, He J, Klein AP, Goggins M, Wolfgang CL, Javed AA, Dodhia R, Papadopolous N, Kinzler K, Hruban RH,  Weeks WB, Fishman EK, Lennon AM.  
    Pancreatology. 2024 Sep 2:S1424-3903(24)00730-0. doi: 10.1016/j.pan.2024.09.001. Epub ahead of print. PMID: 39261223.
  • “Radiomics is a science based on the quantitative analysis of medical images by mathematically obtaining a series of values representing signal intensities or a variety of pixel interrelationship metric. It has enabled the conversion of routine radiology images into high-throughput quantitative data to describe non-intuitive properties of the imaging phenotype and tissue micro-environment. In general, a radiomics analysis workflow comprises four main steps: image segmentation, image preprocessing, radiomics extraction and ML modelling. All these steps have evolved over time to increase the robustness of the extracted quantitative data.”  
    Cystic pancreatic neoplasms: what we need to know and new perspectives
    Antonio Galluzzo · Silvia Bogani · Filippo Fedeli · Ginevra Danti · Vittorio Miele
    Journal of Medical Imaging and Interventional Radiology (2024) 11:22
  • “In general, a radiomics analysis workflow comprises four main steps: image segmentation, image preprocessing, radiomics extraction and ML modelling. All these steps have evolved over time to increase the robustness of the extracted quantitative data. In the first step (image segmentation), it is necessary to circumscribe the specific region of interest (ROI) within the image from which radiomics features are extracted. The most accurate segmentation methods involve fully automated AI methodologies with the use of DL to minimize intra- and inter-observer variability. The second phase (image pre-processing) is used for removing or alleviating noise and artefacts, a very important detail for the accuracy of the radiomic model. In this case, CNNs proved to be useful for improving image quality.”
    Cystic pancreatic neoplasms: what we need to know and new perspectives
    Antonio Galluzzo · Silvia Bogani · Filippo Fedeli · Ginevra Danti · Vittorio Miele
    Journal of Medical Imaging and Interventional Radiology (2024) 11:22
  • “The next critical step is radiomic extraction, a complex process that can be based on mathematical equations to obtain handcrafted features (descriptors of shape, size and textural patterns) or on a totally automated complex DL architecture that uses non-linear image transformations to extract a huge amount of “deep features”. Although AI enables correct feature extraction, the weakness of radiomics studies mainly concerns certain sources of variability such as the patient himself or the different machine used. To standardize this pre-processing step and achieve greater reproducibility, image biomarker standardization initiative (IBSI) guidelines were established. The last step involves the construction of a radiomic model which is now mostly DL-based and requires the training of AI algorithms that will subsequently make statistical inferences to make previsions.”
    Cystic pancreatic neoplasms: what we need to know and new perspectives
    Antonio Galluzzo · Silvia Bogani · Filippo Fedeli · Ginevra Danti · Vittorio Miele
    Journal of Medical Imaging and Interventional Radiology (2024) 11:22
  • “The combination of artificial intelligence and genomics may encourage a further evolution of personalised medicine , several studies have, therefore, also focused on radiogenomics in pancreas oncology. Attiyeh et al. identified radiomic features associated with PDAC genetic alterations and stromal content. In particular, their algorithm was able to distinguish between tumour with and without SMAD4 alterations. The studies by Yosuke Iwatate et al. and Gao et al. suggest that the construction of a radiomic model based, respectively, on CT and certain MRI sequences (T2W, ADC, DWI and CE T1W) can identify the TP53 mutation status in PDAC. Li qu.et al. recently developed a radiomic normogram able to evaluate preoperatively the proliferation status of KI-67 in PDAC.”  
    Cystic pancreatic neoplasms: what we need to know and new perspectives
    Antonio Galluzzo · Silvia Bogani · Filippo Fedeli · Ginevra Danti · Vittorio Miele
    Journal of Medical Imaging and Interventional Radiology (2024) 11:22
  • ”PC is often not easily visible in its early stages although certain morphological changes (parenchyma inhomogeneity, loss of fatty marbling and dilatation of the main pancreatic duct) become more visible over time and help in diagnosis. A quantitative analysis of these factors was the aim of the study by Chu et al.: they manually segmented the venous phase of PC patients and compared it with the pancreas of healthy subjects. They demonstrated high sensitivity (100%) and specificity (98.5%) and accuracy (99.2%) of radiomic features in differentiating PC cases from normal control cases.”  
    Cystic pancreatic neoplasms: what we need to know and new perspectives
    Antonio Galluzzo · Silvia Bogani · Filippo Fedeli · Ginevra Danti · Vittorio Miele
    Journal of Medical Imaging and Interventional Radiology (2024) 11:22
  • “The same author (Chu et al.) was able to distinguish between normal and abnormal tissue utilizing both a commercially available radiomics research prototype and in-house radiomics software. In his study, despite differences and variations in the radiomics features employed by the software (854 features in commercial programe vs. 478 features in in-house programme), they did not seem to impact the overall diagnostic performance of the constellation of radiomics features. That also mean that commercially available radiomics software may be a viable alternative to in-house computer science expertise.”  
    Cystic pancreatic neoplasms: what we need to know and new perspectives
    Antonio Galluzzo · Silvia Bogani · Filippo Fedeli · Ginevra Danti · Vittorio Miele
    Journal of Medical Imaging and Interventional Radiology (2024) 11:22
  • “Surgical treatment is mandatory in PDAC, which sometimes requires neoadjuvant chemo(radio)therapy, especially in resectable and borderline resectable disease, resulting in longer survival compared to patients treated with non-surgical treatment alone. It also leads to conversion in initially unresectable patients. Not all tumours show the same response to treatment, and proper assessment of response to chemo-radiotherapy is essential to optimize results. In addition to the well-known radiological, serum and EUS sampling methods, radiomic models have been proposed. The study by Chen et al. showed changes in radiomic features during chemo-radiotherapy in 20 patients, parameters that could be used to intensify or not intensify therapy. Borhani et al. investigated the correlation between CT-derived texture features and progression disease (PR); they assessed that CT-derived tumour textural features may have a relationship with tumour response to neoadjuvant chemotherapy.”  
    Cystic pancreatic neoplasms: what we need to know and new perspectives
    Antonio Galluzzo · Silvia Bogani · Filippo Fedeli · Ginevra Danti · Vittorio Miele
    Journal of Medical Imaging and Interventional Radiology (2024) 11:22
  • “It has been pointed out that radiomics cannot be applied clinically yet due to known problems related to standardisation and generalisation of radiomic results, data quality control, repeatability, reproducibility, database matching and model overfitting problems. The mentioned studies present different methods of image segmentation, feature extraction and model construction. Some of them lack external validation and have an unbalanced dataset. To obtain standardised models, it is mandatory to follow the IBSI guidelines and a common radiomic feature extraction tool. Important steps to bring radiomics into clinical practice are the establishment of a single acquisition protocol and the conduction of multicentre prospective studies.”  
    Cystic pancreatic neoplasms: what we need to know and new perspectives
    Antonio Galluzzo · Silvia Bogani · Filippo Fedeli · Ginevra Danti · Vittorio Miele
    Journal of Medical Imaging and Interventional Radiology (2024) 11:22
  • Background: Weidentified computed tomography (CT)-derived radiomic features predictive oftumor progression within three months, then examined their ability to prognosticate overall survival (OS) along with clinical features in pancreatic cancer. We evaluated these features in patients with unresected pancreatic cancer who underwent stereotactic body radiation therapy (SBRT) in sequence with chemotherapy, but not surgery
    Conclusions: CT-derived radiomic features predict rapid tumor progression following SBRT, confer nearly a twofold increase in mortality risk, and, along with patient age, enhance the identification of patients with stage IIIII pancreatic cancer with poor OS.
    Utility of radiomic features in predicting clinical outcomes in stage II-III pancreatic cancer.
    Haruka Itakura,et al.
    2024 American Society of Clinical Oncology (abstract 74 gastrointestinal cancer)
  • Results: Our cohort consisted of 48 men (mean age, 70 years 6 11 [SD]) and 53 women (mean age, 67 years 6 13 [SD]). From the first phase, 32 textural features comprised the radiomic feature set that best predicted rapid tumor progression, with mean AUCs of 0.852 (CV, n=53) and 0.814 (test, n=48). In the univariate Coxmodel, only the radiomic feature set was predictive of OS (hazard ratio, HR, 1.724, p=0.011). In the multivariate Cox model, radiomic features and age were significant predictors of OS, with HR of 1.819 (p=0.007) and 1.024 (p=0.024), respectively.  
    Conclusions: CT-derived radiomic features predict rapid tumor progression following SBRT, confer nearly a twofold increase in mortality risk, and, along with patient age, enhance the identification of patients with stage IIIII pancreatic cancer with poor OS.
    Utility of radiomic features in predicting clinical outcomes in stage II-III pancreatic cancer.
    Haruka Itakura,et al.
    2024 American Society of Clinical Oncology (abstract 74 gastrointestinal cancer)
  • “Pancreatic surveillance can detect early-stage pancreatic cancer and achieve long-term survival, but currently involves annual endoscopic ultrasound and MRI/MRCP, and is recommended only for individuals who meet familial/genetic risk criteria. To improve upon current approaches to pancreatic cancer early detection and to expand access, more accurate, inexpensive, and safe biomarkers are needed, but finding them has remained elusive. Newer approaches to early detection, such as using gene tests to personalize biomarker interpretation, and the increasing application of artificial intelligence approaches to integrate complex biomarker data, offer promise that clinically useful biomarkers for early pancreatic cancer detection are on the horizon.”
    The role of biomarkers in the early detection of pancreatic cancer
    Michael Goggins
    Fam Cancer. 2024 Apr 25. doi: 10.1007/s10689-024-00381-4. Online ahead of print.
  • “After decades of effort and many challenges associated with discovering suitable biomarkers that could improve the early detection of pancreatic cancer, there are signs of progress. The detection of early-stage pancreatic cancer, particularly Stage I disease is associated with long-term survival. Using a tumor marker gene test that accounts for common gene variants that influence the level of CA19-9 and DUPAN-2 significantly improves diagnostic accuracy. Machine learning approaches offer the possibility of yielding greater information from biomarkers, particularly imaging based biomarkers which remain the main diagnostic tools for pancreatic surveillance and the evaluation of suspected pancreatic cancer.”
    The role of biomarkers in the early detection of pancreatic cancer
    Michael Goggins
    Fam Cancer. 2024 Apr 25. doi: 10.1007/s10689-024-00381-4. Online ahead of print.
  • Results: Fifty-one patients (16.1%) achieved a 5-y RFS. A tumor size ≤23 mm, the absence of serosal invasion on computed tomography (CT), and Neutrophil-to- Lymphocyte Ratio <1.0, were significantly associated with the 5-y RFS in model 1. A Prognostic Nutritional Index ≥58 and the absence of serosal invasion and extrapancreatic nerve plexus invasion on CT were significantly associated with 5-y RFS in model 2. Only six (11.8%, model 1) and four (7.8%, model 2) patients had all three prognostic factors, and their 5-y RFS rates were 83.3% and 100%, respectively.
    Conclusions: A modest number of patients who underwent upfront surgery achieved 5-yRFS, but only ~10% of them could be identified preoperatively. Based on these results, almost all R-PC patients are forced to undergo neoadjuvant treatment in daily practice.
    Predictive factors of actual 5-y recurrence-free survival after upfront surgery for resectable pancreatic cancer
    Masao Uemura1 | Teiichi Sugiura1 | Ryo Ashida1 et al
    Ann Gastroenterol Surg. 2024;00:1–11.  
  • “Current guidance for pancreatic cancer surveillance is restricted to high-risk individuals (HRIs) who have germline mutations that predispose to a lifetime increased risk of pancreatic cancer or a strong family history of pancreatic cancer. When a pancreatic cyst is detected incidentally by abdominal imaging, such patients are often put in the HRI category for surveillance. Cumulatively, HRIs account for only about 20–25% of cases. What about the majority of patients with no risk factors who present at an advanced stage? This is where advances in artificial intelligence (AI) based on mining of electronic health records (EHRs) have started to show some promise. ”
    Early detection of pancreatic cancer and AI risk partitioning.
    Maitra A, Topol EJ.  
    Lancet. 2024 Apr 13;403(10435):1438. doi: 10.1016/S0140-6736(24)00690-1. PMID: 38615682.  
  • “ It is important to emphasise that these are retrospective studies and have not yet been evaluated prospectively in a real-world setting. Nonetheless, such research provides a potential roadmap for early detection of pancreatic cancer that extends beyond the current narrow definition of HRIs by enriching the general population with a larger proportion of individuals at “sporadic” risk who are identified through the mining of EHR data (figure). If prospective studies support this approach, this enriched population could then undergo longitudinal surveillance using liquid biopsy tools (circulating tumour DNA, methylation assays, or proteins) that are being deployed in the context of early detection of multiple cancers.”  
    Early detection of pancreatic cancer and AI risk partitioning.
    Maitra A, Topol EJ.  
    Lancet. 2024 Apr 13;403(10435):1438. doi: 10.1016/S0140-6736(24)00690-1. PMID: 38615682.  
  •  ”The contribution of AI does not stop at the initial EHR-based enrichment step since deep learning models are also being developed to improve the resolution of CT and MRI imaging scans for the detection of early, subcentimetric cancers in the pancreas. In addition to changes within the pancreas, these computational algorithms could also identify subtle changes in body composition (eg, attenuation of visceral fat and muscle) that may be missed by clinicians. With such surveillance of a high-risk group, early diagnosis would be enabled, as would the potential for improving outcomes, with treatment including surgical resection followed by emerging immunotherapy options, such as personalised vaccines. Therein lies the opportunity for AI support to help advance diagnosis and care for pancreatic cancer. ”
    Early detection of pancreatic cancer and AI risk partitioning.
    Maitra A, Topol EJ.  
    Lancet. 2024 Apr 13;403(10435):1438. doi: 10.1016/S0140-6736(24)00690-1. PMID: 38615682. 
  • “ In a study that used a transformer AI model that incorporated time sequence data of longitudinal EHRs over several years, an aggregate of nearly 28 000 cases of pancreatic cancer were analysed and compared with 11 million patients who did not develop this disease. The primary dataset was from over 6 million patients in a Danish national registry, and findings were subsequently validated in an additional 3 million patients in the US Veterans Affairs system. The authors were able define a group of people among those aged 50 years and older who had a 30–60 times higher risk than the general population of being diagnosed with pancreatic cancer within the next 12 months. One of the EHR diagnostic codes that the model consistently identified as a feature predictive of incident pancreatic cancer within the next 24 months was diabetes, reinforcing the established link between new-onset diabetes and underlying pancreatic cancer. A second independent study used AI to differentiate the approximately 35 000 patients who developed pancreatic cancer from 1·5 million people who did not. This study identified over 80 features derived from EHRs, laboratory tests, symptoms, medications, and coexisting conditions that defined increased risk. Some of the features within the algorithm are intuitive, such as age or diabetes, whereas others underscore how AI can identify patterns not readily discernible by human assessment (eg, mean corpuscular haemoglobin concentration in red blood cells).”
    Early detection of pancreatic cancer and AI risk partitioning.
    Maitra A, Topol EJ.  
    Lancet. 2024 Apr 13;403(10435):1438. doi: 10.1016/S0140-6736(24)00690-1. PMID: 38615682.  
  • The early detection of pancreatic cancer is a critical factor in improving patient outcomes, as it is often diagnosed at an advanced stage when treatment options are limited. AI has the potential to aid in the early detection of pancreatic cancer by analyzing medical data and identifying patterns that may indicate the presence of the disease. Deep learning techniques can be trained on large datasets to accurately identify early stage pancreatic cancer based on characteristic imaging features or use morphology features to build segmentation frameworks for the pancreas. AI algorithms can integrate various patient data, such as age, family history, lifestyle factors, and medical history, to detect an individual’s developing pancreatic cancer early. AI can also analyze a patient’s electronic health records, including medical history, laboratory results, and diagnostic reports, to identify potential indicators of pancreatic cancer. By processing and interpreting vast amounts of data, AI algorithms can detect subtle patterns and abnormalities that may go unnoticed by clinicians.
    From Machine Learning to Patient Outcomes: A Comprehensive Review of AI in Pancreatic Cancer.  
    Tripathi S, et al.  
    Diagnostics (Basel). 2024 Jan 12;14(2):174. doi: 10.3390/diagnostics14020174. PMID: 38248051;

  • From Machine Learning to Patient Outcomes: A Comprehensive Review of AI in Pancreatic Cancer.  
    Tripathi S, et al.  
    Diagnostics (Basel). 2024 Jan 12;14(2):174. doi: 10.3390/diagnostics14020174. PMID: 38248051; 
  • “The lack of large, centralized datasets that can be used to build and test algorithms poses a barrier to developing comprehensive models. Currently, there is only one major effort in addressing this through the NIH-NCI-sponsored EDRN project for pancreatic cancer. Studies that have used smaller available datasets have not accounted for suboptimal image quality and factors that make images unsuitable for AI, such as posttreatment status and the presence of biliary stents. These gaps in the quality of the data used to develop models may result in errors and biases that limit their applications in clinical medicine.”
    From Machine Learning to Patient Outcomes: A Comprehensive Review of AI in Pancreatic Cancer.  
    Tripathi S, et al.  
    Diagnostics (Basel). 2024 Jan 12;14(2):174. doi: 10.3390/diagnostics14020174. PMID: 38248051;
  • “AI can serve as a powerful tool in the advancement of pancreatic cancer diagnosis, management, and prognosis, particularly in identifying tumors earlier in disease progression. Despite the many applications and advantages of AI in pancreatic cancer, multiple limitations pose challenges that must be addressed as the field grows. One is the lack of a standardized approach to treatment and diagnosis. Other challenges include a lack of robust and high-quality data, transparency and reproducibility of findings, and ethical considerations, including biases in algorithms.”  
    From Machine Learning to Patient Outcomes: A Comprehensive Review of AI in Pancreatic Cancer.  
    Tripathi S, et al.  
    Diagnostics (Basel). 2024 Jan 12;14(2):174. doi: 10.3390/diagnostics14020174. PMID: 38248051;
  • Furthermore, AI algorithms have been previously referred to as “Black boxes” due to their lack of transparency and interpretability. The opacity of the code used to build AI models and the hidden level of complexity make it difficult to reproduce results in an independent manner. General descriptions of the code used to build models do not provide enough information to reproduce most findings. The lack of easy interpretation of these AI models and prospective studies assessing AI-based tools has increased the hesitancy of adaptation into clinical practice. Without transparency and interpretation, clinicians are not able to critically interrogate the output of these models, putting an incredible amount of faith in the accuracy of the model. Improving reproducibility and interpretability will be crucial challenges to overcome prior to the clinical adaptation of AI models in pancreatic cancer.”
    From Machine Learning to Patient Outcomes: A Comprehensive Review of AI in Pancreatic Cancer.  
    Tripathi S, et al.  
    Diagnostics (Basel). 2024 Jan 12;14(2):174. doi: 10.3390/diagnostics14020174. PMID: 38248051;
  • “Lastly, a few ethical concerns should be considered when discussing the implementation of AI in pancreatic cancer. Datasets used to build models tend to lack data from underrepresented groups such as women and minorities, leading to biased models that may not be applicable to the diverse patient population seen clinically. Implementing these skewed algorithms can increase disparities in health outcomes between groups rather than improving outcomes, particularly because models tend to perform best on data that are most like the data they were trained with. Improving the diversity in patient data used to train models and validating models across various populations could mitigate this challenge and provide models that are more generalizable to a heterogeneous patient population. Additionally, the creation and use of large datasets needed to create AI models pose the challenging questions of data ownership and patient privacy, particularly in reference to medical imaging. At the same time, the integration of AI systems in medical practices raises questions about the security and confidentiality of sensitive patient data. Ensuring robust data protection mechanisms is imperative to prevent unauthorized access and potential misuse of personal health information.”
    From Machine Learning to Patient Outcomes: A Comprehensive Review of AI in Pancreatic Cancer.  
    Tripathi S, et al.  
    Diagnostics (Basel). 2024 Jan 12;14(2):174. doi: 10.3390/diagnostics14020174. PMID: 38248051;
  • “Pancreatic cancer is a complicated disease with molecular heterogeneity. Integrating multi-omics data, such as genomes, transcriptomics, proteomics, and metabolomics, can offer a complete picture of the disease pathology. Future research should concentrate on building artificial intelligence algorithms capable of assessing and combining these disparate datasets in order to uncover strong molecular signatures, biomarkers, and therapeutic targets for pancreatic cancer.”
    From Machine Learning to Patient Outcomes: A Comprehensive Review of AI in Pancreatic Cancer.  
    Tripathi S, et al.  
    Diagnostics (Basel). 2024 Jan 12;14(2):174. doi: 10.3390/diagnostics14020174. PMID: 38248051;
  • “Current guidance for pancreatic cancer surveillance is restricted to high-risk individuals (HRIs) who have germline mutations that predispose to a lifetime increased risk of pancreatic cancer or a strong family history of pancreatic cancer. When a pancreatic cyst is detected incidentally by abdominal imaging, such patients are often put in the HRI category for surveillance. Cumulatively, HRIs account for only about 20–25% of cases. What about the majority of patients with no risk factors who present at an advanced stage? This is where advances in artificial intelligence (AI) based on mining of electronic health records (EHRs) have started to show some promise. ”
    Early detection of pancreatic cancer and AI risk partitioning.
    Maitra A, Topol EJ.  
    Lancet. 2024 Apr 13;403(10435):1438. doi: 10.1016/S0140-6736(24)00690-1. PMID: 38615682. 
  • “ It is important to emphasize that these are retrospective studies and have not yet been evaluated prospectively in a real-world setting. Nonetheless, such research provides a potential roadmap for early detection of pancreatic cancer that extends beyond the current narrow definition of HRIs by enriching the general population with a larger proportion of individuals at “sporadic” risk who are identified through the mining of EHR data (figure). If prospective studies support this approach, this enriched population could then undergo longitudinal surveillance using liquid biopsy tools (circulating tumour DNA, methylation assays, or proteins) that are being deployed in the context of early detection of multiple cancers.”  
    Early detection of pancreatic cancer and AI risk partitioning.
    Maitra A, Topol EJ.  
    Lancet. 2024 Apr 13;403(10435):1438. doi: 10.1016/S0140-6736(24)00690-1. PMID: 38615682.  
  •  ”The contribution of AI does not stop at the initial EHR-based enrichment step since deep learning models are also being developed to improve the resolution of CT and MRI imaging scans for the detection of early, subcentimetric cancers in the pancreas. In addition to changes within the pancreas, these computational algorithms could also identify subtle changes in body composition (eg, attenuation of visceral fat and muscle) that may be missed by clinicians. With such surveillance of a high-risk group, early diagnosis would be enabled, as would the potential for improving outcomes, with treatment including surgical resection followed by emerging immunotherapy options, such as personalised vaccines. Therein lies the opportunity for AI support to help advance diagnosis and care for pancreatic cancer. ”
    Early detection of pancreatic cancer and AI risk partitioning.
    Maitra A, Topol EJ.  
    Lancet. 2024 Apr 13;403(10435):1438. doi: 10.1016/S0140-6736(24)00690-1. PMID: 38615682.  
  • “ In a study that used a transformer AI model that incorporated time sequence data of longitudinal EHRs over several years, an aggregate of nearly 28 000 cases of pancreatic cancer were analyzed and compared with 11 million patients who did not develop this disease. The primary dataset was from over 6 million patients in a Danish national registry, and findings were subsequently validated in an additional 3 million patients in the US Veterans Affairs system. The authors were able define a group of people among those aged 50 years and older who had a 30–60 times higher risk than the general population of being diagnosed with pancreatic cancer within the next 12 months. One of the EHR diagnostic codes that the model consistently identified as a feature predictive of incident pancreatic cancer within the next 24 months was diabetes, reinforcing the established link between new-onset diabetes and underlying pancreatic cancer. A second independent study used AI to differentiate the approximately 35 000 patients who developed pancreatic cancer from 1·5 million people who did not. This study identified over 80 features derived from EHRs, laboratory tests, symptoms, medications, and coexisting conditions that defined increased risk. Some of the features within the algorithm are intuitive, such as age or diabetes, whereas others underscore how AI can identify patterns not readily discernible by human assessment (eg, mean corpuscular haemoglobin concentration in red blood cells).”
    Early detection of pancreatic cancer and AI risk partitioning.
    Maitra A, Topol EJ.  
    Lancet. 2024 Apr 13;403(10435):1438. doi: 10.1016/S0140-6736(24)00690-1. PMID: 38615682. 
  • “The challenges faced during implementation are to ensure that data used by AI systems are accurate, complete, and interoperable across different healthcare systems. In addition, other challenges include navigating complex regulatory frameworks, gaining acceptance from healthcare professionals who may be skeptical about relying on AI recommendations for patient care, balancing the costs associated with implementing AI solutions against the expected benefits, and demonstrating a clear ROI. These challenges require collaboration among healthcare professionals, technology developers, policymakers, and regulatory bodies to create a supportive and secure environment for the integration of AI in healthcare workflows.”
    From Machine Learning to Patient Outcomes: A Comprehensive Review of AI in Pancreatic Cancer.  
    Tripathi S, et al.  
    Diagnostics (Basel). 2024 Jan 12;14(2):174. doi: 10.3390/diagnostics14020174. PMID: 38248051;
  • Purpose Delay in diagnosis can contribute to poor outcomes in pancreatic ductal adenocarcinoma (PDAC), and new tools for early detection are required. Recent application of artificial intelligence to cancer imaging has demonstrated great potential in detecting subtle early lesions. The aim of the study was to evaluate global and local accuracies of deep neural network (DNN) segmentation of normal and abnormal pancreas with pancreatic mass. Methods Our previously developed and reported residual deep supervision network for segmentation of PDAC was applied to segment pancreas using CT images of potential renal donors (normal pancreas) and patients with suspected PDAC (abnormal pancreas). Accuracy of DNN pancreas segmentation was assessed using DICE simulation coefficient (DSC), average symmetric surface distance (ASSD), and Hausdorff distance 95% percentile (HD95) as compared to manual segmentation. Furthermore, two radiologists semi-quantitatively assessed local accuracies and estimated volume of correctly segmented pancreas.
    Deep neural network-based segmentation of normal and abnormal pancreas on abdominal CT: evaluation of global and local accuracies.  
    Kawamoto S, Zhu Z, Chu LC, Javed AA, Kinny-Köster B, Wolfgang CL, Hruban RH, Kinzler KW, Fouladi DF, Blanco A, Shayesteh S, Fishman EK.  
    Abdom Radiol (NY). 2024 Feb;49(2):501-511
  • Methods Our previously developed and reported residual deep supervision network for segmentation of PDAC was applied to segment pancreas using CT images of potential renal donors (normal pancreas) and patients with suspected PDAC (abnormal pancreas). Accuracy of DNN pancreas segmentation was assessed using DICE simulation coefficient (DSC), average symmetric surface distance (ASSD), and Hausdorff distance 95% percentile (HD95) as compared to manual segmentation. Furthermore, two radiologists semi-quantitatively assessed local accuracies and estimated volume of correctly segmented pancreas.
    Deep neural network-based segmentation of normal and abnormal pancreas on abdominal CT: evaluation of global and local accuracies.  
    Kawamoto S, Zhu Z, Chu LC, Javed AA, Kinny-Köster B, Wolfgang CL, Hruban RH, Kinzler KW, Fouladi DF, Blanco A, Shayesteh S, Fishman EK.  
    Abdom Radiol (NY). 2024 Feb;49(2):501-511
  • Results Forty-two normal and 49 abnormal CTs were assessed. Average DSC was 87.4  ± 3.1% and 85.5 ± 3.2%, ASSD 0.97 ± 0.30 and 1.34 ± 0.65, HD95 4.28 ± 2.36 and 6.31 ± 6.31 for normal and abnormal pancreas, respectively. Semiquantitatively, ≥95% of pancreas volume was correctly segmented in 95.2% and 53.1% of normal and abnormal pancreas by both radiologists, and 97.6% and 75.5% by at least one radiologist. Most common segmentation errors were made on pancreatic and duodenal borders in both groups, and related to pancreatic tumor including duct dilatation, atrophy, tumor infiltration and collateral vessels. Conclusion Pancreas DNN segmentation is accurate in a majority of cases, however, minor manual editing may be necessary; particularly in abnormal pancreas.
    Deep neural network-based segmentation of normal and abnormal pancreas on abdominal CT: evaluation of global and local accuracies.  
    Kawamoto S, Zhu Z, Chu LC, Javed AA, Kinny-Köster B, Wolfgang CL, Hruban RH, Kinzler KW, Fouladi DF, Blanco A, Shayesteh S, Fishman EK.  
    Abdom Radiol (NY). 2024 Feb;49(2):501-511
  • “Pancreas DNN segmentation is accurate in a majority of cases, however, minor manual editing may be necessary; particularly in abnormal pancreas.” .
    Deep neural network-based segmentation of normal and abnormal pancreas on abdominal CT: evaluation of global and local accuracies.  
    Kawamoto S, Zhu Z, Chu LC, Javed AA, Kinny-Köster B, Wolfgang CL, Hruban RH, Kinzler KW, Fouladi DF, Blanco A, Shayesteh S, Fishman EK.  
    Abdom Radiol (NY). 2024 Feb;49(2):501-511
  • “Development of the algorithms using deep learning to automatically detect the pancreas and PDAC on CT scans is dependent on the quality of data input and therefore, it is vital to have high-quality annotated data to maximize their performance and clinical utility. The accuracy of manual segmenting the pancreas on CT images is one factor that can affect performance and reproducibility. Segmentation of the pancreas and other abdominal organs for supervised learning in particular via the manual approach is tedious, time consuming, and requires experienced radiologists. Furthermore, it is operator dependent with inter-observer and intra-observer variability being recognized as issues for manual segmentation.”
    Deep neural network-based segmentation of normal and abnormal pancreas on abdominal CT: evaluation of global and local accuracies.  
    Kawamoto S, Zhu Z, Chu LC, Javed AA, Kinny-Köster B, Wolfgang CL, Hruban RH, Kinzler KW, Fouladi DF, Blanco A, Shayesteh S, Fishman EK.  
    Abdom Radiol (NY). 2024 Feb;49(2):501-511

  • Deep neural network-based segmentation of normal and abnormal pancreas on abdominal CT: evaluation of global and local accuracies.  
    Kawamoto S, Zhu Z, Chu LC, Javed AA, Kinny-Köster B, Wolfgang CL, Hruban RH, Kinzler KW, Fouladi DF, Blanco A, Shayesteh S, Fishman EK.  
    Abdom Radiol (NY). 2024 Feb;49(2):501-511

  • Deep neural network-based segmentation of normal and abnormal pancreas on abdominal CT: evaluation of global and local accuracies.  
    Kawamoto S, Zhu Z, Chu LC, Javed AA, Kinny-Köster B, Wolfgang CL, Hruban RH, Kinzler KW, Fouladi DF, Blanco A, Shayesteh S, Fishman EK.  
    Abdom Radiol (NY). 2024 Feb;49(2):501-511

  • Deep neural network-based segmentation of normal and abnormal pancreas on abdominal CT: evaluation of global and local accuracies.  
    Kawamoto S, Zhu Z, Chu LC, Javed AA, Kinny-Köster B, Wolfgang CL, Hruban RH, Kinzler KW, Fouladi DF, Blanco A, Shayesteh S, Fishman EK.  
    Abdom Radiol (NY). 2024 Feb;49(2):501-511
  • ”Deep neural network segmentation of the pancreas is more difficult compared to other abdominal organs including liver, spleen, kidneys, and gallbladder. This difficulty may be related to poor boundary and low contrast of pancreas from adjacent organs (e.g., duodenum, vessels) and large variation of its shape and size compared to other organs. For example, pancreas with fatty infiltration with scattered fat within and along the surface of the pancreas is difficult to manually segment accurately due to irregularly lobulated contour. It is also difficult to accurately segment pancreas border with poor contrast organs such as the duodenum particularly in thin patients with poor fat planes.”
    Deep neural network-based segmentation of normal and abnormal pancreas on abdominal CT: evaluation of global and local accuracies.  
    Kawamoto S, Zhu Z, Chu LC, Javed AA, Kinny-Köster B, Wolfgang CL, Hruban RH, Kinzler KW, Fouladi DF, Blanco A, Shayesteh S, Fishman EK.  
    Abdom Radiol (NY). 2024 Feb;49(2):501-511
  • Deep neural network segmentation of abnormal pancreas was more challenging. In abnormal pancreata with a variety of pancreatic masses, deep neural network prediction of the pancreas was less accurate than normal pancreas with average DSC of 85.5%. It is likely due to various size, shape, and locations of pancreatic masses, and unpredicted changes in shape and geometry in the pancreas upstream from the pancreatic masses .In our cases, however, only minor errors were observed in many cases. By visual assessment using the scores, 53.1% of cases were score 9 or higher by both radiologists, and 75.5% by at least one radiologist in which more than 95% of volume of the pancreas and pancreatic mass together was correctly segmented.
    Deep neural network-based segmentation of normal and abnormal pancreas on abdominal CT: evaluation of global and local accuracies.  
    Kawamoto S, Zhu Z, Chu LC, Javed AA, Kinny-Köster B, Wolfgang CL, Hruban RH, Kinzler KW, Fouladi DF, Blanco A, Shayesteh S, Fishman EK.  
    Abdom Radiol (NY). 2024 Feb;49(2):501-511 
  • In conclusion, our study found that segmentation of the pancreas using deep neural network is accurate and can be applied for AI based volumetric analyses in the majority of the cases. Minor manual editing may be necessary, more commonly in cases with pancreatic pathology. Further study using a larger number of cases with different CT equipment and protocol variation is needed to generalize the pancreatic segmentation model that would be used to further improvement of algorithms.  
    Deep neural network-based segmentation of normal and abnormal pancreas on abdominal CT: evaluation of global and local accuracies.  
    Kawamoto S, Zhu Z, Chu LC, Javed AA, Kinny-Köster B, Wolfgang CL, Hruban RH, Kinzler KW, Fouladi DF, Blanco A, Shayesteh S, Fishman EK.  
    Abdom Radiol (NY). 2024 Feb;49(2):501-511 
  • “Moreover, AI is playing a crucial role in personalized medicine. By analyzing large datasets that include patient health records, genetic information, and treatment outcomes, AI algorithms can identify patterns and correlations that help tailor treatment plans to individual patients. This enables healthcare providers to deliver targeted therapies, predict disease progression, and reduce adverse effects. Additionally, AI is streamlining administrative tasks and improving operational efficiency in healthcare facilities. Natural language processing (NLP) algorithms can automate tasks like medical coding and documentation, reducing the burden on healthcare professionals and minimizing errors. AI chatbots are being used to provide patients with round-the-clock assistance, answer their queries, schedule appointments, and even provide basic medical advice.”
    From Machine Learning to Patient Outcomes: A Comprehensive Review of AI in Pancreatic Cancer
    Satvik Tripathi et al.
    Diagnostics 2024, 14, 174. https://doi.org/10.3390/diagnostics14020174

  • From Machine Learning to Patient Outcomes: A Comprehensive Review of AI in Pancreatic Cancer
    Satvik Tripathi et al.
    Diagnostics 2024, 14, 174. https://doi.org/10.3390/diagnostics1402017
  • “Overall, ML techniques, including supervised learning algorithms like support vector machines and random forests, as well as unsupervised learning techniques like clustering and dimensionality reduction, are very valuable in pancreatic cancer research. They enable researchers to extract meaningful insights from complex datasets, improve diagnostic accuracy, predict patient outcomes, and facilitate personalized treatment strategies.”  
    From Machine Learning to Patient Outcomes: A Comprehensive Review of AI in Pancreatic Cancer
    Satvik Tripathi et al.
    Diagnostics 2024, 14, 174. https://doi.org/10.3390/diagnostics14020174
  • “We can also utilize CNNs for lesion detection and localization for automated identification of anomalous or dubious regions in medical imagery. The application of computer vision techniques in pancreatic cancer research has the potential to facilitate the identification and localization of pancreatic tumors and other lesions. Through the automated identification of these regions, medical professionals can concentrate their efforts on the specific areas of concern, thereby enabling enhanced precision in diagnosis and treatment strategizing. These algorithms can also help classify tumors into distinct subtypes or determine their malignancy by extracting pertinent features from medical images, such as texture, shape, or intensity patterns. These extracted data hold significant value in terms of prognostication, informing treatment choices, and forecasting patient results.”
    From Machine Learning to Patient Outcomes: A Comprehensive Review of AI in Pancreatic Cancer
    Satvik Tripathi et al.
    Diagnostics 2024, 14, 174. https://doi.org/10.3390/diagnostics14020174
  • “The early detection of pancreatic cancer is a critical factor in improving patient outcomes, as it is often diagnosed at an advanced stage when treatment options are limited. AI has the potential to aid in the early detection of pancreatic cancer by analyzing medical data and identifying patterns that may indicate the presence of the disease. Deep learning techniques can be trained on large datasets to accurately identify early stage pancreatic cancer based on characteristic imaging features or use morphology features to build segmentation frameworks for the pancreas. AI algorithms can integrate various patient data, such as age, family history, lifestyle factors, and medical history, to detect an individual’s developing pancreatic cancer early. AI can also analyze a patient’s electronic health records, including medical history, laboratory results, and diagnostic reports, to identify potential indicators of pancreatic cancer. By processing and interpreting vast amounts of data, AI algorithms can detect subtle patterns and abnormalities that may go unnoticed by clinicians.”
    From Machine Learning to Patient Outcomes: A Comprehensive Review of AI in Pancreatic Cancer
    Satvik Tripathi et al.
    Diagnostics 2024, 14, 174. https://doi.org/10.3390/diagnostics14020174
  • However, finding reliable and specific biomarkers for pancreatic cancer is challenging due to the heterogeneity and complexity of the disease, the lack of adequate samples, and the interference of confounding factors . AI can help overcome these challenges by applying advanced computational methods to analyze large and diverse datasets of biomolecular information, such as genomics, proteomics, metabolomics, or microbiomics. AI can also integrate multiple types of data from the pancreas to identify novel biomarkers or biomarker signatures that have higher sensitivity and specificity than single biomarkers . A deep learning model based on multimodal neural networks (MNNs) was proposed to combine imaging data (WSI), gene expression data, clinical data (age, gender, tumor location), and biomarker data (mi-RNA) to forcast the survival of pancreatic cancerpatients.
    From Machine Learning to Patient Outcomes: A Comprehensive Review of AI in Pancreatic Cancer
    Satvik Tripathi et al.
    Diagnostics 2024, 14, 174. https://doi.org/10.3390/diagnostics14020174 
  • “AI can serve as a powerful tool in the advancement of pancreatic cancer diagnosis, management, and prognosis, particularly in identifying tumors earlier in disease progression. Despite the many applications and advantages of AI in pancreatic cancer, multiple limitations pose challenges that must be addressed as the field grows. One is the lack of a standardized approach to treatment and diagnosis. Other challenges include a lack of robust and high-quality data, transparency and reproducibility of findings, and ethical considerations, including biases in algorithms.”
    From Machine Learning to Patient Outcomes: A Comprehensive Review of AI in Pancreatic Cancer
    Satvik Tripathi et al.
    Diagnostics 2024, 14, 174. https://doi.org/10.3390/diagnostics14020174
  • “Furthermore, AI algorithms have been previously referred to as “Black boxes” due to their lack of transparency and interpretability. The opacity of the code used to build AI models and the hidden level of complexity make it difficult to reproduce results in an independent manner. General descriptions of the code used to build models do not provide enough information to reproduce most findings. The lack of easy interpretation of these AI models and prospective studies assessing AI-based tools has increased the hesitancy of adaptation into clinical practice. Without transparency andinterpretation, clinicians are not able to critically interrogate the output of these models, putting an incredible amount of faith in the accuracy of the model.”  
    From Machine Learning to Patient Outcomes: A Comprehensive Review of AI in Pancreatic Cancer
    Satvik Tripathi et al.
    Diagnostics 2024, 14, 174. https://doi.org/10.3390/diagnostics14020174
  • “Additionally, the creation and use of large datasets needed to create AI models pose the challenging questions of data ownership and patient privacy, particularly inreference to medical imaging. At the same time, the integration of AI systems in medical practices raises questions about the security and confidentiality of sensitive patient data. Ensuring robust data protection mechanisms is imperative to prevent unauthorized access and potential misuse of personal health information. Additionally, ethical challenges encompass issues such as algorithmic bias, transparency, and accountability. Addressing these challenges requires the establishment of ethical guidelines and regulatory frameworks that prioritize fairness, transparency, and the responsible use of AI technologies. Striking a balance between innovation and ethical considerations is essential to foster public trust and promote the responsible adoptionof AI in healthcare, ultimately ensuring that advancements in technology benefit patientswithout compromising their privacy or perpetuating existing healthcare disparities.” 
  • “Additionally, ethical challenges encompass issues such as algorithmic bias, transparency, and accountability. Addressing these challenges requires the establishment of ethical guidelines and regulatory frameworks that prioritize fairness, transparency, and the responsible use of AI technologies. Striking a balance between innovation and ethical considerations is essential to foster public trust and promote the responsible adoptionof AI in healthcare, ultimately ensuring that advancements in technology benefit patientswithout compromising their privacy or perpetuating existing healthcare disparities.”
    From Machine Learning to Patient Outcomes: A Comprehensive Review of AI in Pancreatic Cancer
    Satvik Tripathi et al.
    Diagnostics 2024, 14, 174. https://doi.org/10.3390/diagnostics14020174
  • In order to convert AI research into clinical practice, robust validation studies in pancreatic cancer are required to establish the clinical efficacy, safety, and cost-effectiveness of AI-based methods. Large-scale prospective studies should be conducted in the future to evaluate the performance of AI algorithms in realworld healthcare situations. Furthermore, regulatory and ethical factors such as privacy protection, informed consent, and algorithm transparency must be addressed to enable responsible and fair AI technology implementation in healthcare.  
    From Machine Learning to Patient Outcomes: A Comprehensive Review of AI in Pancreatic Cancer
    Satvik Tripathi et al.
    Diagnostics 2024, 14, 174. https://doi.org/10.3390/diagnostics14020174
  • • [18F] Fluorodeoxyglucose18F-FDG) PET/CT can improve the staging accuracy and clinical management of patients with hepatobiliary and pancreatic cancers, by detection of unsuspected metastases.  
    • 18F-FDG PET/CT metabolic parameters are valuable in predicting treatment response and survival.  
    • Metabolic response on 18F-FDG PET/CT can predict preoperative pathologic response to neoadjuvant therapy in patients with pancreatic cancer and determine prognosis.  
    • Several novel non-FDG tracers, such as 68-Ga prostate-specific membrane antigen and 68Gafibroblast activation protein inhibitor PET/CT, show promise for imaging hepatobiliary and pancreatic cancers with potential for radioligand therapy.
    Quarter-Century PET/ Tomography Transformation of Oncology Hepatobiliary and Pancreatic Cancer
    Asha Kandathil et al.
    PET Clin (in press) 2024
  • “18F-FDG PET/CT has reported sensitivity of 85%to 100%, specificity of 61% to 94%, and accuracy of 84% to 95% in diagnosing pancreatic cancer.39–42 FDG uptake by pancreatic cancer correlates with increased Ki-67 and is highest in poorly differentiated tumors. Medium- or well-differentiated pancreatic cancers may not have increased FDG uptake. Inflammatory lesions such as chronic lymphoplasmacytic pancreatitis, autoimmune pancreatitis, and tuberculosis may have increased FDG uptake.”  
    Quarter-Century PET/ Tomography Transformation of Oncology Hepatobiliary and Pancreatic Cancer
    Asha Kandathil et al.
    PET Clin (in press) 2024
  • In a multicenter prospective study conducted in 18 UK pancreatic tertiary referral centers, Ghaneh and colleagues evaluated the performance of multidetector CT (MDCT) in 589 patients and FDG PET/CT in 550 patients with suspected pancreatic cancer. MDCT had a sensitivity of 88.5%and specificity of 70.6%; FDG PET/CT had a sensitivity of 92.7% and specificity of 75.8% for the diagnosis of pancreatic cancer. Pancreatic cancer had a higher median SUVmax of 7.5 compared with median SUVmax of 5.7 for other lesions. Adding PET/ CT to standard workup improved pancreatic cancer diagnosis, staging, and management.
    Quarter-Century PET/ Tomography Transformation of Oncology Hepatobiliary and Pancreatic Cancer
    Asha Kandathil et al.
    PET Clin (in press) 2024
  • “Surgical resection is the only curative option for pancreatic cancer; however, more than 80% of patients present unresectable disease due to locally advanced disease or distant metastases. Borderline resectable pancreatic cancer (BRPC) patients who could be eligible for radical surgery following neoadjuvant chemotherapy may have local arterial or venous (superior mesenteric vein/ portal vein) invasion.44 PET has less spatial resolution and accuracy than CT in assessing locoregional involvement, which is critical in therapeutic decision-making in pancreatic cancer. CT, MR imaging, and endoscopic ultrasound are better at defining tumor’s border and local spread.45 However, PET/CT performs better than CT in identifying unsuspected metastases, reducing the frequency of futile surgeries.”
    Quarter-Century PET/ Tomography Transformation of Oncology Hepatobiliary and Pancreatic Cancer
    Asha Kandathil et al.
    PET Clin (in press) 2024
  • “In a study of the utility of 18F-FDG PET/CT in assessing treatment response in 20 patients with LAPC treated with neoadjuvant chemo-RT, Choi and colleagues observed that mean survival was longer (23.2 months) in patients with   50% decrease in SUV between pre-study PET scan and PET scan after the first cycle of chemotherapy, as compared with 11.3 months in patients with less than 50% decrease in SUV.”  
    Quarter-Century PET/ Tomography Transformation of Oncology Hepatobiliary and Pancreatic Cancer
    Asha Kandathil et al.
    PET Clin (in press) 2024
  • In conclusion, we have established a radiomics model for predicting early recurrence after upfront surgery in patients with resectable PDAC. The result of this study may provide evidence based on preoperative radiographic imaging for surgeons to make better individual therapeutic choice by selecting patients at high risk of early recurrence who may benefit from neoadjuvant therapy.
    Preoperative evaluating early recurrence in resectable pancreatic ductal adenocarcinoma by using CT radiomics
    Gang Wang · Weijie Lei · Shaofeng Duan · Aihong Cao · Hongyuan Shi
    Abdominal Radiology https://doi.org/10.1007/s00261-023-04074-x
  • Objective: To investigate the feasibility of a radiomics model based on contrast-enhanced CT for preoperatively predicting early recurrence after curative resection in patients with resectable pancreatic ductal adenocarcinoma (PDAC).
    Methods: One hundred and eighty-six patients with resectable PDAC who underwent curative resection were included and allocated to training set (131 patients) and validation set (55 patients). Radiomics features were extracted from arterial phase
    and portal venous phase images. The Mann-Whitney U test and least absolute shrinkage and selection operator (LASSO) regression were used for feature selection and radiomics signature construction. The radiomics model based on radiomics
    signature and clinical features was developed by the multivariate logistic regression analysis. Performance of the radiomics model was investigated by the area under the receiver operating characteristic (ROC) curve.
    Results: The radiomics signature, consisting of three arterial phase and three venous phase features, showed optimal prediction performance for early recurrence in both training (AUC = 0.73) and validation sets (AUC = 0.66). Multivariate logistic
    analysis identified the radiomics signature (OR, 2.58; 95% CI 2.36–3.17; p = 0.002) and clinical stage (OR, 1.60; 95% CI 1.15–2.30; p = 0.007) as independent predictors. The AUC values for risk evaluation of early recurrence using the radiomics
    model incorporating clinical stage were 0.80 (training set) and 0.75 (validation set).
    Conclusion: The radiomics-based model integrating with clinical stage can predict early recurrence after upfront surgery in patients with resectable PDAC.
    Preoperative evaluating early recurrence in resectable pancreatic
    ductal adenocarcinoma by using CT radiomics
    Gang Wang1 · Weijie Lei1 · Shaofeng Duan2 · Aihong Cao3 · Hongyuan Shi4
    Abdominal Radiology https://doi.org/10.1007/s00261-023-04074-x
  • “In this study, we investigated the ability of preoperative contrast-enhanced CT-based radiomics analysis to predict early recurrence in patients with resectable PDAC. Previous prediction models had limited clinical applicability because of the inclusion of pathologic or postoperative variables not applicable to the preoperative setting. Our results demonstrated that the radiomics signature with clinical stage showed excellent performance for predicting early recurrence. The determining of early recurrence for resectable PDAC is significant because early recurrence means that the upfront surgery performed is likely to have been of little benefit to the patient, who may benefit from neoadjuvant therapy.”
    Preoperative evaluating early recurrence in resectable pancreatic ductal adenocarcinoma by using CT radiomics
    Gang Wang · Weijie Lei · Shaofeng Duan · Aihong Cao · Hongyuan Shi
    Abdominal Radiology https://doi.org/10.1007/s00261-023-04074-x
  • In conclusion, we have established a radiomics model for predicting early recurrence after upfront surgery in patients with resectable PDAC. The result of this study may provide evidence based on preoperative radiographic imaging for surgeons to make better individual therapeutic choice by selecting patients at high risk of early recurrence who may benefit from neoadjuvant therapy.
    Preoperative evaluating early recurrence in resectable pancreatic ductal adenocarcinoma by using CT radiomics
    Gang Wang · Weijie Lei · Shaofeng Duan · Aihong Cao · Hongyuan Shi
    Abdominal Radiology https://doi.org/10.1007/s00261-023-04074-x
  • Pancreatic ductal adenocarcinoma (PDAC), the most deadly solid malignancy, is typically detected late and at an inoperable stage. Early or incidental detection is associated with prolonged survival, but screening asymptomatic individuals for PDAC using a single test remains unfeasible due to the low prevalence and potential harms of false positives. Non-contrast computed tomography (CT), routinely performed for clinical indications, offers the potential for large-scale screening, however, identification of PDAC using non-contrast CT has long been considered impossible. Here, we develop a deep learning approach, pancreatic cancer detection with artificial intelligence (PANDA), that can detect and classify pancreatic lesions with high accuracy via non-contrast CT. PANDA is trained on a dataset of 3,208 patients from a single center. PANDA achieves an area under the receiver operating characteristic curve (AUC) of 0.986–0.996 for lesion detection in a multicenter validation involving 6,239 patients across 10 centers, outperforms the mean radiologist performance by 34.1% in sensitivity and 6.3% in specificity for PDAC identification, and achieves a sensitivity of 92.9% and specificity of 99.9% for lesion detection in a real-world multi-scenario validation consisting of 20,530 consecutive patients. Notably, PANDA utilized with non-contrast CT shows non-inferiority to radiology reports (using contrast-enhanced CT) in the differentiation of common pancreatic lesion subtypes. PANDA could potentially serve as a new tool for large-scale pancreatic cancer screening.
    Large-scale pancreatic cancer detection via non-contrast CT and deep learning
    Kai Cao,Yingda Xia, Jiawen Yao,et al.
    Nature Medicine https://doi.org/10.1038/s41591-023-02640-w
  • “PANDA is trained on a continual learning approach using multicenter data, but includes only limited data outside the East Asian population and hospitals. The model should be further validated in external real-world centers, more international cohorts, and prospective studies. PANDA exhibited relatively low accuracy for PNET. PNET tumors are rare and highly diverse in appearance, and the model may primarily miss some cases with very low image contrast in non-contrast CT.”
    Large-scale pancreatic cancer detection via non-contrast CT and deep learning
    Kai Cao,Yingda Xia, Jiawen Yao,et al.
    Nature Medicine https://doi.org/10.1038/s41591-023-02640-w
  • “PANDA is an interpretable deep model that outputs the lesion boundaries and lesion subtype probabilities. Although radiologists usually do not diagnose pancreatic lesions from non-contrast CT alone, when assisted by PANDA their performance could be drastically increased regardless of experience, especially for the task of PDAC identification. Radiology residents with less experience benefit the most from PANDA’s assistance, and can reach a level comparable with pancreas specialists. Although general radiologists might still doubt the AI results, their performance could be improved to a level close to that of pancreas specialists. Note that non-contrast CT is widely performed in non-tertiary hospitals and physical examination centers, where radiologists are usually less experienced or not specialized in pancreas imaging diagnosis. In tertiary hospitals, non-contrast CT is commonly performed as well, such as chest CT for lung nodule detection and abdominal CT in the emergency room. Taken together, PANDA could be widely used to increase the level of pancreas cancer diagnosis expertise in medical centers, especially by detecting more pancreatic malignancies at an earlier stage.”  
    Large-scale pancreatic cancer detection via non-contrast CT and deep learning
    Kai Cao,Yingda Xia, Jiawen Yao,et al.
    Nature Medicine https://doi.org/10.1038/s41591-023-02640-w
  • “Fourth, the model has been tuned to yield a 99% specificity during cross-validation on the large training set (n = 3,208), to achieve reliable control of false positives. Fifth, the AI model’s continual learning enhances specificity to 99.9% by fine-tuning with false positives from external centers and the real world. And last, regarding training data, the cases and controls have similar CT imaging protocols (for example, slice thickness, CT dose index, oral water), thereby forcing the model to focus on the primary learning objectives rather than fitting to shortcuts or confounders.”  
    Large-scale pancreatic cancer detection via non-contrast CT and deep learning
    Kai Cao,Yingda Xia, Jiawen Yao,et al.
    Nature Medicine https://doi.org/10.1038/s41591-023-02640-w
  • “We present PANDA, an AI model that detects the seven most common pancreatic lesions and ‘other’, and diagnoses the lesion subtypes in routine non-contrast CT scans. This task has long been considered impossible for radiologists and, as such, contrast-enhanced CT and/ or MRI and endoscopic ultrasound (EUS) have been used as the recognized and recommended diagnostic imaging modalities. We show that by curating a large dataset covering common pancreatic lesion types confirmed by pathology, transferring lesion annotations from contrast-enhanced to non-contrast CT, designing a deep learning approach that incorporates a cascade network architecture for lesion detection and a memory transformer for pancreas lesion diagnostic information modeling, and learning from the real-world feedback, PANDA, which uses only non-contrast CT as input, achieves high sensitivity and exceptionally high specificity in the detection of pancreatic lesions, with a significantly higher accuracy than radiologists in the primary diagnosis between PDAC and non-PDAC, and non-inferior accuracy to radiology reports in the differential diagnosis of the eight aforementioned pancreatic lesion subtypes.”
    Large-scale pancreatic cancer detection via non-contrast CT and deep learning
    Kai Cao,Yingda Xia, Jiawen Yao,et al.
    Nature Medicine https://doi.org/10.1038/s41591-023-02640-w
  • PANDA achieved an AUC of 0.984 (95% CI 0.980–0.987, Fig. 2a), sensitivity of 93.3% (95% CI 92.5–94.1%) and specificity of 98.8% (95% CI 98.3–99.4%) for lesion detection. For the PDAC patient subgroup, the detection rate was 96.5%n(95% CI 95.8–97.2%) overall, 95.6% (95% CI 93.9–97.0%; Fig. 2c) for stage I, and 96.5% (95% CI 95.3–97.8%; Fig. 2c) for stage II. For small PDAC lesions (diameter <2 cm, T1 stage), the sensitivity for detection was 92.2% (95% CI 89.0–95.4%; n = 283; Fig. 2c). The lesion detection results for each center are shown in Fig. 2d and the performance stratified by lesion subtype is given in Fig. 2e. For PDAC identification, the sensitivity was 90.1% (95% CI 89.0–91.2%) and the specificity was 95.7% (95% CI94.9–96.5%;.  
    Large-scale pancreatic cancer detection via non-contrast CT and deep learning
    Kai Cao,Yingda Xia, Jiawen Yao,et al.
    Nature Medicine https://doi.org/10.1038/s41591-023-02640-w
  • PANDA (on non-contrast CT imaging) did better than the mean performance of the specialists (using contrast-enhanced  CT scans) by 2.9% (95% CI 0.1–5.8%, P = 0.0002 for non-inferiority) in sensitivity and by 2.1% (95% CI 1.4–3.0%, P = 0.0002 for difference) in specificity, for lesion detection (Supplementary Tables 10a and 11a); and by a margin of 13.0% (95% CI 8.5–17.8%, P = 0.0002 for difference) in sensitivity and 0.5% (95% CI −0.7 to 1.9%, P = 0.0002 for non-inferiority) in specificity, for PDAC identification .  
    Large-scale pancreatic cancer detection via non-contrast CT and deep learning
    Kai Cao,Yingda Xia, Jiawen Yao,et al.
    Nature Medicine https://doi.org/10.1038/s41591-023-02640-w
  • We present a deep learning model, PANDA, to detect and diagnose PDAC and seven subtypes of non-PDAC lesions (Methods), that is, pancreatic neuroendocrine tumor (PNET), solid pseudopapillary tumor (SPT), intraductal papillary mucinous neoplasm (IPMN), mucinous cystic neoplasm (MCN), serous cystic neoplasm (SCN), chronic pancreatitis, and ‘other’ from abdominal and chest non-contrast CT scans. Our model can detect the presence or absence of a pancreatic lesion, segment the lesion, and classify the lesion subtypes
    Large-scale pancreatic cancer detection via non-contrast CT and deep learning
    Kai Cao,Yingda Xia, Jiawen Yao,et al.
    Nature Medicine https://doi.org/10.1038/s41591-023-02640-w
  • Purpose: Delay in diagnosis can contribute to poor outcomes in pancreatic ductal adenocarcinoma (PDAC), and new tools for early detection are required. Recent application of artificial intelligence to cancer imaging has demonstrated great potential in detecting subtle early lesions. The aim of the study was to evaluate global and local accuracies of deep neural network (DNN) segmentation of normal and abnormal pancreas with pancreatic mass.
    Methods: Our previously developed and reported residual deep supervision network for segmentation of PDAC was applied to segment pancreas using CT images of potential renal donors (normal pancreas) and patients with suspected PDAC (abnormal pancreas). Accuracy of DNN pancreas segmentation was assessed using DICE simulation coefficient (DSC), average symmetric surface distance (ASSD), and Hausdorff distance 95% percentile (HD95) as compared to manual segmentation. Furthermore, two radiologists semi-quantitatively assessed local accuracies and estimated volume of correctly segmented pancreas.
    Deep neural network-based segmentation of normal and abnormal pancreas on abdominal CT: evaluation of global and local accuracies.  
    Kawamoto S, Zhu Z, Chu LC, Javed AA, Kinny-Köster B, Wolfgang CL, Hruban RH, Kinzler KW, Fouladi DF, Blanco A, Shayesteh S, Fishman EK.
    Abdom Radiol (NY). 2023 Dec 15. doi: 10.1007/s00261-023-04122-6. Epub ahead of print. PMID: 38102442.
  • Results: Forty-two normal and 49 abnormal CTs were assessed. Average DSC was 87.4 ± 3.1% and 85.5 ± 3.2%, ASSD 0.97 ± 0.30 and 1.34 ± 0.65, HD95 4.28 ± 2.36 and 6.31 ± 6.31 for normal and abnormal pancreas, respectively. Semi-quantitatively, ≥95% of pancreas volume was correctly segmented in 95.2% and 53.1% of normal and abnormal pancreas by both radiologists, and 97.6% and 75.5% by at least one radiologist. Most common segmentation errors were made on pancreatic and duodenal borders in both groups, and related to pancreatic tumor including duct dilatation, atrophy, tumor infiltration and collateral vessels.
    Conclusion: Pancreas DNN segmentation is accurate in a majority of cases, however, minor manual editing may be necessary; particularly in abnormal pancreas.
    Deep neural network-based segmentation of normal and abnormal pancreas on abdominal CT: evaluation of global and local accuracies.  
    Kawamoto S, Zhu Z, Chu LC, Javed AA, Kinny-Köster B, Wolfgang CL, Hruban RH, Kinzler KW, Fouladi DF, Blanco A, Shayesteh S, Fishman EK.
    Abdom Radiol (NY). 2023 Dec 15. doi: 10.1007/s00261-023-04122-6. Epub ahead of print. PMID: 38102442.
  •     “Development of the algorithms using deep learning to automatically detect the pancreas and PDAC on CT scans is dependent on the quality of data input and therefore, it is vital to have high-quality annotated data to maximize their performance and clinical utility. The accuracy of manual segmenting the pancreas on CT images is one factor that can affect performance and reproducibility. Segmentation of the pancreas and other abdominal organs for supervised learning in particular via the manual approach is tedious, time consuming, and requires experienced radiologists. Furthermore, it is operator dependent with inter-observer and intra-observer variability being recognized as issues for manual segmentation.”
    Deep neural network-based segmentation of normal and abnormal pancreas on abdominal CT: evaluation of global and local accuracies.  
    Kawamoto S, Zhu Z, Chu LC, Javed AA, Kinny-Köster B, Wolfgang CL, Hruban RH, Kinzler KW, Fouladi DF, Blanco A, Shayesteh S, Fishman EK.
    Abdom Radiol (NY). 2023 Dec 15. doi: 10.1007/s00261-023-04122-6. Epub ahead of print. PMID: 38102442.
  •  Among variations of deep neural networks, the ResDSN (residual deep supervision network) developed for pancreatic tumor segmentation was used. The ResDSN network was introduced by Zhu et al.  with residual connections and deep supervision to learn powerful pancreatic feature representations from 3D CT data. The ResDSN was intended for the automatic pancreas segmentation, and developed and trained on previously annotated CT data, which did not include the patients used in the current study (42 potential renal donors and the 49 patients with suspected PDAC). These cases were directly tested for the comparison of assessment between the deep neural network segmentation and the manual segmentation
    Deep neural network-based segmentation of normal and abnormal pancreas on abdominal CT: evaluation of global and local accuracies.  
    Kawamoto S, Zhu Z, Chu LC, Javed AA, Kinny-Köster B, Wolfgang CL, Hruban RH, Kinzler KW, Fouladi DF, Blanco A, Shayesteh S, Fishman EK.
    Abdom Radiol (NY). 2023 Dec 15. doi: 10.1007/s00261-023-04122-6. Epub ahead of print. PMID: 38102442.

  • Deep neural network-based segmentation of normal and abnormal pancreas on abdominal CT: evaluation of global and local accuracies.  
    Kawamoto S, Zhu Z, Chu LC, Javed AA, Kinny-Köster B, Wolfgang CL, Hruban RH, Kinzler KW, Fouladi DF, Blanco A, Shayesteh S, Fishman EK.
    Abdom Radiol (NY). 2023 Dec 15. doi: 10.1007/s00261-023-04122-6. Epub ahead of print. PMID: 38102442.
  • For abnormal pancreas cases, a part of the pancreas uninvolved by pancreatic mass was underpredicted by deep neural network prediction in 11 cases (22.4%), most commonly at the head or uncinate process of the pancreas, including one case of multiple collateral veins around the head of the pancreas secondary to portal vein/superior mesenteric vein occlusion by PDAC. In 6 cases (12.2%), uninvolved body and tail, or tail was excluded from prediction, including 3 cases of atrophic body and/or tail secondary to downstream PDAC (Fig. 7). In 13 cases (26.5%), non-pancreatic structures were predicted as the pancreas by deep neural network prediction, most commonly in the duodenum at the border between the head of the pancreas. Peripancreatic lymph nodes in 4 cases (8.2%), and left adrenal gland in 1 case (2.0%) were included in prediction in cases of infiltrating PDAC with poor fat planes between the pancreas and these structures.
    Deep neural network-based segmentation of normal and abnormal pancreas on abdominal CT: evaluation of global and local accuracies.  
    Kawamoto S, Zhu Z, Chu LC, Javed AA, Kinny-Köster B, Wolfgang CL, Hruban RH, Kinzler KW, Fouladi DF, Blanco A, Shayesteh S, Fishman EK.
    Abdom Radiol (NY). 2023 Dec 15. doi: 10.1007/s00261-023-04122-6. Epub ahead of print. PMID: 38102442.
  • “Deep neural network segmentation of the pancreas is more difficult compared to other abdominal organs including liver, spleen, kidneys, and gallbladder. This difficulty may be related to poor boundary and low contrast of pancreas from adjacent organs (e.g., duodenum, vessels) and large variation of its shape and size compared to other organs. For example, pancreas with fatty infiltration with scattered fat within and along the surface of the pancreas is difficult to manually segment accurately due to irregularly lobulated contour. It is also difficult to accurately segment pancreas border with poor contrast organs such as the duodenum particularly in thin patients with poor fat planes.”  
    Deep neural network-based segmentation of normal and abnormal pancreas on abdominal CT: evaluation of global and local accuracies.  
    Kawamoto S, Zhu Z, Chu LC, Javed AA, Kinny-Köster B, Wolfgang CL, Hruban RH, Kinzler KW, Fouladi DF, Blanco A, Shayesteh S, Fishman EK.
    Abdom Radiol (NY). 2023 Dec 15. doi: 10.1007/s00261-023-04122-6. Epub ahead of print. PMID: 38102442.
  •        “In conclusion, our study found that segmentation of the pancreas using deep neural network is accurate and can be applied for AI based volumetric analyses in the majority of the cases. Minor manual editing may be necessary, more commonly in cases with pancreatic pathology. Further study using a larger number of cases with different CT equipment and protocol variation is needed to generalize the pancreatic segmentation model that would be used to further improvement of algorithms.”  
    Deep neural network-based segmentation of normal and abnormal pancreas on abdominal CT: evaluation of global and local accuracies.  
    Kawamoto S, Zhu Z, Chu LC, Javed AA, Kinny-Köster B, Wolfgang CL, Hruban RH, Kinzler KW, Fouladi DF, Blanco A, Shayesteh S, Fishman EK.
    Abdom Radiol (NY). 2023 Dec 15. doi: 10.1007/s00261-023-04122-6. Epub ahead of print. PMID: 38102442.
  • “Radiomics of pancreatic CT and MR images has enhanced pancreatic ductal adenocarcinoma detection and its differentiation from pancreatic neuroendocrine tumors, mass-forming chronic pancreatitis, or autoimmune pancreatitis. Radiomics can further help to better characterize incidental pancreatic cystic lesions, accurately discriminating benign from malignant intrapancreatic mucinous neoplasms.”
    Radiomics in CT and MR imaging of the liver and pancreas: tools with potential for clinical application
    M. .lvaro Berbis et al.
    Abdominal Radiology (in press)
  • “This step consists of the generation of the ROI or VOI that defines the area of the image in which the radiomics features will be calculated (Fig. 3). In liver and pancreas images, this step is frequently performed via semi-automatic or manual methods. Several open-source applications (Slicer [11], MITK Workbench [10], CERR [12]) and freeware(LifEx[13]) allow the semi-automatic segmentation of lesions. Conversely, manual segmentation tools or tools that require the intervention of a specialist are limited by the bias they can potentially introduce in the model, as well as their need for considerable time and resources [14]. In these cases, inter-subject reproducibility must be evaluated and the characteristics that are not reproducible should be eliminated, as shown in the following sections.”
    Radiomics in CT and MR imaging of the liver and pancreas: tools with potential for clinical application
    M. lvaro Berbis et al.
    Abdominal Radiology (in press)
  • “Regarding pancreatic lesions, RF-based models have been trained to distinguish between pancreatic cancer (PC) and healthy tissue. Models based on RF, adaptive boosting, support vector machine (SVM), or extremely randomized trees have also been used to classify PC and pancreatitis. In intraductal papillary mucinous neoplasm (IPNM), logistic regression has been used to generate models to detect cancer. Cas. et al. reviewed all these works, concluding that radiomics may be a valid approach to apply in the diagnosis, risk stratification, prediction of biological or genomic status, or treatment response assessment in cases of PC.”
    Radiomics in CT and MR imaging of the liver and pancreas: tools with potential for clinical application
    M. lvaro Berbis et al.
    Abdominal Radiology (in press)
  • “With the arrival of higher-resolution cross-sectional imaging techniques, incidental pancreatic cystic lesions (PCL) have been increasingly discovered. PCLs are defined and classified according to the WHO criteria. Among the different types of PCLs, some kinds of mucinous lesions present a risk of malignant transformation to PDAC. Their differential diagnosis includes those of non-neoplastic (pseudocysts) and neoplastic origin (pancreatic cystic neoplasms). The latter can be benign neoplasms (serous cystic neoplasm, SCN) or cystic neoplasms with the potential to become malignant (main duct and brunch duct intraductal papillary mucinous neoplasms [IPMN] and mucinous cystic neoplasms).”
    Radiomics in CT and MR imaging of the liver and pancreas: tools with potential for clinical application
    M. lvaro Berbis et al.
    Abdominal Radiology (in press)
  • “Radiomics and AI are promising techniques that allow the development and validation of cancer biomarkers and the building of predictive models. However, although the analysis of radiomics features by ML algorithms has been demonstrated to be useful to find patterns and to serve as predictive markers for patient outcomes in lung, kidney, or colorectal cancer, there is still limited information regarding the pancreas.”  
    Radiomics in CT and MR imaging of the liver and pancreas: tools with potential for clinical application
    M. lvaro Berbis et al.
    Abdominal Radiology (in press)
  • “The extraction of quantitative CT texture features allows us to distinguish PDAC from PNET. Moreover, PNET grade can be predicted based on texture analysis. Radiomics analysis by five different ML models (distance correlation, AdaBoost, gradient boosting decision tree, least absolute shrinkage and selection operator, XGBoost, and RF) in a retrospective study conducted on 82 patients was able to differentiate between pathological grades G1, G2, and G3 in PNET patients. Interestingly, Gu et al. developed a radiomics signature with a solid ability to discriminate different PNET histological grades and established a nomogram incorporating both radiomics features and clinical risk factors to assist clinical decision-making for PNET patients.”
    Radiomics in CT and MR imaging of the liver and pancreas: tools with potential for clinical application
    M. lvaro Berbis et al.
    Abdominal Radiology (in press)
  • “In the pancreas, radiomics can contribute to improving the accuracy of the diagnosis, prognosis, and prediction of PC (the fourth leading cause of cancer death in Europe) and its differentiation from healthy tissue and other pancreatic pathologies. Although still limited by the scarcity of studies with good methodologic quality and the methodological difficulties inherently associated with DL algorithms, we can expect a bright future for radiomics in these fields, presumably brought about by the fast development of high-performance computers and DL tools and theincreasing availability of higher volumes of clinical imaging datasets.”
    Radiomics in CT and MR imaging of the liver and pancreas: tools with potential for clinical application
    M. lvaro Berbis et al.
    Abdominal Radiology (in press)
  • Background: Existing (artificial intelligence [AI]) tools in radiology are modeled without necessarily considering the expectations and experience of the end user-the radiologist. The literature is scarce on the tangible parameters that AI capabilities need to meet for radiologists to consider them useful tools.
    Objective: The purpose of this study is to explore radiologists' attitudes toward AI tools in pancreatic cancer imaging and to quantitatively assess their expectations of these tools.
    Results: A total of 161 respondents completed the survey, yielding a response rate of 46.3% of the total 348 clicks on the survey link. The minimum acceptable sensitivity of an AI program for the detection of pancreatic cancer chosen by most respondents was either 90% or 95% at a specificity of 95%. The minimum size of pancreatic cancer that most respondents would find an AI useful at detecting was 5 mm. Respondents preferred AI tools that demonstrated greater sensitivity over those with greater specificity. Over half of respondents anticipated incorporating AI tools into their clinical practice within the next 5 years.
    Conclusion: Radiologists are open to the idea of integrating AI-based tools and have high expectations regarding the performance of these tools. Consideration of radiologists' input is important to contextualize expectations and optimize clinical adoption of existing and future AI tools.
    Radiologists' Expectations of Artificial Intelligence in Pancreatic Cancer Imaging: How Good Is Good Enough? Chu LC, Ahmed T, Blanco A, Javed A, Weisberg EM, Kawamoto S, Hruban RH, Kinzler KW, Vogelstein B, Fishman EK.  
    J Comput Assist Tomogr. 2023 Jul 28. doi: 10.1097/RCT.0000000000001503. Epub ahead of print.
  • Purpose To analyze the conspicuity of pancreatic ductal adenocarcinoma (PDAC) in virtual monoenergetic images (VMI) on a novel photon-counting detector CT (PCD-CT) in comparison to energy-integrating CT (EID-CT).
    Methods Inclusion criteria comprised initial diagnosis of PDAC (reference standard: histopathological analysis) and standardized contrast-enhanced CT imaging either on an EID-CT or a PCD-CT. Patients were excluded due to different histopathological diagnosis or missing tumor delineation on CT. On the PCD-CT, 40–190 keV VMI reconstructions were generated. Image noise, tumor-to-pancreas ratio (TPR) and contrast-to-noise ratio (CNR) were analyzed by ROI-based measurements in arterial and portal venous contrast phase. Two board-certified radiologist evaluated image quality and tumor delineation at both, EID-CT and PCD-CT (40 and 70 keV)
    Conclusion PCD-CT VMI reconstructions (≤ 70 keV) showed significantly improved conspicuity of PDAC in quantitative and qualitative analysis in both, arterial and portal venous contrast phase, compared to EID-CT, which may be important forearly detection of tumor tissue in clinical routine. Tumor delineation was superior in portal venous contrast phase compared to arterial contrast phase.
    Optimal conspicuity of pancreatic ductal adenocarcinoma in virtual monochromatic imaging reconstructions on a photon‑counting detector CT: comparison to conventional MDCT
    Josua A. Decker et al.
    Abdominal Radiologyhttps://doi.org/10.1007/s00261-023-04042
  • PCD-CT showed significantly improved tumor conspicuity (reflected by low TPR and high CNR) at lower keV-levels (≤ 70 keV) in arterial and portal venous contrast phases. Compared to EID-CT, tumor delineation on PCD-CT is superior only in the portal venous phase, not in the arterial phase. Tumor tissue showed a slower decrease of CTvalues with increasing keV levels compared to pancreatic tissue in arterial phase, which may also be helpful for the diagnosis. Subjective image analysis showed improved tumor delineation at lower keV levels compared to 70 keV in both, arterial and portal venous phase.
    Optimal conspicuity of pancreatic ductal adenocarcinoma in virtual monochromatic imaging reconstructions on a photon‑counting detector CT: comparison to conventional MDCT
    Josua A. Decker et al.
    Abdominal Radiologyhttps://doi.org/10.1007/s00261-023-04042
  • “Implementation of VMI with low keV levels (e.g. 40 keV) for both—arterial and portal venous phase—in clinical routine may improve delineation of pancreatic ductal adenocarcinoma in patients with suspected pancreatic cancer.”
    Optimal conspicuity of pancreatic ductal adenocarcinoma in virtual monochromatic imaging reconstructions on a photon‑counting detector CT: comparison to conventional MDCT
    Josua A. Decker et al.
    Abdominal Radiologyhttps://doi.org/10.1007/s00261-023-04042
  • Intraductal papillary mucinous neoplasms (IPMNs) have become a very common diagnosis and represent a spectrum of disease that ranges from benign to malignant lesions. Presently, clinical and radiographic features are used to predict the presence of high-grade dysplasia and invasive cancer to inform treatment decisions of whether to pursuit surgical resection or continued surveillance. However, the natural history of IPMNs is still not completely understood, with guidelines from different societies providing contradictory recommendations. This underscores the challenge in balancing the risk of missing cancer with long-term surveillance and the morbidity associated with surgical resection. In this review, we aim to reconcile the differences in the guidelines’ recommendations and provide a clinical framework to the management of IPMNs with hopes of adding clarity to how treatment decisions should be made.  
    A Clinical Guide to the Management of Intraductal Papillary Mucinous Neoplasms: the Need for a More Graded Approach in Clinical Decision‑making
    Zhi Ven Fong . Yasmin G. Hernandez‑Barco . Carlos Fernandez‑del Castillo
    Journal of Gastrointestinal Surgery (2023) 27:1988–1998
  • Similar to PDAC, the most helpful serum tumor marker for IPMNs is serum CA 19–9. In an analysis of 594 patients who had undergone resection for IPMN, a CA 19–9 level of > 37 U/ml was associated with a higher likelihood of harboring invasive carcinoma (45.3% vs. 18.0%, p < 0.001) and a concomitantly occurring PDAC (17.2% vs. 4.9%, p < 0.001).9 An elevated CA 19–9 level was also associated with worse overall and disease-free survival. However, it was not associated with the incidence of high-grade dysplasia, and as such, a normal level should not be considered a reassuring data point. It should also be noted that 5–10% of the population lack the Lewis A antigen necessary to secrete CA 19–9, and as such, would not have elevated levels even if they harbored invasive cancer.In this population, preliminary studies have suggested that CA-125 could serve as an alternate biomarker.12
    A Clinical Guide to the Management of Intraductal Papillary Mucinous Neoplasms: the Need for a More Graded Approach in Clinical Decision‑making
    Zhi Ven Fong . Yasmin G. Hernandez‑Barco . Carlos Fernandez‑del Castillo
    Journal of Gastrointestinal Surgery (2023) 27:1988–1998
  • IPMNs are an increasingly common entity that represent a spectrum of disease that range from benign to malignant entities. Presently, the predictors of the presence of high grade dysplasia or invasive cancer are based on a combination of clinical and radiographic features. The differences in guidelines’ treatment recommendations reflect the difficulty in balancing the risks of missing invasive cancer with the morbidity of surgical resection. The ultimate decision to pursue surgical resection or surveillance should be individualized to the patients’ personalized risk of harboring high grade dysplasia or cancer, age, comorbidities, and personal preferences. For patients who had undergone resection and those with IPMNs not meeting criteria for surgical resection, continued surveillance should be pursued so long as they remain surgical candidates given the continued risk of developing new IPMNs and invasive cancer in the remnant gland. Current efforts underway are focused on developing non-invasive tools that can be routinely used to predict highgrade dysplasia in IPMNs, and thus providing a window of opportunity for intervention before the development of invasive cancer.
    A Clinical Guide to the Management of Intraductal Papillary Mucinous Neoplasms: the Need for a More Graded Approach in Clinical Decision‑making
    Zhi Ven Fong . Yasmin G. Hernandez‑Barco . Carlos Fernandez‑del Castillo
    Journal of Gastrointestinal Surgery (2023) 27:1988–1998
  • Purpose: A wide array of benign and malignant lesions of the pancreas can be cystic and these cystic lesions can have overlapping imaging appearances. The purpose of this study is to compare the diagnostic accuracy of a radiomics-based pancreatic cyst classifier to an experienced academic radiologist. Methods: In this IRB-approved retrospective single-institution study, patients with surgically resected pancreatic cysts who underwent preoperative abdominal CT from 2003 to 2016 were identified. Pancreatic cyst(s) and background pancreas were manually segmented, and 488 radiomics features were extracted. Random forest classification based on radiomics features, age, and gender was evaluated with fourfold cross-validation. An academic radiologist blinded to the final pathologic diagnosis reviewed each case and provided the most likely diagnosis.
    Classification of pancreatic cystic neoplasms using radiomic feature analysis is equivalent to an experienced academic radiologist: a step toward computer-augmented diagnostics for radiologists.  
    Chu LC, Park S, Soleimani S, Fouladi DF, Shayesteh S, He J, Javed AA, Wolfgang CL, Vogelstein B, Kinzler KW, Hruban RH, Afghani E, Lennon AM, Fishman EK, Kawamoto S.  
    Abdom Radiol (NY). 2022 Dec;47(12):4139-4150.
  • Results: 214 patients were included (64 intraductal papillary mucinous neoplasms, 33 mucinous cystic neoplasms, 60 serous cystadenomas, 24 solid pseudopapillary neoplasms, and 33 cystic neuroendocrine tumors). The radiomics-based machine learning approach showed AUC of 0.940 in pancreatic cyst classification, compared with AUC of 0.895 for the radiologist. Conclusion: Radiomics-based machine learning achieved equivalent performance as an experienced academic radiologist in the classification of pancreatic cysts. The high diagnostic accuracy can potentially maximize the efficiency of healthcare utilization by maximizing detection of high-risk lesions.
    Classification of pancreatic cystic neoplasms using radiomic feature analysis is equivalent to an experienced academic radiologist: a step toward computer-augmented diagnostics for radiologists.  
    Chu LC, Park S, Soleimani S, Fouladi DF, Shayesteh S, He J, Javed AA, Wolfgang CL, Vogelstein B, Kinzler KW, Hruban RH, Afghani E, Lennon AM, Fishman EK, Kawamoto S.  
    Abdom Radiol (NY). 2022 Dec;47(12):4139-4150.
  • “This study showed that a radiomics-based model can achieve equivalent performance as an experienced academic radiologist in the classifcation of a wide array of pancreatic cysts with variable malignant potential. This model has the potential to refne pancreatic cyst management by improving diagnostic accuracy of cystic lesions, which can minimize healthcare utilization while maximizing detection of malignant lesions. This study confrms the ability of a radiomicbased model to accurately classify pancreatic cystic neoplasms. Further validation and clinical integration of this model could help optimize management of pancreatic cysts by maximizing the rate of detection of malignant lesions while reducing healthcare utilization.”
    Classification of pancreatic cystic neoplasms using radiomic feature analysis is equivalent to an experienced academic radiologist: a step toward computer-augmented diagnostics for radiologists.  
    Chu LC, Park S, Soleimani S, Fouladi DF, Shayesteh S, He J, Javed AA, Wolfgang CL, Vogelstein B, Kinzler KW, Hruban RH, Afghani E, Lennon AM, Fishman EK, Kawamoto S.  
    Abdom Radiol (NY). 2022 Dec;47(12):4139-4150.

  • Classification of pancreatic cystic neoplasms using radiomic feature analysis is equivalent to an experienced academic radiologist: a step toward computer-augmented diagnostics for radiologists.  
    Chu LC, Park S, Soleimani S, Fouladi DF, Shayesteh S, He J, Javed AA, Wolfgang CL, Vogelstein B, Kinzler KW, Hruban RH, Afghani E, Lennon AM, Fishman EK, Kawamoto S.  
    Abdom Radiol (NY). 2022 Dec;47(12):4139-4150.
  • Purpose: The purpose of this study was to determine whether computed tomography (CT)-based machine learning of radiomics features could help distinguish autoimmune pancreatitis (AIP) from pancreatic ductal adenocarcinoma (PDAC). Materials and methods: Eighty-nine patients with AIP (65 men, 24 women; mean age, 59.7±13.9 [SD] years; range: 21-83 years) and 93 patients with PDAC (68 men, 25 women; mean age, 60.1±12.3 [SD] years; range: 36-86 years) were retrospectively included. All patients had dedicated dual-phase pancreatic protocol CT between 2004 and 2018. Thin-slice images (0.75/0.5mm thickness/increment) were compared with thick-slices images (3 or 5mm thickness/increment). Pancreatic regions involved by PDAC or AIP (areas of enlargement, altered enhancement, effacement of pancreatic duct) as well as uninvolved parenchyma were segmented as three-dimensional volumes. Four hundred and thirty-one radiomics features were extracted and a random forest was used to distinguish AIP from PDAC. CT data of 60 AIP and 60 PDAC patients were used for training and those of 29 AIP and 33 PDAC independent patients were used for testing.
    Differentiating autoimmune pancreatitis from pancreatic ductal adenocarcinoma with CT radiomics features.  
    Park S, Chu LC, Hruban RH, Vogelstein B, Kinzler KW, Yuille AL, Fouladi DF, Shayesteh S, Ghandili S, Wolfgang CL, Burkhart R, He J, Fishman EK, Kawamoto S.  
    Diagn Interv Imaging. 2020 Sep;101(9):555-564.
  • Results: The pancreas was diffusely involved in 37 (37/89; 41.6%) patients with AIP and not diffusely in 52 (52/89; 58.4%) patients. Using machine learning, 95.2% (59/62; 95% confidence interval [CI]: 89.8-100%), 83.9% (52:67; 95% CI: 74.7-93.0%) and 77.4% (48/62; 95% CI: 67.0-87.8%) of the 62 test patients were correctly classified as either having PDAC or AIP with thin-slice venous phase, thin-slice arterial phase, and thick-slice venous phase CT, respectively. Three of the 29 patients with AIP (3/29; 10.3%) were incorrectly classified as having PDAC but all 33 patients with PDAC (33/33; 100%) were correctly classified with thin-slice venous phase with 89.7% sensitivity (26/29; 95% CI: 78.6-100%) and 100% specificity (33/33; 95% CI: 93-100%) for the diagnosis of AIP, 95.2% accuracy (59/62; 95% CI: 89.8-100%) and area under the curve of 0.975 (95% CI: 0.936-1.0). Conclusions: Radiomic features help differentiate AIP from PDAC with an overall accuracy of 95.2%.
    Differentiating autoimmune pancreatitis from pancreatic ductal adenocarcinoma with CT radiomics features.  
    Park S, Chu LC, Hruban RH, Vogelstein B, Kinzler KW, Yuille AL, Fouladi DF, Shayesteh S, Ghandili S, Wolfgang CL, Burkhart R, He J, Fishman EK, Kawamoto S.  
    Diagn Interv Imaging. 2020 Sep;101(9):555-564.
  • RESULTS. Mean tumor size was 4.1 ± 1.7 (SD) cm. The overall accuracy of the random forest binary classification was 99.2% (124/125), and AUC was 99.9%. All PDAC cases (60/60) were correctly classified. One case from a renal donor was misclassified as PDAC (1/65). The sensitivity was 100%, and specificity was 98.5%.  CONCLUSION. Radiomics features extracted from whole pancreas can be used to differentiate between CT cases from patients with PDAC and healthy control subjects with normal pancreas.
    Utility of CT Radiomics Features in Differentiation of Pancreatic Ductal Adenocarcinoma From Normal Pancreatic Tissue.  
    Chu LC, Park S, Kawamoto S, Fouladi DF, Shayesteh S, Zinreich ES, Graves JS, Horton KM, Hruban RH, Yuille AL, Kinzler KW, Vogelstein B, Fishman EK.
    AJR Am J Roentgenol. 2019 Aug;213(2):349-357.
  • “This preliminary study showed that the radiomics features extracted from the whole pancreas can be used to differentiate between CT images of patients with PDAC and CT images of healthy control subjects. There is the potential to combine this algorithm with automatic organ segmentation algorithms for automatic detection of PDAC.”
    Utility of CT Radiomics Features in Differentiation of Pancreatic Ductal Adenocarcinoma From Normal Pancreatic Tissue.  
    Chu LC, Park S, Kawamoto S, Fouladi DF, Shayesteh S, Zinreich ES, Graves JS, Horton KM, Hruban RH, Yuille AL, Kinzler KW, Vogelstein B, Fishman EK.
    AJR Am J Roentgenol. 2019 Aug;213(2):349-357.

  •  Utility of CT Radiomics Features in Differentiation of Pancreatic Ductal Adenocarcinoma From Normal Pancreatic Tissue.  
    Chu LC, Park S, Kawamoto S, Fouladi DF, Shayesteh S, Zinreich ES, Graves JS, Horton KM, Hruban RH, Yuille AL, Kinzler KW, Vogelstein B, Fishman EK.
    AJR Am J Roentgenol. 2019 Aug;213(2):349-357.
  • In conclusion, in this study, Multi-channel CT images were obtained through preprocessing based on single-channel manual outline ROI images, and ResNet was used to extract CT image features of pancreatic SCNs and MCNs. The random forest classifier is used to integrate the classification probabilities of the KNN, Bayesian, and Softmax classifiers to determine the CT image properties of pancreatic SCNs and MCNs. Finally, a better classification result was obtained relative to the commonly used radiomics methods, suggesting that MMRF-ResNet is an ideal CT classification model for distinguishing between pancreatic SCNs and MCNs.
    CT classification model of pancreatic serous cystic neoplasms and mucinous cystic neoplasms based on a deep neural network
    Rong Yang et al.
    Abdominal Radiology (2022) 47:232–241
  • Background & Aims
    The aims of our case-control study were – 1) to develop an automated 3D-Convolutional Neural Network (CNN) for detection of PDA on diagnostic CTs, 2) evaluate its generalizability on multi-institutional public datasets, 3) its utility as a potential screening tool using a simulated cohort with high pretest probability, and 4) its ability to detect visually occult pre-invasive cancer on pre-diagnostic CTs.
    Methods
    A 3D-CNN classification system was trained using algorithmically generated bounding boxes and pancreatic masks on a curated dataset of 696 portal phase diagnostic CTs with PDA and 1080 controls with non-neoplastic pancreas. Model was evaluated on (a) an intramural hold-out test subset (409 CTs with PDA, 829 controls); (b) a simulated cohort with a case-control distribution that matched the risk of PDA in glycemically-defined new-onset diabetes and END-PAC score ≥3; (c) multi-institutional public datasets (194 CTs with PDA, 80 controls), and (d) a cohort of 100 pre-diagnostic CTs (i.e., CTs incidentally acquired 3–36 months before clinical diagnosis of PDA) without a focal mass, and 134 controls. 
  • Results
    Majority CTs (n=798; 64%) in intramural test subset were from outside hospitals. The model correctly classified 360 (88%) CTs with PDA and 783 (94%) controls [accuracy (mean; 95% CI) 0·92 (0·91-0·94); AUROC 0·97 (0·96-0·98), sensitivity 0·88 (0·85-0·91), specificity 0·95 (0·93-0·96)]. Activation areas on heat maps overlapped with the tumor in most CTs (350/360 CTs; 97%). Performance was high across tumor stages (sensitivity 0·80, 0·87, 0·95 and 1.0 on T1 through T4 stages, respectively), comparable for hypodense versus isodense tumors (sensitivity: 0·90 vs. 0·82), different age, sex, CT slice thicknesses & vendors (all p >0·05), and generalizable on both the simulated cohort [accuracy 0·95 (0·94-0·95), AUROC 0·97 (0·94-0·99)] and public datasets [accuracy 0·86 (0·82-0·90), AUROC 0·90 (0·86-0·95)]. Despite being exclusively trained on diagnostic CTs with larger tumors, the model could detect occult PDA on pre-diagnostic CTs [accuracy 0·84 (0·79-0·88), AUROC 0·91 (0·86-0·94), sensitivity 0·75 (0·67-0·84), specificity 0·90 (0·85-0·95)] at a median 475 days (range: 93-1082) prior to clinical diagnosis.
    Conclusions
    Automated AI model trained on a large and diverse dataset shows high accuracy and generalizable performance for detection of PDA on diagnostic CTs as well as for visually occult PDA on pre-diagnostic CTs. Prospective validation with blood-based biomarkers is warranted to assess the potential for early detection of sporadic PDA in high-risk subjects. 
  • “Automated AI model trained on a large and diverse dataset shows high accuracy and generalizable performance for detection of PDA on diagnostic CTs as well as for visually occult PDA on pre-diagnostic CTs. Prospective validation with blood-based biomarkers is warranted to assess the potential for early detection of sporadic PDA in high-risk subjects.”
    Automated Artificial Intelligence Model Trained on a Large Dataset Can Detect Pancreas Cancer on Diagnostic CTs as well as Visually Occult Pre-invasive Cancer on Pre-diagnostic CTs.  
    Korfiatis P, Suman G, Patnam NG et al.  
    Gastroenterology. 2023 Aug 30:S0016-5085(23) Epub ahead of print. PMID: 37657758.
  • “To evaluate whether the model could detect pre-invasive cancer even in the absence of a focal lesion (i.e., visually occult PDA), we used a previously identified cohort of pre-diagnostic CTs 15 . The latter were defined as incidental portal venous phase CTs performed for unrelated indications (e.g., trauma, fever or sepsis of unknown origin, abdominal aortic aneurysms, guidance for biopsies and other procedures, bowel obstruction and/or mesenteric ischemia, etc.) between 3- and 36-months prior to the clinical diagnosis of PDA. All these CTs had been previously interpreted to be negative for PDA during routine clinical evaluation, which was further confirmed as part of data curation by radiologist investigators. The pre-diagnostic CTs of those patients whose diagnostic CT were part of the training-validation of the model (vide supra) were excluded to avoid bias or overestimation of model’s performance. The curation process resulted in a dataset of 100 pre-diagnostic CTs [59 men, 41 women; mean age (SD): 67 (10.8) years].”
    Automated Artificial Intelligence Model Trained on a Large Dataset Can Detect Pancreas Cancer on Diagnostic CTs as well as Visually Occult Pre-invasive Cancer on Pre-diagnostic CTs.  
    Korfiatis P, Suman G, Patnam NG et al.  
    Gastroenterology. 2023 Aug 30:S0016-5085(23) Epub ahead of print. PMID: 37657758.
  • “In summary, the automated AI model shows high accuracy and generalizable performance for detection of PDA on standard-of-care diagnostic CTs as well as for detection of pre-invasive visually occult PDA on pre-diagnostic CTs at a substantial lead time prior to clinical diagnosis. Despite being trained on larger tumors, the model had a high sensitivity for stage T1 and isodense tumors as well as high specificity for control CTs. The model’s performance was consistent across variations in patient demographics and image acquisition parameters, and generalizable on multi-institutional public datasets. The model also showed promising potential in a bootstrapped population with a case-control distribution that matches high-risk groups such as glycemically-defined NOD. Further optimization and prospective evaluation in combination with emerging blood-based biomarkers is warranted to assess the potential for early detection of sporadic PDA in high-risk cohorts.”
    Automated Artificial Intelligence Model Trained on a Large Dataset Can Detect Pancreas Cancer on Diagnostic CTs as well as Visually Occult Pre-invasive Cancer on Pre-diagnostic CTs.  
    Korfiatis P, Suman G, Patnam NG et al.  
    Gastroenterology. 2023 Aug 30:S0016-5085(23) Epub ahead of print. PMID: 37657758.
  • ”Radiomics is changing the world of medicine and more specifically the world of oncology. Early diagnosis and treatment improve the prognosis of patients with cancer. After treatment, the evaluation of the response will determine future treatments. In oncology, every change in treatment means a loss of ther- apeutic options and this is key in pancreatic cancer. Radiomics has been developed in oncology in the early diagnosis and differential diagnosis of benign and malignant lesions, in the evaluation of response, in the prediction of possible side effects, marking the risk of recurrence, survival and prognosis of the disease. Some studies have validated its use to differentiate normal tissues from tumor tissues with high sensitivity and specificity, and to differentiate cystic lesions and pancreatic neuroendocrine tumor grades with texture parameters. In addition, these parameters have been related to survival in patients with pancreatic cancer and to response to radiotherapy and chemotherapy. This review aimed to establish the current status of the use of radiomics in pancreatic cancer and future perspectives.”  
    Radiomics in pancreatic cancer for oncologist: Present and future  
    Carolina de la Pinta  
    Hepatobiliary & Pancreatic Diseases International 21 (2022) 356–361    
  •  “Chu et al. used radiomic features of CT images to differentiate pancreatic adenocarcinoma and normal pancreatic tissues in a series of patients with a radiological and pathological diagnosis, and the study included a training cohort and a validation cohort. Accuracy, sensitivity and specificity were calculated. Patients were classified with a sensitivity of 100% and a specificity of 98.5%. This would allow a more precise definition of tumor areas, which is very important to local treatment strategies.”  
    Radiomics in pancreatic cancer for oncologist: Present and future  
    Carolina de la Pinta  
    Hepatobiliary & Pancreatic Diseases International 21 (2022) 356–361    
  •  “Dmitriev et al. differentiated four types of cysts by com- bining demographic variables with radiomic characteristics of in- tensity and shape, achieving differentiation of 84% of the lesions. Wei et al. analyzed cyst images in preoperative tests to differentiate SCNs from other pancreatic cystic lesions (PCLs) includ- ing 17 intensity and texture features (T-range, wavelet intensity, T-median, and wavelet neighbourhood gray-tone difference matrix busyness) and clinical features. Adequate classification was achieved in 76% of patients and 84% in a validation cohort of 60 patients. Yang et al. evaluated variable slice images, 2 and 5 mm, without affecting feature extraction. In the validation group the accuracy was 74% in patients with 2-mm slice and 83% in 5- mm slice. ”  
    Radiomics in pancreatic cancer for oncologist: Present and future  
    Carolina de la Pinta  
    Hepatobiliary & Pancreatic Diseases International 21 (2022) 356–361
  • “Yamashita et al. demonstrated that differences in contrast- enhanced CT acquisition affected the results of the radiomic study leading to changes in segmentation and its reproducibility and comparability between series . The study did not demonstrate statistically significant differences in CT model, pixel spacing, and contrast administration ratio. The study suggests that radiologists are more or less sensitive to CT acquisition parameters, demonstrating the importance of adjusting for these variables to established protocols. Furthermore, this study support the hypothesis of the usefulness of a semi-automated segmentation tool previously trained by several radiologists that can homogenize these varia- tions. Standardization of protocols is therefore important, in addition to external validation. Also many of the comparisons between diagnostic entities using radiomics are subjective and not clinically applicable. For example, the distinction between pancreatic adenocarcinoma and pancreatic neuroendocrine tumors alone.”  
    Radiomics in pancreatic cancer for oncologist: Present and future  
    Carolina de la Pinta  
    Hepatobiliary & Pancreatic Diseases International 21 (2022) 356–361   
  • ”Radiomics is a promising non-invasive tool for the diagnosis and clinical management of pancreatic tumors. The usefulness of radiomics has been studied in the differential diagnosis of benign, premalignant and malignant lesions in the pancreas. In addition, in patients with neoadjuvant pancreatic cancer, it can help in the more precise definition of lesions for radiotherapy and assessment of response. Radiomics provides a more adequate and reproducible measurement of the tumor than other methods. In addition, the combination of radiomics and genomics has a promising future. However, image acquisition protocols and radiomic analysis sys- tems need to be standardized and validation cohorts are needed. Further studies are needed to consolidate the available data.”  
    Radiomics in pancreatic cancer for oncologist: Present and future  
    Carolina de la Pinta  
    Hepatobiliary & Pancreatic Diseases International 21 (2022) 356–361

  • CT classification model of pancreatic serous cystic neoplasms and mucinous cystic neoplasms based on a deep neural network
    Rong Yang et al.
    Abdominal Radiology (2022) 47:232–241 
  • Results: Multi-channel-ResNet (AUC 0.98) was superior to Manual-ResNet (AUC 0.91).CT image characteristics of lesions extracted by ResNet are more representative than wavelet, LBP, HOG, GLCM, Gabor, and AlexNet. Compared to the use of three classifiers alone and Majority Voting rule method, the use of the MMRF-ResNet model exhibits a better evaluation effect (AUC 0.96) for the classification of the pancreatic SCNs and MCNs. Conclusion The CT image classification model MMRF-ResNet is an effective method to distinguish between pancreatic SCNs and MCNs.
    CT classification model of pancreatic serous cystic neoplasms and mucinous cystic neoplasms based on a deep neural network
    Rong Yang et al.
    Abdominal Radiology (2022) 47:232–241 
  • Background At present, numerous challenges exist in the diagnosis of pancreatic SCNs and MCNs. After the emergence of artificial intelligence (AI), many radiomics research methods have been applied to the identification of pancreatic SCNs and MCNs.
    Purpose A deep neural network (DNN) model termed Multi-channel-Multiclassifier-Random Forest-ResNet (MMRFResNet) was constructed to provide an objective CT imaging basis for differential diagnosis between pancreatic serous cystic neoplasms (SCNs) and mucinous cystic neoplasms (MCNs).
    CT classification model of pancreatic serous cystic neoplasms and mucinous cystic neoplasms based on a deep neural network
    Rong Yang et al.
    Abdominal Radiology (2022) 47:232–241 
  • In conclusion, in this study, Multi-channel CT images were obtained through preprocessing based on single-channel manual outline ROI images, and ResNet was used to extract CT image features of pancreatic SCNs and MCNs. The random forest classifier is used to integrate the classification probabilities of the KNN, Bayesian, and Softmax classifiers to determine the CT image properties of pancreatic SCNs and MCNs. Finally, a better classification result was obtained relative to the commonly used radiomics methods, suggesting that MMRF-ResNet is an ideal CT classification model for distinguishing between pancreatic SCNs and MCNs.
    CT classification model of pancreatic serous cystic neoplasms and mucinous cystic neoplasms based on a deep neural network
    Rong Yang et al.
    Abdominal Radiology (2022) 47:232–241 
  • Background : Existing (artificial intelligence [AI]) tools in radiology are modeled without necessarily considering the expectations and experience of the end user—the radiologist. The literature is scarce on the tangible parameters that AI capabilities need to meet for radiologists to consider them useful tools.
    Objective : The purpose of this study is to explore radiologists' attitudes toward AI tools in pancreatic cancer imaging and to quantitatively assess their expectations of these tools.
    Methods : A link to the survey was posted on the www.ctisus.com website, advertised in the www.ctisus.com email newsletter, and publicized on LinkedIn, Facebook, and Twitter accounts. This survey asked participants about their demographics, practice, and current attitudes toward AI. They were also asked about their expectations of what constitutes a clinically useful AI tool. The survey consisted of 17 questions, which included 9 multiple choice questions, 2 Likert scale questions, 4 binary (yes/no) questions, 1 rank order question, and 1 free text question.
    Radiologists' Expectations of Artificial Intelligence in Pancreatic Cancer Imaging: How Good Is Good Enough?.
    Chu, Linda C. MD*; Ahmed, Taha MBBS*; Blanco, Alejandra MD*; Javed, Ammar MD†; Weisberg, Edmund M. MS, MBE*; Kawamoto, Satomi MD*; Hruban, Ralph H. MD‡; Kinzler, Kenneth W. PhD§; Vogelstein, Bert MD§; Fishman, Elliot K. MD*.  
    Journal of Computer Assisted Tomography July 28, 2023. (in press)
  • Results: A total of 161 respondents completed the survey, yielding a response rate of 46.3% of the total 348 clicks on the survey link. The minimum acceptable sensitivity of an AI program for the detection of pancreatic cancer chosen by most respondents was either 90% or 95% at a specificity of 95%. The minimum size of pancreatic cancer that most respondents would find an AI useful at detecting was 5 mm. Respondents preferred AI tools that demonstrated greater sensitivity over those with greater specificity. Over half of respondents anticipated incorporating AI tools into their clinical practice within the next 5 years.
    Conclusion: Radiologists are open to the idea of integrating AI-based tools and have high expectations regarding the performance of these tools. Consideration of radiologists' input is important to contextualize expectations and optimize clinical adoption of existing and future AI tools.
    Radiologists' Expectations of Artificial Intelligence in Pancreatic Cancer Imaging: How Good Is Good Enough?.
    Chu, Linda C. MD*; Ahmed, Taha MBBS*; Blanco, Alejandra MD*; Javed, Ammar MD†; Weisberg, Edmund M. MS, MBE*; Kawamoto, Satomi MD*; Hruban, Ralph H. MD‡; Kinzler, Kenneth W. PhD§; Vogelstein, Bert MD§; Fishman, Elliot K. MD*.  
    Journal of Computer Assisted Tomography July 28, 2023. (in press)
  •    “The minimum acceptable sensitivity of an AI program for the detection of pancreatic cancer chosen by most respondents was either 90% or 95% at a specificity of 95%. The minimum size of pancreatic cancer that most respondents would find an AI useful at detecting was 5 mm. Respondents preferred AI tools that demonstrated greater sensitivity over those with greater specificity. Over half of respondents anticipated incorporating AI tools into their clinical practice within the next 5 years.”  
    Radiologists' Expectations of Artificial Intelligence in Pancreatic Cancer Imaging: How Good Is Good Enough?.
    Chu, Linda C. MD*; Ahmed, Taha MBBS*; Blanco, Alejandra MD*; Javed, Ammar MD†; Weisberg, Edmund M. MS, MBE*; Kawamoto, Satomi MD*; Hruban, Ralph H. MD‡; Kinzler, Kenneth W. PhD§; Vogelstein, Bert MD§; Fishman, Elliot K. MD*.  
    Journal of Computer Assisted Tomography July 28, 2023. (in press)
  • “Artificial Intelligence (AI) is set to transform medical imaging by leveraging the vast data contained in medical images. Deep learning and radiomics are the two main AI methods currently being applied within radiology. Deep learning uses a layered set of self-correcting algorithms to develop a mathematical model that best fits the data. Radiomics converts imaging data into mineable features such as signal intensity, shape, texture, and higher-order features. Both methods have the potential to improve disease detection, characterization, and prognostication.”
    A primer on artificial intelligence in pancreatic imaging.  
    Ahmed TM, Kawamoto S, Hruban RH, Fishman EK, Soyer P, Chu LC.
    Diagn Interv Imaging. 2023 Mar 24:S2211-5684(23)00050-5.
  • ”The number of features extracted during this image analysis process can vary widely, depending on the software package and filters used. However, a high number of features and a low number of cases in a group for a classification task can result in overfitting of the model. To mitigate this risk, it is essential to perform feature selection or dimension reduction to reduce the number of features and increase the validity and generalizability of the results. Once appropriate features have been selected, they are subsequently analyzed with advanced machine learning algorithms, such as random forest or support vector machine, to perform specific classification tasks that can be used to help answer clinical questions.”
    A primer on artificial intelligence in pancreatic imaging.  
    Ahmed TM, Kawamoto S, Hruban RH, Fishman EK, Soyer P, Chu LC.
    Diagn Interv Imaging. 2023 Mar 24:S2211-5684(23)00050-5.
  • “While most prior studies had applied radiomics as a "second reader" to catch a diagnosis that may be missed due to human error, several more recent studies have reported that radiomics models may be able to detect PDAC before it is even discernable to the human eye on imaging . During the development of PDAC, the pancreas undergoes various morphological changes. PDACs may arise from detectable precancerous lesions such as intraductal papillary mucinous neoplasms (IPMN), and the pancreatic parenchyma upstream from a subtle cancer may show focal parenchymal atrophy and changes of chronic pancreatitis. Each of these can gradually increase the heterogeneity of the pancreatic tissue and result in detectable morphological and textural changes. These alterations may be difficult to interrogate on visual assessment, making AI the ideal tool to analyze them.”
    A primer on artificial intelligence in pancreatic imaging.  
    Ahmed TM, Kawamoto S, Hruban RH, Fishman EK, Soyer P, Chu LC.
    Diagn Interv Imaging. 2023 Mar 24:S2211-5684(23)00050-5.
  • “AI has also made advancements in the detection of a variety of solid and cystic pancreatic neoplasms aside from PDAC. In a recent study, a deep learning model was able to detect PDAC, pancreatic neuroendocrine tumors (pNET), solid pseudopapillary neoplasms (SPN), mucinous cystic neoplasms (MCN), serous cystic neoplasms, and IPMNs with a sensitivity of 98%−100% for solid lesions and 92%–93% for cystic lesions larger than 1.0 cm across two test sets consisting of 1192 patients. The performance of this model was not significantly different from that of radiologists (95–100% for solid lesions and 93–98% for cystic lesions > 1.0 cm). Similar prior deep learning studies have reported the sensitivity of detecting PDAC, pNET and pancreatic cystic lesions ranging from 78.8% to 87.6%.”
    A primer on artificial intelligence in pancreatic imaging.  
    Ahmed TM, Kawamoto S, Hruban RH, Fishman EK, Soyer P, Chu LC.
    Diagn Interv Imaging. 2023 Mar 24:S2211-5684(23)00050-5.
  • “Studies on classification of cystic pancreatic tumors have also reported excellent results. These studies have predominantly employed three different strategies in cyst classification: 1), A multi-class method to distinguish each category of pancreatic cyst. 2), A binary approach to separate benign cysts from those with malignant potential. 3), A binary classification of mucin-producing cysts into high-grade or low-grade dysplasia. A recent multiclass study consisting of 214 patients reported a radiomics model to perform on par with experienced academic radiologists at classifying various cystic tumors (IPMN, MCN, serous cystadenoma, SPN, PNET) with an AUC of 0.940 for the radiomics model compared to an AUC of 0.895 for the radiologists.”
    A primer on artificial intelligence in pancreatic imaging.  
    Ahmed TM, Kawamoto S, Hruban RH, Fishman EK, Soyer P, Chu LC.
    Diagn Interv Imaging. 2023 Mar 24:S2211-5684(23)00050-5.
  • “The third category of radiomics-based cyst classification studies have attempted to fill this gap through applying radiomics to risk-stratify patients with IPMNs. Studies have found that radiomics features extracted from CT, MRI and ultrasound have superior ability in identifying high-risk vs low-risk disease compared to clinical features and/or Fukuoka criteria. The most recent of such studies enrolled 66 patients and compared both MRI and CT radiomics models. In this study, the MRI model outperformed the CT radiomics model and achieved an AUC of 0.940 in preoperatively predicting malignant potential of IPMNs . Numerous similar prior studies with MRI or CT radiomics model have been conducted, and despite methodological variation, these studies have reported comparably strong results (AUC range, 0.71–0.96). Prior studies have also integrated clinical models based on the Fukuoka guidelines with radiomics models and have demonstrated superior performance of the combined models . Future integration of additional multidimensional data, such as novel radiogenomic features of cyst fluid DNA, into machine learning models has potential to further improve upon the performance of existing models.”  
    A primer on artificial intelligence in pancreatic imaging.  
    Ahmed TM, Kawamoto S, Hruban RH, Fishman EK, Soyer P, Chu LC.
    Diagn Interv Imaging. 2023 Mar 24:S2211-5684(23)00050-5.
  • “A unique application of radiomics beyond diagnostics has been to predict preoperatively a patient's survival should they undergo surgical resection of PDAC. Survival prediction of PDAC currently relies mainly on postoperative features such as the TNM stage and margins. This precludes preoperative survival prediction which could separate patients who will benefit from surgery from those who will not. Although surgical resection remains the only cure for PDAC, it is associated with significant complications and carries a small mortality risk. The development of an accurate preoperative survival prediction model could allow for a quantitative risk-benefit analysis prior to pancreatic resection and allow for individualized triaging of patients for surgery based on overall anticipated benefit from resection. In the current literature, four studies directly compared the prognostic performance of radiomics models with the clinical TNM staging criteria, with all four studies reporting that the radiomics models outperformed clinical criteria in predicting overall survival.”  
    A primer on artificial intelligence in pancreatic imaging.  
    Ahmed TM, Kawamoto S, Hruban RH, Fishman EK, Soyer P, Chu LC.
    Diagn Interv Imaging. 2023 Mar 24:S2211-5684(23)00050-5.
  • “Neoadjuvant therapy for PDAC is associated with lower rates of post-operative nodal involvement and perineural invasion, and higher rates of negative margin resection. However, determining the response to neoadjuvant treatment and resectability can be difficult. Radiomics have demonstrated the potential to identify a rapid response to chemotherapy and early down-staging to a surgically resectable tumor by evaluating the longitudinal evolution of radiomic features over chemoradiation cycles, termed delta radiomic features. Nasief et al. notably showed that CT delta radiomics features, particularly skewness and kurtosis (a measure of the shape of the distribution), could differentiate good responders from poor responders of chemoradiation therapy in a validation cohort of 40 patients with an AUC of 0.94 .”  
    A primer on artificial intelligence in pancreatic imaging.  
    Ahmed TM, Kawamoto S, Hruban RH, Fishman EK, Soyer P, Chu LC.
    Diagn Interv Imaging. 2023 Mar 24:S2211-5684(23)00050-5.
  • “When discussing the quality and generalizability of current evidence, perhaps the biggest challenge that needs to be overcome is the consolidation of large public annotated datasets. Radiomics and deep learning need to be trained on large datasets, and model performance and generalizability are critically dependent on the quality and size of these datasets. While the existence of such datasets had been previously limited, efforts to grow them are underway, with a notable dataset such as Imagenet and the National Cancer Institute's The Cancer Imaging Archive already being used by one included study to externally validate their model. In addition, efforts to synthetically augment datasets through deep learning methods such as neural style transfer and generative adversarial networks, which garnered public interest due to its application in "deepfake" media, have also demonstrated potential, but their current utility is uncertain. Although efforts to develop these databases and augment datasets are ongoing, their utilization in the development and validation of recent radiomics studies remains limited, as highlighted by the low overall RQS for validation amongst included studies. ”  
    A primer on artificial intelligence in pancreatic imaging.  
    Ahmed TM, Kawamoto S, Hruban RH, Fishman EK, Soyer P, Chu LC.
    Diagn Interv Imaging. 2023 Mar 24:S2211-5684(23)00050-5.
  • ”Beyond quality and generalizability issues, several practical barriers also exist, with one being the determination of the added clinical value of these models. To truly gauge a model's clinical utility, it must be compared against existing gold standards. For studies reporting models that autonomously detect and classify pancreatic lesions, the gold standard remains the radiologists' reads, while among studies reporting models that predict patient survival, the gold standard is TNM staging. Amongst included studies, only 31.5% reported a comparison with these gold standards making interpretation of the net clinical benefit of most current models questionable. While the vast majority (98.1%) of reviewed studies discussed potential clinical applications, simply suggesting prospective methods in which AI models may be of value is no longer adequate and future studies should report objective metrics such as incremental value over gold standards or decision curve analyses alongside their models.”  
    A primer on artificial intelligence in pancreatic imaging.  
    Ahmed TM, Kawamoto S, Hruban RH, Fishman EK, Soyer P, Chu LC.
    Diagn Interv Imaging. 2023 Mar 24:S2211-5684(23)00050-5.
  • “The final and arguably most formidable barrier to AI adoption is that of the legal hurdles associated with AI use in healthcare. The current legal framework for computer aided detection tools and for AI in triaging (e.g., AIdoc) is cloudy, and how this approach translates to the next generation of increasingly autonomous and diagnostic AI is uncertain. Mistakes are inevitable and consideration should be given to the difficult questions that will arise when these mistakes happen. Who is responsible for the accuracy of an autonomous AI system when it makes an error? How do we factor in the radiologist's liability when using AI tools? What is the liability of the health system that purchases an AI product? It has been suggested that analysis of how lawsuits involving autonomous cars, which share certain similarities with medical AI tools, have been handled by the courts could be instructive in providing a legal framework for medical AI. ”
     A primer on artificial intelligence in pancreatic imaging.  
    Ahmed TM, Kawamoto S, Hruban RH, Fishman EK, Soyer P, Chu LC.
    Diagn Interv Imaging. 2023 Mar 24:S2211-5684(23)00050-5.
  • AI has made significant progress in the detection, classification, and prognostication of pancreatic lesions, through techniques such as radiomics and deep learning. Despite this promise, the quality of existing literature is far from robust. While we acknowledge that the potential value of existing literature may extend beyond what may be formally evaluated through the RQS tool, to fully realize the benefit of these advancements, current results need to be validated through higher quality studies and multicenter trials that include the full spectrum of normal and abnormal. Fundamental questions still need addressing before clinical adoption, and efforts to establish sound evidence for future studies is warranted. Given the rate of discovery of AI in abdominal imaging however, we optimistically believe that these challenges will inevitably be overcome and that a future in which synergy between radiologists and machines will become the norm is not a matter of ‘if’ but only a matter of ‘when’.  
    A primer on artificial intelligence in pancreatic imaging.  
    Ahmed TM, Kawamoto S, Hruban RH, Fishman EK, Soyer P, Chu LC.
    Diagn Interv Imaging. 2023 Mar 24:S2211-5684(23)00050-5.
  • Radiomics and Pancreatic Cancer
    1. early lesion detection
    2. classification of pancreatic tumors
    3. risk stratification of masses (IPMN)
    4. prediction of tumor grade
    5. survival prediction
    6. treatment response and surgical resectability
  • “Stopping surveillance after stable cyst imaging for 5 years is a recommendation of the AGA guidelines, and after 10 years of stability in low-risk cysts, or sooner if the patients reaches 80 years of age after stability, or until the patients is no longer a surgical candidate is the recommendations of the ACR. This issue of ceasing surveillance isnot addressed in the other PCN clinical guidelines.The ACG guidelines recommend that patients fit for surgery should continue surveillance until they are no longer surgical candidates, and that patients older than 75 years should undergo surveillance imaging only after discussion with the multidisciplinary team.”
    Surveillance of Pancreatic Cystic Neoplasms
    Ankit Chhoda, Julie Schmidt, James J. Farrell
    Gastrointest Endoscopy Clin N Am 33 (2023) 613–640
  • A greater understanding of the biology and natural history of progression of pancreatic cysts is needed to improve our PCN surveillance strategies. This in turn may permit the development and validation of a blood-based approach for pancreatic cyst diagnosis and stratification, as well as refining pancreatic cyst fluid biomarkers for prediction of natural history purposes. Further studies on the role of chemoprevention andeven PCN ablation to alter the natural history of PCNs may impact on how we survey these patients Additional prospective studies such as the ACRIN-ECOG 2185 which is a prospective randomized controlled trial comparing a high-intensity surveillance program with a low-intensity testing program will provide very valuable, needed, and detailed clinical outcome information on pancreatic cysts surveillance, which will allow for a more reasoned discussions about the intensity of surveillance, use of valuable resources, and when to consider stopping surveillance.
    Surveillance of Pancreatic Cystic Neoplasms
    Ankit Chhoda, Julie Schmidt, James J. Farrell
    Gastrointest Endoscopy Clin N Am 33 (2023) 613–640
  • “It is increasingly appreciated that new-onset diabetes, especially type 2 diabetes mellitus (DM), is a risk factor for the development of PDAC. Data including a recent large meta-analysis demonstrate the association between the development of DM and both the morphologic progression of pancreatic cysts as well as the development of cancer. Some clinical guidelines have incorporated new-onset DM as a WF necessitating closer imaging and surveillance.”
    Surveillance of Pancreatic Cystic Neoplasms
    Ankit Chhoda, Julie Schmidt, James J. Farrell
    Gastrointest Endoscopy Clin N Am 33 (2023) 613–640
  • “A combination of significant family history of pancreatic cancer (defined as greater than 2 affected family members with PDAC) and certain inherited germline mutations is known to be associated an increased risk of PDAC. The exact interplay between family history, germline genetics, and PCNs still remains to be clarified. Some studies suggest that a family history of pancreatic cancer and germline mutations are associated with a higher risk of morphologic progression and cancer risk in pancreatic cysts, hence justifying closer and prolonged surveillance. However,other studies have not been able to demonstrate a strong correlation to justify a change in cyst surveillance based on a limited family history of PDAC.”
    Surveillance of Pancreatic Cystic Neoplasms
    Ankit Chhoda, Julie Schmidt, James J. Farrell
    Gastrointest Endoscopy Clin N Am 33 (2023) 613–640
  • “Artificial intelligence (AI) is a promising tool that has been applied to improve accuracy in screening for solid tumors, including breast, lung, cervical, and colon cancer. More recently, it has shown promise in diagnosing pancreatic cancer by identifying high-risk populations, risk-stratifying premalignant lesions, and predicting the progression of IPMNs to adenocarcinoma. This review summarizes the available literature on artificial intelligence in the screening and prognostication of precancerous lesions in the pancreas, and streamlining the diagnosis of pancreatic cancer.”
    Artificial Intelligence in the Diagnosis and Treatment of Pancreatic Cystic Lesions and Adenocarcinoma
    Joanna Jiang et al.
    Cancers 2023, 15, 2410
  • “Other PDACs (15–20%) originate as cystic lesions, most commonly intraductal papillary mucinous neoplasms (IPMNs), which account for half of all pancreatic cystic lesions (PCLs). IPMNs are mucin-producing epithelial tumors with papillary architecture on histology, and may progress to high-grade dysplasia and pancreatic cancer. They are classified by location. The most common type is branch-duct (BD)-IPMN, a cyst that communicates with the main pancreatic duct . Main-duct (MD)-IPMNs represent the main pancreatic duct dilation without other causes of obstruction. Mixed IPMNs display features of both types. Mucinous cystic neoplasms (MCNs), another type of mucinous cyst, also carry a risk of malignancy.”
    Artificial Intelligence in the Diagnosis and Treatment of Pancreatic Cystic Lesions and Adenocarcinoma
    Joanna Jiang et al.
    Cancers 2023, 15, 2410
  • “While the goal of surgery is to resect lesions with advanced neoplasia (high-grade dysplasia and/or adenocarcinoma), approximately 42–63% of resected IPMNs were found to have only low-grade dysplasia. Conversely, a negative biopsy or cytology does not rule out the presence of a high-risk lesion, and it is estimated that 5% of patients with IPMNs have concomitant adenocarcinoma elsewhere in the pancreas. Considering he high morbidity of resection techniques (including Whipple procedures, left pancreatectomy, or total pancreatectomy), there is a dire need for a reliable, accurate, and minimally invasive diagnostic tool for risk stratification of precancerous lesions.”
    Artificial Intelligence in the Diagnosis and Treatment of Pancreatic Cystic Lesions and Adenocarcinoma
    Joanna Jiang et al.
    Cancers 2023, 15, 2410
  • “New-onset diabetes has been suggested as a risk factor or potential early predictor of PDAC in multiple studies. The pathophysiology of this link is complex; longstanding diabetes is a known risk factor for PDAC, and new evidence suggests that pancreatic cancer may also cause diabetes through a paraneoplastic syndrome or direct effects on islets and insulin secretion. Using a discovery cohort of patients with new-onset diabetes, Sharma et al. (2018) created the END-PAC model to predict the development of pancreatic cancer within 3 years of diabetes onset. The AUC of this logistic regression model was 0.87, and sensitivity and specificity were 80%. Significant predictors included weight change, change in blood glucose, and age of onset of diabetes.”
    Artificial Intelligence in the Diagnosis and Treatment of Pancreatic Cystic Lesions and Adenocarcinoma
    Joanna Jiang et al.
    Cancers 2023, 15, 2410
  • “While CT and MRI classically provide qualitative data that are interpreted by radiologists, images can also be considered as a matrix with large amounts of quantitative data. Qureshi et al. published a novel study in identifying high-risk individuals based on “pre-diagnostic” CT imaging, acquired 6 months to 3 years before patients were diagnosed with PDAC. These imaging studies were performed prior to the development of qualitative signs of cancer that could be detected by trained radiologists. Textural and morphological features of the pancreas were analyzed from a set of 66 contrast-enhanced abdominal CT scans. The naïve Bayes classifier (ML algorithm) was able to classify scansinto pre-diagnostic vs. control (no PDAC diagnosis) groups with 86% accuracy in anexternal dataset. The generalizability of this model, however, was limited by its relatively small dataset.”
    Artificial Intelligence in the Diagnosis and Treatment of Pancreatic Cystic Lesions and Adenocarcinoma
    Joanna Jiang et al.
    Cancers 2023, 15, 2410
  • “ In a larger retrospective study including 214 patients who underwent resection for pancreatic cysts at Johns Hopkins, the radiomics-based random forest model yielded an AUC of 0.940 for distinguishing between five types of cystic neoplasms (IPMNs, MCNs, SPNs, SCAs, and cystic NETs) . The radiomics model was compared to radiologists’ diagnostic interpretation; the AUC for academic radiologists reached 0.895. Predictions were made based on radiomics features from preoperative CTs and demographics (age andgender). Liang et al. reported similar success for their SVM and logistic regression models in differentiating between IPMNs, MCNs, and SCAs based on data from CT images. An SVM algorithm was used to train a fused radiomics–DL model, which yielded an AUC of 0.92 for the diagnosis of SCA and 0.97 for differentiating between MCNs and IPMNs.”
    Artificial Intelligence in the Diagnosis and Treatment of Pancreatic Cystic Lesions and Adenocarcinoma
    Joanna Jiang et al.
    Cancers 2023, 15, 2410
  • “AI has been applied to imaging analysis of lung, prostate, and breast cancer; however, The pancreas is highly variable in size, shape, and location. It lies in close proximity to organs of varying radiographic textures (including the liver, stomach, intestines, and spleen), and occupies comparatively little space in cross-sectional images. Pancreatic tumors often have similar characteristics as their background tissue, which impacts diagnostic efficiency . Therefore, while AI algorithms for certain solid tumors are able to analyze minimally processed images, researchers often need to manually outline or segment the pancreas (divide it into four segments) prior to applying AI techniques. This increases specialist workload and time to arrive at a diagnosis. A group at Zhejiang University was able to create a deep learning model that automated image processing and analysis. Using nearly 150,000 abdominal CT images from 319 patients, the model was able to diagnose pancreatic tumors and propose treatment with an accuracy of 82.7% for all pancreatic tumor types. The model yielded an AUC of 0.87. Notably, there was higher accuracy for identifying PDAC (87.6%), and perfect accuracy (100%) for IPMNs.”
    Artificial Intelligence in the Diagnosis and Treatment of Pancreatic Cystic Lesions and Adenocarcinoma
    Joanna Jiang et al.
    Cancers 2023, 15, 2410
  • “Current challenges to creating accurate, scalable AI models for PDAC include insufficient data for model training, the subsequent risk of overfitting with prediction models, and the need for specialized, resource-rich hospitals with large patient populations to conduct such studies. There remains a need for multi-center studies that include diversecohorts to improve the generalizability of these algorithms. Additionally, the majority of radiomics algorithms in this review required manual preprocessing of images, which can be time-consuming for specialists. More sophisticated models that can be applied to unedited images or videos would reduce long-term healthcare utilization.”
    Artificial Intelligence in the Diagnosis and Treatment of Pancreatic Cystic Lesions and Adenocarcinoma
    Joanna Jiang et al.
    Cancers 2023, 15, 2410
  • “AI algorithms have been developed to identify high-risk populations who may benefit from PDAC screening, determine malignant potential of PCLs, and predict treatment response and cancer survival. Models for PCL risk stratification have demonstrated high accuracies, while algorithms for predicting an individual’s risk of developing PDAC were less reliable. There remains a role for more sophisticated algorithms that require minimal data pre-processing, as well as models developed using diverse, multi-center cohorts.”
    Artificial Intelligence in the Diagnosis and Treatment of Pancreatic Cystic Lesions and Adenocarcinoma
    Joanna Jiang et al.
    Cancers 2023, 15, 2410
  • “Artificial Intelligence (AI) is set to transform medical imaging by leveraging the vast data contained in medical images. Deep learning and radiomics are the two main AI methods currently being applied within radiology. Deep learning uses a layered set of self-correcting algorithms to develop a mathematical model that best fits the data. Radiomics converts imaging data into mineable features such as signal intensity, shape, texture, and higher-order features. Both methods have the potential to improve disease detection, characterization, and prognostication.”
    A primer on artificial intelligence in pancreatic imaging.  
    Ahmed TM, Kawamoto S, Hruban RH, Fishman EK, Soyer P, Chu LC.
    Diagn Interv Imaging. 2023 Mar 24:S2211-5684(23)00050-5.

  • A primer on artificial intelligence in pancreatic imaging.  
    Ahmed TM, Kawamoto S, Hruban RH, Fishman EK, Soyer P, Chu LC.
    Diagn Interv Imaging. 2023 Mar 24:S2211-5684(23)00050-5.
  • “While most prior studies had applied radiomics as a "second reader" to catch a diagnosis that may be missed due to human error, several more recent studies have reported that radiomics models may be able to detect PDAC before it is even discernable to the human eye on imaging. During the development of PDAC, the pancreas undergoes various morphological changes. PDACs may arise from detectable precancerous lesions such as intraductal papillary mucinous neoplasms (IPMN), and the pancreatic parenchyma upstream from a subtle cancer may show focal parenchymal atrophy and changes of chronic pancreatitis. Each of these can gradually increase the heterogeneity of the pancreatic tissue and result in detectable morphological and textural changes. These alterations may be difficult to interrogate on visual assessment, making AI the ideal tool to analyze them. Current studies on this have extracted radiomics features from prediagnostic CT examinations (3–36 months prior to the diagnosis of PDAC) and developed radiomics models that could predict the risk of developing PDAC with an accuracy ranging from 89.3% to100% .”
    A primer on artificial intelligence in pancreatic imaging.  
    Ahmed TM, Kawamoto S, Hruban RH, Fishman EK, Soyer P, Chu LC. Diagn Interv
    Imaging. 2023 Mar 24:S2211-5684(23)00050-5.
  • “A unique application of radiomics beyond diagnostics has been to predict preoperatively a patient's survival should they undergo surgical resection of PDAC. Survival prediction of PDAC currently relies mainly on postoperative features such as the TNM stage and margins. This precludes preoperative survival prediction which could separate patients who will benefit from surgery from those who will not. Although surgical resection remains the only cure for PDAC, it is associated with significant complications and carries a small mortality risk. The development of an accurate preoperative survival prediction model could allow for a quantitative risk-benefit analysis prior to pancreatic resection and allow for individualized triaging of patients for surgery based on overall anticipated benefit from resection. In the current literature, four studies directly compared the prognostic performance of radiomics models with the clinical TNM staging criteria, with all four studies reporting that the radiomics models outperformed clinical criteria in predicting overall survival.”
    A primer on artificial intelligence in pancreatic imaging.  
    Ahmed TM, Kawamoto S, Hruban RH, Fishman EK, Soyer P, Chu LC. Diagn Interv
    Imaging. 2023 Mar 24:S2211-5684(23)00050-5.
  • “Beyond quality and generalizability issues, several practical barriers also exist, with one being the determination of the added clinical value of these models. To truly gauge a model's clinical utility, it must be compared against existing gold standards. For studies reporting models that autonomously detect and classify pancreatic lesions, the gold standard remains the radiologists' reads, while among studies reporting models that predict patient survival, the gold standard is TNM staging. Amongst included studies, only 31.5% reported a comparison with these gold standards making interpretation of the net clinical benefit of most current models questionable. While the vast majority (98.1%) of reviewed studies discussed potential clinical applications, simply suggesting prospective methods in which AI models may be of value is no longer adequate and future studies should report objective metrics such as incremental value over gold standards or decision curve analyses alongside their models.”
    A primer on artificial intelligence in pancreatic imaging.  
    Ahmed TM, Kawamoto S, Hruban RH, Fishman EK, Soyer P, Chu LC. Diagn Interv
    Imaging. 2023 Mar 24:S2211-5684(23)00050-5.
  • “AI has made significant progress in the detection, classification, and prognostication of pancreatic lesions, through techniques such as radiomics and deep learning . Despite this promise, the quality of existing literature is far from robust. While we acknowledge that the potential value of existing literature may extend beyond what may be formally evaluated through the RQS tool, to fully realize the benefit of these advancements, current results need to be validated through higher quality studies and multicenter trials that include the full spectrum of normal and abnormal. Fundamental questions still need addressing before clinical adoption, and efforts to establish sound evidence for future studies is warranted. Given the rate of discovery of AI in abdominal imaging however, we optimistically believe that these challenges will inevitably be overcome and that a future in which synergy between radiologists and machines will become the norm is not a matter of ‘if’ but only a matter of ‘when’ .”
    A primer on artificial intelligence in pancreatic imaging.  
    Ahmed TM, Kawamoto S, Hruban RH, Fishman EK, Soyer P, Chu LC. Diagn Interv
    Imaging. 2023 Mar 24:S2211-5684(23)00050-5.
  •  Background: Few studies have focused on computed tomography findings before a pancreatic cancer diagnosis. We aimed to investigate the prediagnostic computed tomography findings of patients who had undergone computed tomography within the prediagnostic period of their pancreatic cancer diagnosis.  
    Conclusions: In contrast-enhanced computed tomography performed for other purposes, attention should be paid to the presence of a hypoattenuating mass, focal pancreatic duct dilatation, or distal parenchymal atrophy of the pancreas. These features may be clues for an early diagnosis of pancreatic cancer.    
    Suspicious findings observed retrospectively on CT imaging performed before the diagnosis of pancreatic cancer  
    Byung Kyu Park1^,  
    J Gastrointest Oncol 2023 | https://dx.doi.org/10.21037/jgo-22-863
  • What is known and what is new?  
    • In this study, 51.9% of the patients who underwent CT before pancreatic cancer diagnosis had findings suggestive of pancreatic cancer in a retrospective review.  
    • Suspicious findings of pancreatic cancer were a hypoattenuating mass, focal pancreatic duct dilatation, and distal parenchymal atrophy of the pancreas.  
    Suspicious findings observed retrospectively on CT imaging performed before the diagnosis of pancreatic cancer  
    Byung Kyu Park et al.  
    J Gastrointest Oncol 2023 | https://dx.doi.org/10.21037/jgo-22-863
  • “Early pancreatic cancer is mostly asymptomatic; therefore, the processes by which early pancreatic cancer is diagnosed are regular follow-up examination of high-risk patients, medical examination in a healthy general population, and the incidental detection of pancreatic lesions on imaging tests conducted for other purposes. Regular screening can be considered for patients in known high-risk groups for pancreatic cancer, but the selection of the patients and test method remain controversial. An international consensus recommends conducting follow-up EUS or MRI annually in individuals with a family history or genetically high risk of pancreatic cancer . The health examination for screening pancreatic cancer in the general population is not recommended because it is impractical and less cost-effective, and the diagnosis rate is low.”  
    Suspicious findings observed retrospectively on CT imaging performed before the diagnosis of pancreatic cancer  
    Byung Kyu Park et al.  
    J Gastrointest Oncol 2023 | https://dx.doi.org/10.21037/jgo-22-863
  • “In conclusion, pancreatic cancer is often incidentally detected on CT conducted for other purposes. Therefore, to diagnose pancreatic cancer in the early stage, clinicians need to always pay attention to the presence of a hypoattenuating mass, focal pancreatic duct dilatation, or distal parenchymal atrophy of the pancreas in contrast-enhanced CT conducted for other purposes, which may be clues for an early diagnosis of pancreatic cancer.”  
    Suspicious findings observed retrospectively on CT imaging performed before the diagnosis of pancreatic cancer
     Byung Kyu Park et al.  
    J Gastrointest Oncol 2023 | https://dx.doi.org/10.21037/jgo-22-863
  • “The cancers that are found in these high-risk individuals by MRI and/or EUS screening show favorable 73% 5-year overall survival. Even with the emphasis on screening in enriched high-risk populations, only a minority of incident cancers are detected this way. One strategy to improve early detection outcomes is to integrate artificial intelligence (AI) into biomarker discovery and risk models. This expert review summarizes recent publications that have developed AI algorithms for the applications of risk stratification of PDAC using radiomics and electronic health records. Furthermore, this review illustrates the current uses of radiomics and biomarkers in AI for early detection of PDAC. Finally, various challenges and potential solutions are highlighted regarding the use of AI in medicine for early detection purposes.
    Potential of artificial intelligence in the risk stratification for and early detection of pancreatic cancer
    Daniela R. Tovar, Michael H. Rosenthal, Aniban Maitra,Eugene J. Koay
    Art Int Surg 2023;3:14-26
  • ”Multiple challenges remain with clinical implementation of AI for early detection of PDAC. Awareness of the ethical and privacy concerns involved in examining patient data at population scales is essential to creating a trustworthy model. Privacy under protection and overprotection of patient information is a major concern when using big data. While under protecting data can lead to breaches in privacy, overprotecting can inhibit or block innovation. In the context of PDAC, new developments that balance data protection concerns are needed as early detection strategies are integrated into health systems. In addition, there are ethical pitfalls in implementing AI models in a healthcare setting. For example, there may be instances when the AI and physician disagree on a diagnosis, where the physician can explain their reasoning in their judgment, whereas AI cannot provide an explanation. Without a clear justification, the patient may not be given enough information to make the best decision for his or her own health. The physician may keep their original diagnosis, but in the case that it is wrong, it will appear as if they were disregarding crucial evidence. They may also be pressured into agreeing with the model, trusting its accuracy more than their clinical judgement.”
    Potential of artificial intelligence in the risk stratification for and early detection of pancreatic cancer
    Daniela R. Tovar, Michael H. Rosenthal, Aniban Maitra,Eugene J. Koay
    Art Int Surg 2023;3:14-26
  • “This review summarizes the recent developments in which AI has the potential to aid early detection efforts. Risk prediction models have been developed by focusing on factors associated with PDAC, such as new onset diabetes, to identify those who may benefit from surveillance imaging. With proper validation and development, AI may be used as an aid for clinicians to detect cancer growth at a curable stage by using blood-based markers, radiomics and analyzing fecal microbiome composition. In the development of AI models, ethical and privacy concerns should be carefully addressed before full implementation, including data protection and discordant conclusions between AI and physicians. Future studies incorporating federated learning may advance these efforts by assembling large and diverse data while ensuring patient data privacy. In building AI models for clinical implementation, considerations of transparency about the model application and in what settings AI should be deployed are critical to ensure proper use for PDAC early detection and other AI applications.”
    Potential of artificial intelligence in the risk stratification for and early detection of pancreatic cancer
    Daniela R. Tovar, Michael H. Rosenthal, Aniban Maitra,Eugene J. Koay
    Art Int Surg 2023;3:14-26

  • Potential of artificial intelligence in the risk stratification for and early detection of pancreatic cancer
    Daniela R. Tovar, Michael H. Rosenthal, Aniban Maitra,Eugene J. Koay
    Art Int Surg 2023;3:14-26
  • “Pancreatic ductal adenocarcinoma (PDAC) is the third most lethal cancer in the United States, with a 5-year life expectancy of 11%. Most symptoms manifest at an advanced stage of the disease when surgery is no longer appropriate. The dire prognosis of PDAC warrants new strategies to improve the outcomes of patients, and early detection has garnered significant attention. However, early detection of PDAC is most often incidental, emphasizing the importance of developing new early detection screening strategies. Due to the low incidence of the disease in the general population, much of the focus for screening has turned to individuals at high risk of PDAC. This enriches the screening population and balances the risks associated with pancreas interventions. The cancers that are found in these high-risk individuals by MRI and/or EUS screening show favorable 73% 5-year overall survival. Even with the emphasis on screening in enriched high-risk populations, only a minority of incident cancers are detected this way. One strategy to improve early detection outcomes is to integrate artificial intelligence (AI) into biomarker discovery and risk models. This expert review summarizes recent publications that have developed AI algorithms for the applications of risk stratification of PDAC using radiomics and electronic health records. Furthermore, this review illustrates the current uses of radiomics and biomarkers in AI for early detection of PDAC.”
    Potential of artificial intelligence in the risk stratification for and early detection of pancreatic cancer
    Daniela R. Tovar, Michael H. Rosenthal, Anirban Maitra, Eugene J. Koay
    Art Int Surg 2023;3:14-26
  • “To overcome the significant challenge of screening in the general population, researchers have focused surveillance methods for high-risk populations, including patients with multiple first-degree relatives with a history of PDAC diagnosis and high-risk germline mutations, although the frequency and modality(ies) of surveillance of these individuals remains an open research question. Furthermore, another major clinical conundrum is the surveillance of patients who have incidental findings of mucinous cysts such as intraductal papillary mucinous neoplasms (IPMNs) or mucinous cystic neoplasms (MCNs) in the pancreas. Only a small proportion of IPMNs and MCNs undergo malignant transformation, but a high proportion are overdiagnosed and subsequently overtreated.”
    Potential of artificial intelligence in the risk stratification for and early detection of pancreatic cancer
    Daniela R. Tovar, Michael H. Rosenthal, Anirban Maitra, Eugene J. Koay
    Art Int Surg 2023;3:14-26
  • “This review summarizes the recent developments in which AI has the potential to aid early detection efforts. Risk prediction models have been developed by focusing on factors associated with PDAC, such as new onset diabetes, to identify those who may benefit from surveillance imaging. With proper validation and development, AI may be used as an aid for clinicians to detect cancer growth at a curable stage by using blood-based markers, radiomics and analyzing fecal microbiome composition. In the development of AI models, ethical and privacy concerns should be carefully addressed before full implementation, including data protection and discordant conclusions between AI and physicians. Future studies incorporating federated learning may advance these efforts by assembling large and diverse data while ensuring patient data privacy. In building AI models for clinical implementation, considerations of transparency about the model application and in what settings AI should be deployed are critical to ensure proper use for PDAC early detection and other AI applications.”
    Potential of artificial intelligence in the risk stratification for and early detection of pancreatic cancer
    Daniela R. Tovar, Michael H. Rosenthal, Anirban Maitra, Eugene J. Koay
    Art Int Surg 2023;3:14-26
  • “Pancreatic cysts are often incidentally detected on cross-sectional imaging, from approximately 2% of abdominal computed tomography (CT) to 20% of magnetic resonance imaging (MRI) exams. These pancreatic cysts represent a spectrum of pathologies ranging from benign (e.g., serous cystadenoma [SCA], pseudocyst), cysts with malignant potential (e.g., mucinous cystic neoplasm [MCN], intraductal papillary mucinous neoplasm [IPMN]), to cystic or necrotic appearance of overt malignancies (e.g., pancreatic ductal adenocarcinoma [PDAC], pancreatic neuroendocrine tumor [PNET]). These pancreatic cysts can have overlapping clinical and imaging features and can be difficult to diagnose accurately.”
    Artificial Intelligence in the Detection and Surveillance of Cystic Neoplasms
    Chu LC, Fishman EK
    The Pancreas: An Integrated Textbook of Basic Science, Medicine, and Surgery, Fourth Edition 2023
    Edited by Hans G. Beger, Markus W. Büchler,Ralph H. Hruban, et al.
  • “Machine learning is a subset of AI that trains the algorithms to perform tasks by learning patterns from the data, instead of by explicit programming. The machine learning algorithms can be trained using supervised or unsupervised learning methods. In supervised learning, the algorithm is provided with annotated “ground truth” labels, which is used as feedback to improve the algorithm in an iterative process. The ground truth is the reference standard, which can range from normal versus abnormal at the individual patient level, to detailed slice-by- slice labeling of medical images. In unsupervised learning, the algorithm determines how to classify the data into groups, without the assistance of ground truth labels .”
    Artificial Intelligence in the Detection and Surveillance of Cystic Neoplasms
    Chu LC, Fishman EK
    The Pancreas: An Integrated Textbook of Basic Science, Medicine, and Surgery, Fourth Edition 2023
    Edited by Hans G. Beger, Markus W. Büchler,Ralph H. Hruban, et al.
  • “Liu et al. trained a CNN from CT images obtained from 752 patients with pancreatic cancer and 490 healthy controls, and showed that the CNN model was 97.3–99.0% sensitive, 98.9–100% specific, and 98.6–98.9% accurate in the differentiation of pancreatic cancer from healthy controls . The CNN model achieved superior sensitivity in pancreatic cancer detection compared to radiologists who originally interpreted the studies (97.3–99.0% vs 91.7–94.4%), and it was able to correctly identify 11/12 (92%) of the pancreatic cancers that were missed by the original radiologists’ interpretation. The authors validated their model on external test set, which demonstrated 79.0% sensitivity, 97.6% specificity, and 83.2% accuracy, with the caveat that the pancreatic cancer cases and the healthy control cases came from different institutions, which could affect the performance of the model.”
    Artificial Intelligence in the Detection and Surveillance of Cystic Neoplasms
    Chu LC, Fishman EK
    The Pancreas: An Integrated Textbook of Basic Science, Medicine, and Surgery, Fourth Edition 2023
    Edited by Hans G. Beger, Markus W. Büchler,Ralph H. Hruban, et al.
  • “Several radiomics and machine learning studies have focused on predicting the dysplasia grade in IPMNs. These studies, heterogeneous in design, differed in the type of imaging modality (CT, MRI, endoscopic US), type of cysts (inclusion or exclusion of main-duct IPMN, cases with invasive carcinoma), and validation methods. Despite their methodologic variations, these studies support the notion that radiomics with machine learning (AUC range 0.76–0.96) were superior to guideline-based clinical features (AUC range 0.56–0.84), and the combination of the two (AUC range 0.79–0.93) may offer the best performance in distinguishing between low-grade dysplasia and high-grade dysplasia or invasive carcinoma. Such models could help refine the selection criteria for surgical resection, reduce unnecessary surgery, and tailor the surveillance interval based on the risk profiles of individual patients.”
    Artificial Intelligence in the Detection and Surveillance of Cystic Neoplasms
    Chu LC, Fishman EK
    The Pancreas: An Integrated Textbook of Basic Science, Medicine, and Surgery, Fourth Edition 2023
    Edited by Hans G. Beger, Markus W. Büchler,Ralph H. Hruban, et al.
  • “Artificial intelligence has the potential to improve the detection of pancreatic pathology from medical images, which can lead to earlier pancreatic cancer diagnosis. It also has the potential to improve the diagnostic accuracy in pancreatic cyst classification and assessment of malignancy risk. These promising results must be validated in large-scale multi-institutional clinical trials. Future comprehensive AI models should integrate numerous sources of clinical data and can provide clinical decision support at various stages to determine the next most appropriate diagnostic test or management strategy.”
    Artificial Intelligence in the Detection and Surveillance of Cystic Neoplasms
    Chu LC, Fishman EK
    The Pancreas: An Integrated Textbook of Basic Science, Medicine, and Surgery, Fourth Edition 2023
    Edited by Hans G. Beger, Markus W. Büchler,Ralph H. Hruban, et al.
  • Methods: In this IRB-approved retrospective single-institution study, patients with surgically resected pancreatic cysts who underwent preoperative abdominal CT from 2003 to 2016 were identified. Pancreatic cyst(s) and background pancreas were manually segmented, and 488 radiomics features were extracted. Random forest classification based on radiomics features, age, and gender was evaluated with fourfold cross-validation. An academic radiologist blinded to the final pathologic diagnosis reviewed each case and provided the most likely diagnosis.
    Results: 214 patients were included (64 intraductal papillary mucinous neoplasms, 33 mucinous cystic neoplasms, 60 serous cystadenomas, 24 solid pseudopapillary neoplasms, and 33 cystic neuroendocrine tumors). The radiomics-based machine learning approach showed AUC of 0.940 in pancreatic cyst classification, compared with AUC of 0.895 for the radiologist.
    Conclusion: Radiomics-based machine learning achieved equivalent performance as an experienced academic radiologist in the classification of pancreatic cysts. The high diagnostic accuracy can potentially maximize the efficiency of healthcare utilization by maximizing detection of high-risk lesions.
    Classification of pancreatic cystic neoplasms using radiomic feature analysis is equivalent to an experienced academic radiologist: a step toward computer‑augmented diagnostics for radiologists
    Linda C. Chu et al.
    Abdominal Radiology (2022) 47:4139–4150
  • Conclusion: Radiomics-based machine learning achieved equivalent performance as an experienced academic radiologist in the classification of pancreatic cysts. The high diagnostic accuracy can potentially maximize the efficiency of healthcare utilization by maximizing detection of high-risk lesions.
    Classification of pancreatic cystic neoplasms using radiomic feature analysis is equivalent to an experienced academic radiologist: a step toward computer‑augmented diagnostics for radiologists
    Linda C. Chu et al.
    Abdominal Radiology (2022) 47:4139–4150

  • Classification of pancreatic cystic neoplasms using radiomic feature analysis is equivalent to an experienced academic radiologist: a step toward computer‑augmented diagnostics for radiologists
    Linda C. Chu et al.
    Abdominal Radiology (2022) 47:4139–4150

  • Classification of pancreatic cystic neoplasms using radiomic feature analysis is equivalent to an experienced academic radiologist: a step toward computer‑augmented diagnostics for radiologists
    Linda C. Chu et al.
    Abdominal Radiology (2022) 47:4139–4150
  • In this study, the performance of the radiomics feature based classification achieved AUC of 0.940 in distinguishing among five types of pancreatic cystic neoplasms. The performance was similar to previous studies with multi-class pancreatic cyst classifications that included three or four cyst types, with accuracy of 79.6–83.6%. Previous studies on radiomics-based pancreatic cyst classification did not include a direct comparison with a radiologist, therefore, it was difficult to assess if the radiomics-based classification reported provided any added value relative to the standard of care. The current study showed that the radiomics-based pancreatic cyst classification achieved equivalent performance as an academic radiologist with more than 25 years of experience. These results indicate that radiomics- based classification could be valuable in improving the current standard of care.
    Classification of pancreatic cystic neoplasms using radiomic feature analysis is equivalent to an experienced academic radiologist: a step toward computer‑augmented diagnostics for radiologists
    Linda C. Chu et al.
    Abdominal Radiology (2022) 47:4139–4150  
  • This study showed that a radiomics-based model can achieve equivalent performance as an experienced academic radiologist in the classification of a wide array of pancreatic cysts with variable malignant potential. This model has the potential to refine pancreatic cyst management by improving diagnostic accuracy of cystic lesions, which can minimize healthcare utilization while maximizing detection of malignant lesions. This study confirms the ability of a radiomic based model to accurately classify pancreatic cystic neoplasms. Further validation and clinical integration of this model could help optimize management of pancreatic cysts by maximizing the rate of detection of malignant lesions while reducing healthcare utilization.
    Classification of pancreatic cystic neoplasms using radiomic feature analysis is equivalent to an experienced academic radiologist: a step toward computer‑augmented diagnostics for radiologists
    Linda C. Chu et al.
    Abdominal Radiology (2022) 47:4139–4150
  • Purpose: A wide array of benign and malignant lesions of the pancreas can be cystic and these cystic lesions can have overlapping imaging appearances. The purpose of this study is to compare the diagnostic accuracy of a radiomics-based pancreatic cyst classifier to an experienced academic radiologist.
    Classification of pancreatic cystic neoplasms using radiomic feature analysis is equivalent to an experienced academic radiologist: a step toward computer‑augmented diagnostics for radiologists
    Linda C. Chu et al.
    Abdom Radiol (NY). 2022 Sep 13. doi: 10.1007/s00261-022-03663-6. Online ahead of print.
  • Results: 214 patients were included (64 intraductal papillary mucinous neoplasms, 33 mucinous cystic neoplasms, 60 serous cystadenomas, 24 solid pseudopapillary neoplasms, and 33 cystic neuroendocrine tumors). The radiomics-based machine learning approach showed AUC of 0.940 in pancreatic cyst classification, compared with AUC of 0.895 for the radiologist.  
    Conclusion: Radiomics-based machine learning achieved equivalent performance as an experienced academic radiologist in the classification of pancreatic cysts. The high diagnostic accuracy can potentially maximize the efficiency of healthcare utilization by maximizing detection of high-risk lesions.  
    Classification of pancreatic cystic neoplasms using radiomic feature analysis is equivalent to an experienced academic radiologist: a step toward computer‑augmented diagnostics for radiologists
    Linda C. Chu et al.
    Abdominal Radiology (2022) 47:4139–4150 
  • “A total of 488 radiomics features from the segmented volume were extracted to define cystic lesion and pancreas phenotypes based on venous phase images. Radiomics features used in this study included 14 first-order statistics of the volumetric CT intensities, 8 shape features of the target structure, 33 texture features from a gray-level co-occurrence matrix and a gray-level run-length matrix, 376 texture features from the 8 filtered volumes by wavelets, and an additional 47 texture features form the filtered volume by Laplacian of Gaussian (LoG). Ten image features were extracted from the whole pancreatic region. Table 2 represents the whole feature set used for cyst classification in this study. Two demographic features, age and gender, were also incorporated into the final model.”
    Classification of pancreatic cystic neoplasms using radiomic feature analysis is equivalent to an experienced academic radiologist: a step toward computer‑augmented diagnostics for radiologists
    Linda C. Chu et al.
    Abdominal Radiology (2022) 47:4139–4150
  • AI and Pancreatic Adenocarcinoma
    - Early (earlier) detection
    - Improved staging of disease
    - Pre-operative planning
    - Selection of chemotherapy
    - Selection of radiation therapy
    - Prediction of outcome/survival
  • Early Detection
  • Pre-Operative Planning
  • Pre-Operative Planning
  • “Radiomics is a rapidly growing field that quantitatively extracts image features in a high-throughput manner from medical imaging. In this study, we analyzed the radiomics features of the whole pancreas between healthy individuals and pancreatic cancer patients, and we established a predictive model that can distinguish cancer patients from healthy individuals based on these radiomics features.”
    Compute Tomography Radiomics Analysis on Whole Pancreas Between Healthy Individual and Pancreatic Ductal Adenocarcinoma Patients: Uncertainty Analysis and Predictive Modeling
    Shuo Wang et al.
    Technology in Cancer Research & Treatment Volume 21: 1-14 2022
  • Results: We identified that 91 radiomics features are stable against various uncertainty sources, including bin width, resampling, image transformation, image noise, and segmentation uncertainty. Eight of the 91 features are nonredundant. Our final predictive model, using these 8 features, has achieved a mean area under the receiver operating characteristic curve (AUC) of 0.99±0.01 on the training dataset (189 subjects) by cross-validation. The model achieved an AUC of 0.910 on the independent test set (77 subjects) and an accuracy of 0.935.  
    Conclusion: CT-based radiomics analysis based on the whole pancreas can distinguish cancer patients from healthy individuals, and it could potentially become an early detection tool for pancreatic cancer.
    Compute Tomography Radiomics Analysis on Whole Pancreas Between Healthy Individual and Pancreatic Ductal Adenocarcinoma Patients: Uncertainty Analysis and Predictive Modeling
    Shuo Wang et al.
    Technology in Cancer Research & Treatment Volume 21: 1-14 2022
  • “Second, our study is a single-institution study without any external validation, which is one of the essential metrics for assessing the robustness of a study. Although we sought to improve the  robustness of our study by randomizing the TCIA public dataset into our radiomic analysis and predictive analytics, the generalizability of our results remains to be further validated on new datasets. Third, although all the CT images we collected are the venous phases of the contrast CT, it is difficult to evaluate contrast enhancement variation since it depends on patient-specific physiology (eg, blood flow rate). Therefore, we did not study the feature stability against contrast enhancement variation among various patients.”
    Compute Tomography Radiomics Analysis on Whole Pancreas Between Healthy Individual and Pancreatic Ductal Adenocarcinoma Patients: Uncertainty Analysis and Predictive Modeling
    Shuo Wang et al.
    Technology in Cancer Research & Treatment Volume 21: 1-14 2022
  • Conclusion: Our study proved that CT-based radiomics analysis and modeling can distinguish healthy individuals from pancreatic cancer patients, and potentially can become an effective tool to detect cancerous pancreatic tissue at an early stage.
    Compute Tomography Radiomics Analysis on Whole Pancreas Between Healthy Individual and Pancreatic Ductal Adenocarcinoma Patients: Uncertainty Analysis and Predictive Modeling
    Shuo Wang et al.
    Technology in Cancer Research & Treatment Volume 21: 1-14 2022
  • Background: Approximately 40% of pancreatic tumors smaller than 2 cm are missed at abdominal CT.
    Purpose: To develop and to validate a deep learning (DL)–based tool able to detect pancreatic cancer at CT.
    Conclusion: The deep learning–based tool enabled accurate detection of pancreatic cancer on CT scans, with reasonable sensitivity for tumors smaller than 2 cm.
    Pancreatic Cancer Detection on CT Scans with Deep Learning: A Nationwide Population-based Study
    Po-Ting Chen et al.
    Radiology 2022; 000:1–11 (in press)
  • “Approximately 40% of pancreatic tumors smaller than 2 cm are missed at abdominal CT.”
    Pancreatic Cancer Detection on CT Scans with Deep Learning: A Nationwide Population-based Study
    Po-Ting Chen et al.
    Radiology 2022; 000:1–11 (in press)
  • Materials and Methods: Retrospectively collected contrast-enhanced CT studies in patients diagnosed with pancreatic cancer between January 2006 and July 2018 were compared with CT studies of individuals with a normal pancreas (control group) obtained between January 2004 and December 2019. An end-to-end tool comprising a segmentation convolutional neural network (CNN) and a classifier ensembling five CNNs was developed and validated in the internal test set and a nationwide real-world validation set. The sensitivities of the computer-aided detection (CAD) tool and radiologist interpretation were compared using the McNemar test.
    Pancreatic Cancer Detection on CT Scans with Deep Learning: A Nationwide Population-based Study
    Po-Ting Chen et al.
    Radiology 2022; 000:1–11 (in press)
  • Results: A total of 546 patients with pancreatic cancer (mean age, 65 years 6 12 [SD], 297 men) and 733 control subjects were randomly divided into training, validation, and test sets. In the internal test set, the DL tool achieved 89.9% (98 of 109; 95% CI: 82.7, 94.9) sensitivity and 95.9% (141 of 147; 95% CI: 91.3, 98.5) specificity (area under the receiver operating characteristic curve [AUC], 0.96; 95% CI: 0.94, 0.99), without a significant difference (P = .11) in sensitivity compared with the original radiologist report (96.1% [98 of 102]; 95% CI: 90.3, 98.9). In a test set of 1473 real-world CT studies (669 malignant, 804 control) from institutions throughout Taiwan, the DL tool distinguished between CT malignant and control studies with 89.7% (600 of 669; 95% CI: 87.1, 91.9) sensitivity and 92.8% specificity (746 of 804; 95% CI: 90.8, 94.5) (AUC, 0.95; 95% CI: 0.94, 0.96), with 74.7% (68 of 91; 95% CI: 64.5, 83.3) sensitivity for malignancies smaller than 2 cm.
    Pancreatic Cancer Detection on CT Scans with Deep Learning: A Nationwide Population-based Study
    Po-Ting Chen et al.
    Radiology 2022; 000:1–11 (in press)
  • “CT is the major imaging modality used to help detect PC, but its sensitivity for small tumors is modest, with approximately 40% of tumors smaller than 2 cm being missed. Furthermore, the diagnostic performance of CT is interpreter dependent and may be influenced by disparities in radiologist availability and expertise. Therefore, an effective tool to supplement radiologists in improving the sensitivity for PC detection is needed and constitutes a major unmet medical need.”  
    Pancreatic Cancer Detection on CT Scans with Deep Learning: A Nationwide Population-based Study
    Po-Ting Chen et al.
    Radiology 2022; 000:1–11 (in press)
  • Key Results
    • A deep learning tool for pancreatic cancer detection that was developed using contrast-enhanced CT scans obtained in 546 patients with pancreatic cancer and in 733 healthy control subjects achieved 89.9% sensitivity and 95.9% specificity in the internal test set (109 patients, 147 control subjects), which was similar to the sensitivity of radiologists (96.1%; P = .11).
    • In a validation set comprising 1473 individual CT studies (669 patients, 804 control subjects) from institutions throughout Taiwan, the deep learning tool achieved 89.7% sensitivity and 92.8% specificity in distinguishing pancreatic cancer, with 74.7% sensitivity for pancreatic cancers smaller than 2 cm.  
    Pancreatic Cancer Detection on CT Scans with Deep Learning: A Nationwide Population-based Study
    Po-Ting Chen et al.
    Radiology 2022; 000:1–11 (in press)
  • “Last, the control group did not include patients with pancreatic abnormalities other than PC, many of which require tissue sampling for confirmatory diagnosis. We seek to include other pancreatic abnormalities and prospectively assess the potential usefulness of the CAD tool in clinical settings in a future study.”    
    Pancreatic Cancer Detection on CT Scans with Deep Learning: A Nationwide Population-based Study
    Po-Ting Chen et al.
    Radiology 2022; 000:1–11 (in press)
  • “In conclusion, this study developed an end-to-end deep learning–based computer-aided detection (CAD) tool that could accurately and robustly detect pancreatic cancers (PCs) on contrast-enhanced CT scans. The CAD tool may be a useful supplement for radiologists to enhance detection of PC. Our results also suggest that the classification convolutional neural networks might have learned the secondary signs of PC, which warrants further investigation. While the results of this study provide strong support for the generalizability of the CAD tool in the Taiwanese and perhaps Asian populations, the performance of the CAD tool in other populations needs to be evaluated further.”
    Pancreatic Cancer Detection on CT Scans with Deep Learning: A Nationwide Population-based Study
    Po-Ting Chen et al.
    Radiology 2022; 000:1–11 (in press)
  • “Mukherjee et al. explored the ability of quantitative CT radiomic features of the pancreas to identity patients who would develop pancreatic cancer in the subsequent 3 to 36 months. They found that their radiomics-based model showed good predictive capacity, achieving sensitivity of 95% and specificity of 90% in a validation sample. Importantly, they showed performance robustness across CT scanners and slice thicknesses, and the model outperformed radiologists in identifying cases of pancreatic cancer. These findings add to the growing body of evidence that the indirect effects of pancreatic cancer, including endocrine and exocrine dysfunction and now whole-organ radiomic changes, may precede the diagnosis of cancer and could serve as early detection biomarkers.”
    Beyond the AJR: CT Radiomic Features of the Pancreas Predict Development of Pancreatic Cancer.
    Rosenthal MH, Schawkat K.
    AJR 2022 Oct 5 [published online]. Accepted manuscript. doi:10.2214/AJR.22.28582
  • “This work adds another potential tool to the radiologist’s arsenal for opportunistic screening from routine clinical imaging. Opportunistic screening takes advantage of features within imaging examinations that are not the subject of the examination but nonetheless convey important information about entities such as cardiovascular risk . Potential CT-based biomarkers for cancer include body composition analysis, CT based radiomic and texture analysis, and organ-based volumetry. These automated CT biomarkers could be deployed as part of the radiologist’s clinical workflow, allowing for prospective risk profiling in practice. In pancreatic cancer, opportunistic screening could identify individuals at sufficiently high risk to warrant active screening, as is currently performed for high-risk families. Such an approach, however, would generate a high rate of false positives for every true positive. To be clinically useful, it will likely need to be integrated with other risk markers.”
    Beyond the AJR: CT Radiomic Features of the Pancreas Predict Development of Pancreatic Cancer.
    Rosenthal MH, Schawkat K.
    AJR 2022 Oct 5 [published online]. Accepted manuscript. doi:10.2214/AJR.22.28582
  • “The use of ML-based radiomic analyses may offer a novel screening strategy for pancreatic cancer by detecting changes in the pancreas that precede the development of pancreatic cancer and the emergence of a radiologically detectable mass.”
    Beyond the AJR: CT Radiomic Features of the Pancreas Predict Development of Pancreatic Cancer.
    Rosenthal MH, Schawkat K.
    AJR 2022 Oct 5 [published online]. Accepted manuscript. doi:10.2214/AJR.22.28582
  • “Radiomics is a rapidly growing field that quantitatively extracts image features in a high-throughput manner from medical imaging. In this study, we analyzed the radiomics features of the whole pancreas between healthy individuals and pancreatic cancer patients, and we established a predictive model that can distinguish cancer patients from healthy individuals based on these radiomics features.”
    Compute Tomography Radiomics Analysis on Whole Pancreas Between Healthy Individual and Pancreatic Ductal Adenocarcinoma Patients: Uncertainty Analysis and Predictive Modeling
    Shuo Wang et al.
    Technology in Cancer Research & Treatment 2022; Volume 21: 1-14
  • Results: We identified that 91 radiomics features are stable against various uncertainty sources, including bin width, resampling, image transformation, image noise, and segmentation uncertainty. Eight of the 91 features are nonredundant. Our final predictive model, using these 8 features, has achieved a mean area under the receiver operating characteristic curve (AUC) of 0.99±0.01 on the training dataset (189 subjects) by cross-validation. The model achieved an AUC of 0.910 on the independent test set (77 subjects)and an accuracy of 0.935.  
    Conclusion: CT-based radiomics analysis based on the whole pancreas can distinguish cancer patients from healthy individuals, and it could potentially become an early detection tool for pancreatic cancer.
    Compute Tomography Radiomics Analysis on Whole Pancreas Between Healthy Individual and Pancreatic Ductal Adenocarcinoma Patients: Uncertainty Analysis and Predictive Modeling
    Shuo Wang et al.
    Technology in Cancer Research & Treatment 2022; Volume 21: 1-14
  • “Our study proved that CT-based radiomics analysis and modeling can distinguish healthy individuals from pancreatic cancer patients, and potentially can become an effective tool to detect cancerous pancreatic tissue at an early stage.”  
    Compute Tomography Radiomics Analysis on Whole Pancreas Between Healthy Individual and Pancreatic Ductal Adenocarcinoma Patients: Uncertainty Analysis and Predictive Modeling
    Shuo Wang et al.
    Technology in Cancer Research & Treatment 2022; Volume 21: 1-14
  • Results: A total of 546 patients with pancreatic cancer (mean age, 65 years 6 12 [SD], 297 men) and 733 control subjects were randomly divided into training, validation, and test sets. In the internal test set, the DL tool achieved 89.9% (98 of 109; 95% CI: 82.7, 94.9) sensitivity and 95.9% (141 of 147; 95% CI: 91.3, 98.5) specificity (area under the receiver operating characteristic curve [AUC], 0.96; 95% CI: 0.94, 0.99), without a significant difference (P = .11) in sensitivity compared with the original radiologist report (96.1% [98 of 102]; 95% CI: 90.3, 98.9). In a test set of 1473 real-world CT studies (669 malignant, 804 control) from institutions throughout Taiwan, the DL tool distinguished between CT malignant and control studies with 89.7% (600 of 669; 95% CI: 87.1, 91.9) sensitivity and 92.8% specificity (746 of 804; 95% CI: 90.8, 94.5) (AUC, 0.95; 95% CI: 0.94, 0.96), with 74.7% (68 of 91; 95% CI: 64.5, 83.3) sensitivity for malignancies smaller than 2 cm.”
    Pancreatic Cancer Detection on CT Scans with Deep Learning: A Nationwide Population-based Study
    Po-Ting Chen et al.
    Radiology 2022; 000:1–11
  • “A deep learning tool for pancreatic cancer detection that was developed using contrast-enhanced CT scans obtained in 546 patients with pancreatic cancer and in 733 healthy control subjects achieved 89.9% sensitivity and 95.9% specificity in the internal test set (109 patients, 147 control subjects), which was similar to the sensitivity of radiologists (96.1%; P = .11). N In a validation set comprising 1473 individual CT studies (669 patients, 804 control subjects) from institutions throughout Taiwan, the deep learning tool achieved 89.7% sensitivity and 92.8% specificity in distinguishing pancreatic cancer, with 74.7% sensitivity for pancreatic cancers smaller than 2 cm.”  
    Pancreatic Cancer Detection on CT Scans with Deep Learning: A Nationwide Population-based Study
    Po-Ting Chen et al.
    Radiology 2022; 000:1–11
  • “In a validation set comprising 1473 individual CT studies (669 patients, 804 control subjects) from institutions throughout Taiwan, the deep learning tool achieved 89.7% sensitivity and 92.8% specificity in distinguishing pancreatic cancer, with 74.7% sensitivity for pancreatic cancers smaller than 2 cm.”  
    Pancreatic Cancer Detection on CT Scans with Deep Learning: A Nationwide Population-based Study
    Po-Ting Chen et al.
    Radiology 2022; 000:1–11
  • “In conclusion, this study developed an end-to-end deep learning–based computer-aided detection (CAD) tool that could accurately and robustly detect pancreatic cancers (PCs) on contrast-enhanced CT scans. The CAD tool may be a usefulsupplement for radiologists to enhance detection of PC. Ourresults also suggest that the classification convolutional neura networks might have learned the secondary signs of PC, whichwarrants further investigation. While the results of this studyprovide strong support for the generalizability of the CAD tool in the Taiwanese and perhaps Asian populations, the performance of the CAD tool in other populations needs to be evaluated further.”  
    Pancreatic Cancer Detection on CT Scans with Deep Learning: A Nationwide Population-based Study
    Po-Ting Chen et al.
    Radiology 2022; 000:1–11
  • Summary
    A deep learning–based approach showed high diagnostic performance for identifying patients with solid and cystic pancreatic neoplasms at contrast-enhanced CT.
    Key Results  
    * In a retrospective study of 852 patients for training and two independent test sets comprising 1192 patients for validation, a deep learning (DL)–based approach to identify solid or cystic pancreatic lesions at CT showed an area under the receiver operating characteristic curve of 0.87–0.91.
    * The DL-based approach showed high sensitivity in identifying solid lesions of any size (98% [63 of 64 patients] to 100% [58 of 58 patients]) or cystic lesions measuring 1.0 cm or larger (92% [34 of 37 patients] to 93% [52 of 56 patients]).
    Deep Learning–based Detection of Solid and Cystic Pancreatic Neoplasms at Contrast-enhanced CT
    Hyo Jung Park, et al.
    Radiology 2022; 000:1–11 

  • Deep Learning–based Detection of Solid and Cystic Pancreatic Neoplasms at Contrast-enhanced CT
    Hyo Jung Park, et al.
    Radiology 2022; 000:1–11 
  • “As the future step, DL applications for pancreatic imaging should aim for accurate segmentation or detection of pancreatic lesions even in pancreases with diffuse abnormalities, suchas pancreatitis. Accurate and robust classification of pancreatic lesions (ie, differentiation of malignancy and benignity or classification among several common pancreatic tumors) should also become available, and such algorithms should be developed to perform as a standalone or second reader to facilitate the reading processes of radiologists. In addition, as the incorporation of DL algorithms in clinical practice is an important issue, the clinical feasibility of the DL algorithms should be further evaluated.”
    Deep Learning–based Detection of Solid and Cystic Pancreatic Neoplasms at Contrast-enhanced CT
    Hyo Jung Park, et al.
    Radiology 2022; 000:1–11 
  • “In conclusion, the deep learning–based approach demonstrated high diagnostic performance in identifying patients with various solid or cystic neoplasms at CT. Our approach has the potential to facilitate timely diagnoses and management of pancreatic lesions encountered in routine clinical practice.”
    Deep Learning–based Detection of Solid and Cystic Pancreatic Neoplasms at Contrast-enhanced CT
    Hyo Jung Park, et al.
    Radiology 2022; 000:1–11 
  • Background: Approximately 40% of pancreatic tumors smaller than 2 cm are missed at abdominal CT.
    Purpose: To develop and to validate a deep learning (DL)–based tool able to detect pancreatic cancer at CT.
    Conclusion: The deep learning–based tool enabled accurate detection of pancreatic cancer on CT scans, with reasonable sensitivity for tumors smaller than 2 cm.
    Pancreatic Cancer Detection on CT Scans with Deep Learning: A Nationwide Population-based Study
    Po-Ting Chen et al.
    Radiology 2022; 000:1–11
  • Materials and Methods: Retrospectively collected contrast-enhanced CT studies in patients diagnosed with pancreatic cancer between January 2006 and July 2018 were compared with CT studies of individuals with a normal pancreas (control group) obtained between January 2004 and December 2019. An end-to-end tool comprising a segmentation convolutional neural network (CNN) and a classifier ensembling five CNNs was developed and validated in the internal test set and a nationwide real-world validation set. The sensitivities of the computer-aided detection (CAD) tool and radiologist interpretation were compared using the McNemar test.
    Pancreatic Cancer Detection on CT Scans with Deep Learning: A Nationwide Population-based Study
    Po-Ting Chen et al.
    Radiology 2022; 000:1–11
  • Results: In a test set of 1473 real-world CT studies (669 malignant, 804 control) from institutions throughout Taiwan, the DL tool distinguished between CT malignant and control studies with 89.7% (600 of 669; 95% CI: 87.1, 91.9) sensitivity and 92.8% specificity (746 of 804; 95% CI: 90.8, 94.5) (AUC, 0.95; 95% CI: 0.94, 0.96), with 74.7% (68 of 91; 95% CI: 64.5, 83.3) sensitivity for malignancies smaller than 2 cm.”
    Pancreatic Cancer Detection on CT Scans with Deep Learning: A Nationwide Population-based Study
    Po-Ting Chen et al.
    Radiology 2022; 000:1–11
  • “An automatic end-to-end deep learning–based detection tool could detect pancreatic cancer on CT scans in a nationwide real-world test data set with 91% accuracy, without requiring manual image labeling or preprocessing.”  
    Pancreatic Cancer Detection on CT Scans with Deep Learning: A Nationwide Population-based Study
    Po-Ting Chen et al.
    Radiology 2022; 000:1–11
  • Purpose
    A wide array of benign and malignant lesions of the pancreas can be cystic and these cystic lesions can have overlapping imaging appearances. The purpose of this study is to compare the diagnostic accuracy of a radiomics-based pancreatic cyst classifier to an experienced academic radiologist.
    Classification of pancreatic cystic neoplasms using radiomic feature analysis is equivalent to an experienced academic radiologist: a step toward computer‑augmented diagnostics for radiologists
    Linda C. Chu et al.
    Abdom Radiol (NY). 2022 Sep 13. doi: 10.1007/s00261-022-03663-6. Online ahead of print.
  • Results
    214 patients were included (64 intraductal papillary mucinous neoplasms, 33 mucinous cystic neoplasms, 60 serous cystadenomas, 24 solid pseudopapillary neoplasms, and 33 cystic neuroendocrine tumors). The radiomics-based machine learning approach showed AUC of 0.940 in pancreatic cyst classification, compared with AUC of 0.895 for the radiologist.  
    Conclusion
    Radiomics-based machine learning achieved equivalent performance as an experienced academic radiologist in the classification of pancreatic cysts. The high diagnostic accuracy can potentially maximize the efficiency of healthcare utilization by maximizing detection of high-risk lesions.  
    Classification of pancreatic cystic neoplasms using radiomic feature analysis is equivalent to an experienced academic radiologist: a step toward computer‑augmented diagnostics for radiologists
    Linda C. Chu et al.
    Abdom Radiol (NY). 2022 Sep 13. doi: 10.1007/s00261-022-03663-6. Online ahead of print.
  • “A total of 488 radiomics features from the segmented volume were extracted to define cystic lesion and pancreas phenotypes based on venous phase images. Radiomics features used in this study included 14 first-order statistics of the volumetric CT intensities, 8 shape features of the target structure, 33 texture features from a gray-level co-occurrence matrix and a gray-level run-length matrix, 376 texture features from the 8 filtered volumes by wavelets, and an additional 47 texture features form the filtered volume by Laplacian of Gaussian (LoG). Ten image features were extracted from the whole pancreatic region. Table 2 represents the whole feature set used for cyst classification in this study. Two demographic features, age and gender, were also incorporated into the final model.”
    Classification of pancreatic cystic neoplasms using radiomic feature analysis is equivalent to an experienced academic radiologist: a step toward computer‑augmented diagnostics for radiologists
    Linda C. Chu et al.
    Abdom Radiol (NY). 2022 Sep 13. doi: 10.1007/s00261-022-03663-6. Online ahead of print.
  • “This study showed that a radiomics-based model can achieve equivalent performance as an experienced academic radiologist in the classification of a wide array of pancreatic cysts with variable malignant potential. This model has the potential to refine pancreatic cyst management by improving diagnostic accuracy of cystic lesions, which can minimize healthcare utilization while maximizing detection of malignant lesions. This study confirms the ability of a radiomic based model to accurately classify pancreatic cystic neoplasms. Further validation and clinical integration of this model could help optimize management of pancreatic cysts by maximizing the rate of detection of malignant lesions while reducing healthcare utilization.”
    Classification of pancreatic cystic neoplasms using radiomic feature analysis is equivalent to an experienced academic radiologist: a step toward computer‑augmented diagnostics for radiologists
    Linda C. Chu et al.
    Abdom Radiol (NY). 2022 Sep 13. doi: 10.1007/s00261-022-03663-6. Online ahead of print.
  • “Among the whole 490 features (488 radiomics features plus age and gender), thirty features were found to reduce redundancy by the minimum-redundancy maximum-relevancy feature selection based on mutual information, which showed the best classification performance, with AUC of 0.940. Age and gender were included in the model due to the known gender and gender associations for pancreatic cysts. These demographic features would be available to the radiologist at the time of exam, and this would simulate the real-world application. Age, median and mean intensities of the original images and wavelets, and fractal dimension were highly ranked for the classifications. Gender was ranked as 29th feature for the classification."
    Classification of pancreatic cystic neoplasms using radiomic feature analysis is equivalent to an experienced academic radiologist: a step toward computer‑augmented diagnostics for radiologists
    Linda C. Chu et al.
    Abdom Radiol (NY). 2022 Sep 13. doi: 10.1007/s00261-022-03663-6. Online ahead of print.
  • “In this study, the performance of the radiomics featurebased classification achieved AUC of 0.940 in distinguishing among five types of pancreatic cystic neoplasms. The performance was similar to previous studies with multi-class pancreatic cyst classifications that included three or four cyst types, with accuracy of 79.6–83.6%. Previous studies on radiomics-based pancreatic cyst classification did not include a direct comparison with a radiologist, therefore, it was difficult to assess if the radiomics-based classification reported provided any added value relative to the standard of care. The current study showed that the radiomics- based pancreatic cyst classification achieved equivalent performance as an academic radiologist with more than 25 years of experience.”
    Classification of pancreatic cystic neoplasms using radiomic feature analysis is equivalent to an experienced academic radiologist: a step toward computer‑augmented diagnostics for radiologists
    Linda C. Chu et al.
    Abdom Radiol (NY). 2022 Sep 13. doi: 10.1007/s00261-022-03663-6. Online ahead of print.
  • "Secondly, the performance of the radiomics-based model was compared to the performance of a single-academic radiologist. The experienced academic radiologist in this study may be more accurate at pancreatic cyst classification than an average radiologist in the community, which may underestimate the incremental value of the radiomics-based model. Future reader studies should also recruit multiple readers with a wide range of experience to measure the real-world impact of these radiomics tools. Thirdly, the current radiomics model only used CT-based features plus patient age and demographics. Other important clinical features such as symptoms, family history, laboratory values, and cyst fluid molecular markers  were not included in the current model, which should be incorporated into future models. Our prior experience has demonstrated that the predictive power offered by multiple features is often additive.”
    Classification of pancreatic cystic neoplasms using radiomic feature analysis is equivalent to an experienced academic radiologist: a step toward computer‑augmented diagnostics for radiologists
    Linda C. Chu et al.
    Abdom Radiol (NY). 2022 Sep 13. doi: 10.1007/s00261-022-03663-6. Online ahead of print.
  • Research Agenda for Clinical AI in PDAC Imaging
    - To acquire more, good quality data coming from large, well-curated, multi-institutional private and public PDAC datasets
    - To switch focus towards state-of-the-art, entirely data-driven deep learning models
    - To use better quality ground truths that represent actual clinical endpoints such as overall survival and disease-free survival as the gold standard for model development
    - To investigate the use of multimodal AI, combining information from imaging, histopathology, genetics and clinical records
  • “Pancreatic ductal adenocarcinoma (PDAC) is one of the deadliest cancers worldwide, associated with a 98% loss of life expectancy and a 30% increase in disability-adjusted life years. Image-based artificial intelligence (AI) can help improve outcomes for PDAC given that current clinical guidelines are non-uniform and lack evidence-based consensus. However, research on image based AI for PDAC is too scattered and lacking in sufficient quality to be incorporated into clinical workflows. In this review, an international, multi-disciplinary team of the world’s leading experts in pancreatic cancer breaks down the patient pathway and pinpoints the current clinical touchpoints in each stage. The available PDAC imaging AI literature addressing each pathway stage is then rigorously analyzed, and current performance and pitfalls are identified in a comprehensive overview. Finally, the future research agenda for clinically relevant, image-driven AI in PDAC is proposed.”
    Setting the Research Agenda for Clinical Artificial Intelligence in Pancreatic Adenocarcinoma Imaging.
    Schuurmans, M et al.
    Cancers 2022, 14, 3498. https://doi.org/10.3390/cancers14143498
  • “Early detection, arguably the most pressing issue in PDAC management, is closely linked to identifying small lesions and secondary anatomical signs. However, our results show this is still not considered in AI-based detection research, as there are no studies on pre-diagnostic detection of secondary signs, and most studies do not disaggregate performance based on tumour size/stage. Additionally, there is a lack of research on lesion localization and a general absence of well-curated datasets, with positive and negative cases being retrieved from completely different populations, which does not reflect the clinical landscape and can introduce bias. For AI to improve PDAC detection, it is crucial to acquire and make publicly available well-curated, multimodal datasets that contain a significant proportion of small (<2 cm or even <1 cm) tumours, which should be treated as a subgroup of interest when reporting model performance.”
    Setting the Research Agenda for Clinical Artificial Intelligence in Pancreatic Adenocarcinoma Imaging.
    Schuurmans, M et al.
    Cancers 2022, 14, 3498. https://doi.org/10.3390/cancers14143498
  • “Current research separates detection, which is defined as distinction between PDAC patients and healthy controls, from differential diagnosis, defined as distinction between PDAC and other types of pancreatic lesions. Only one study developed AI for simultaneous detection and characterisation of pancreatic lesions on CECT. The remaining publications focused on binary distinction between PDAC and one other malignancy, limiting the proposed models’ clinical use. Furthermore, it is important to consider that PDAC diagnosis currently relies on high-quality, adequate imaging with multi-phasic scanning protocols, which may not be widely available due to resource limitations. In the future, research should strive towards a single-use case for radiology-based AI in PDAC diagnosis that includes both the detection of a lesion and its correct classification among a variety of pancreatic diseases in accessible, standard-of-care imaging. The current priority is the curation of large datasets with representative percentages of each lesion type and the integration of different imaging modalities that offer complementary information regarding lesion characterisation.”  
    Setting the Research Agenda for Clinical Artificial Intelligence in Pancreatic Adenocarcinoma Imaging.
    Schuurmans, M et al.
    Cancers 2022, 14, 3498. https://doi.org/10.3390/cancers14143498
  • Objective: To develop and validate an effective model for identifying patients with postoperative local disease recurrence of pancreatic ductal adenocarcinoma (PDAC).
    Methods: A total of 153 patients who had undergone surgical resection of PDAC with regular postoperative follow-up were consecutively enrolled and randomly divided into training (n = 108) and validation (n = 45) cohorts. The postoperative soft-tissue biopsy results or clinical follow-up results served as the reference diagnostic criteria. Radiomics analysis of the postoperative soft-tissue was performed on a commercially available prototype software using portal vein phase image. Three models were built to characterize postoperative soft tissue: computed tomography (CT)-based radiomics, clinicoradiological, and their combination. The area under the receiver operating characteristic curves (AUC) was used to evaluate the differential diagnostic performance. A nomogram was used to select the final model with best performance. One radiologist’s diagnostic choices that were made with and without the nomogram’s assistance were evaluated.
    Computed Tomography-based Radiomics Evaluation of Postoperative Local Recurrence of Pancreatic Ductal Adenocarcinoma
    Ming He et al.
    Acad Radiol 2022;&:1–9
  • Results: A seven-feature combined radiomics signature was constructed as a predictor of postoperative local recurrence. The nomogram model combining the radiomics signature with postoperative CA 19-9 elevation showed the best performance (training cohort, AUC = 0.791 [95%CI: 0.707, 0.876]; validation cohort, AUC = 0.742 [95%CI: 0.590, 0.894]). In the validation cohort, the AUC for differential diagnosis was significantly improved for the combined model relative to that for postoperative CA 19-9 elevation (AUC = 0.742 vs. 0.533, p < 0.001). The calibration curve and decision curve analysis demonstrated the clinical usefulness of the proposed nomogram. The diagnostic performance of the radiologist was not significantly improve by using the proposed nomogram (AUC = 0.742 vs. 0.670, p = 0.17).
    Conclusion: The combined model using CT radiomic features and CA 19-9 elevation effectively characterized postoperative soft tissue and potentially may improve treatment strategies and facilitate personalized treatment for PDAC after surgical resection.
    Computed Tomography-based Radiomics Evaluation of Postoperative Local Recurrence of Pancreatic Ductal Adenocarcinoma
    Ming He et al.
    Acad Radiol 2022;&:1–9
  • “In the present study, we obtained encouraging data when using radiomics to analyze enhanced CT scan images recorded 3 months after surgery. The resulting nomogram, which combines the radiomics signatures and postoperative elevation of CA 19-9, is expected to serve as a reference indicator for clinicians planning postoperative follow-up strategies. Patients for whom the nomogram shows a high probability of postoperative local recurrence may be better candidates for regular follow-ups, facilitating earlier confirmation of recurrence and prompt treatment. In patients for whom the nomogram indicates a relatively low probability of recurrence, a symptom-driven follow-up strategy can be used to alleviate the patients’ financial and psychological burdens.”
    Computed Tomography-based Radiomics Evaluation of Postoperative Local Recurrence of Pancreatic Ductal Adenocarcinoma
    Ming He et al.
    Acad Radiol 2022;&:1–9
  • “In the present study, the sensitivity and specificity of radiomics analysis for characterizing postoperative soft tissue were 70.8% and 63.3%, respectively, in the validation cohort; both of these values were significantly higher than those of the postoperative CA 19-9 (54.2% and 52.4%), respectively, (p < 0.05, both). Furthermore, the combination of radiomics signature and clinicoradiological features further improved the sensitivity and specificity to 76.3% and 66.7%, respectively, in the validation cohort. The combined model (postoperative elevation of CA 19-9 combined with the radiomics signatures) performed well both in the primary and validation cohort, showing its robustness and reliability for early diagnosis of postoperative local recurrence.”
    Computed Tomography-based Radiomics Evaluation of Postoperative Local Recurrence of Pancreatic Ductal Adenocarcinoma
    Ming He et al.
    Acad Radiol 2022;&:1–9
  • “Due to the growth pattern of pancreatic cancer, the tumor may not be always visible as a hypodense lesion, therefore experts refer to the visibility of secondary external features that may indicate the presence of the tumor. We propose a method based on a U-Net-like Deep CNN that exploits the following external secondary features: the pancreatic duct, common bile duct and the pancreas, along with a processed CT scan. Using these features, the model segments the pancreatic tumor if it is present. This segmentation for classification and localization approach achieves a performance of 99% sensitivity (one case missed) and 99% specificity, which realizes a 5% increase in sensitivity over the previous state-of-the-art method. The model additionally provides location information with reasonable accuracy and a shorter inference time compared to previous PDAC detection methods. These results offer a significant performance improvement and highlight the importance of incorporating the knowledge of the clinical expert when developing novel CAD methods.”
    Improved Pancreatic Tumor Detection by Utilizing Clinically-Relevant Secondary Features
    Christiaan G.A. Viviers et al.
    arXiv:2208.03581v1 [cs.CV] 6 Aug 2022
  • “In this research, we propose a PDAC segmentation model that utilizes the same visual cues in the surrounding anatomy that experts use when looking for the presence of PDAC. This focus and way of working is to maximally lever- age easily accessible external information and fully exploit clinical expertise, to ultimately optimize classification and localization performance. Since we start from the radiologists' reasoning, our method becomes clinically meaningful. For instance, a clinician pays close attention to pancreatic ductal size as a large (potentially dilated) duct could be indicative of tumor. Compared to normal pancreatic tissue in a CT scan, pancreatic cancer appears less visible as an ill-defined mass. It enhances poorly and is hypodense between 75% and 90% of arterial phase CT cases. For this reason, experts utilize secondary features which may be predictive of pancreatic cancer. These include, but are not limited to: ductal dilatation, hypo-attenuation, ductal interruption, distal pancreatic atro- phy, pancreatic contour anomalies and common bile duct dilation.”
    Improved Pancreatic Tumor Detection by Utilizing Clinically-Relevant Secondary Features
    Christiaan G.A. Viviers et al.
    arXiv:2208.03581v1 [cs.CV] 6 Aug 2022
  • “Despite the eminent success of deep learning networks, even for detection of PDAC, the method presented in this work demonstrates that external tumor- indicative features can significantly boost CAD performance. We optimize a segmentation for classification and localization approach, by adding the easily obtainable and clinically valuable external secondary features used by the radiologist, to considerably improve segmentation performance. The proposed approach consists of a 3D U-Net that takes the CT scan, along with a segmentation map of the pancreas, pancreatic duct and common bile duct as input, in order to finally segment the pancreatic tumor. By integrating these indicative secondary features into the detection process, the proposed method achieves a sensitivity of 99 2% (one cased missed), yielding 5% gain over the previous state-of-the-art method. The proposed method also achieves a specificity of 99% and ultimately requires no sacrifice of specificity in favor of sensitivity.”
    Improved Pancreatic Tumor Detection by Utilizing Clinically-Relevant Secondary Features
    Christiaan G.A. Viviers et al.
    arXiv:2208.03581v1 [cs.CV] 6 Aug 2022
  • “Generally, this research reveals the important value of explicitly including clinical knowledge into the detection model. We suggest that future CAD methods integrate higher orders of feature information, particularly valuable clinical features, into their domain-specific problem to improve performance when such information can be identified. This method paves the way for equipping clinicians with the necessary tools to enable early PDAC detection, with the aim to ultimately improve patient care.”
    Improved Pancreatic Tumor Detection by Utilizing Clinically-Relevant Secondary Features
    Christiaan G.A. Viviers et al.
    arXiv:2208.03581v1 [cs.CV] 6 Aug 2022
  • BACKGROUND & AIMS: Our purpose was to detect pancreatic ductal adenocarcinoma(PDAC) at the prediagnostic stage (3-36 months prior to clinical diagnosis) using radiomics based machine learning (ML) models, and to compare performance against radiologists in a case control study.
    METHODS: Volumetric pancreas segmentation was performed on prediagnostic CTs (median interval between CT and PDAC diagnosis: 398 days) of 155 patients and an age-matched cohort of 265 subjects with normal pancreas. Total 88 first order and gray level radiomic features were extracted and 34 features were selected through LASSO-based feature selection method. Dataset was randomly divided into training (292 CTs: 110 prediagnostic and 182 controls) and test subsets (128 CTs: 45 prediagnostic and 83 controls). Four ML classifiers - K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Random Forest (RF) and XGBoost (XGB) - were evaluated. Specificity of model with highest accuracy was further validated on an independent internal dataset (n=176) and the public NIH dataset (n=80). Two radiologists (R4 and R5) independently evaluated the pancreas on a five-point diagnostic scale.
    Radiomics-Based Machine Learning Models Can Detect Pancreatic Cancer on Prediagnostic CTs at a Substantial Lead Time Prior to Clinical Diagnosis
    Sovanlal Mukherjee,et al.
    Gastroenterology (2022),doi:https://doi.org/10.1053/j.gastro.2022.06.066.
  • “Our study has limitations. The retrospective nature of the study is generally prone to selection bias. As with other radiomics studies, the precise pathologic correlates of the radiomic features that constitute the ML classifiers are not entirely known. We did not investigate the impact of differences in all the acquisition or post-processing parameters (e.g., voxel width, bin width, etc.) on the classifiers, which will be subject of the next phase of our ongoing investigation. Although we validated the high specificity of the SVM classifier on an independent internal cohort of control CTs as well as on the public NIH-PCT dataset, the sample size of these cohorts was small and the subjects in these cohorts were relatively younger. Thus, prospective larger cohorts with both cases and controls are warranted for further validation. Such prospective studies would also help determine the optimal operating point for the models to avoid a high false positive rate in context of a screening paradigm.”  
    Radiomics-Based Machine Learning Models Can Detect Pancreatic Cancer on Prediagnostic CTs at a Substantial Lead Time Prior to Clinical Diagnosis
    Sovanlal Mukherjee,et al.
    Gastroenterology (2022),doi:https://doi.org/10.1053/j.gastro.2022.06.066.
  • “In conclusion, we detected and quantified the imaging signature of early pancreatic  carcinogenesis from volumetrically segmented normal pancreas on standard-of-care CTs. The radiomics-based ML classifiers had high discrimination accuracy for classification of pancreas into prediagnostic for PDAC versus normal. The high accuracy of the SVM model was validated on CTs from external institutions. Its high specificity was generalizable on an independent internal cohort and on an external public dataset. In contrast, radiologist readers had low interreader agreement, sensitivity, and discrimination accuracy, which shows that novel AI-based approaches can detect PDAC at a subclinical stage when it is beyond the scope of the human interrogation. Prospective validation of these ML models and their integration with complementary blood and other fluid-based biomarkers has the potential to further improve cancer prediction capabilities at the prediagnostic or symptom-free stage. Such models also have the potential to elucidate the longitudinal changes of carcinogenesis that precede the clinical diagnosis of PDAC. Finally, such models can be deployed to detect early cancer in ongoing clinical trials such as the Early Detection Initiative that seeks to evaluate outcomes of a screening strategy utilizing clinical risk-prediction models and CT in cohorts at high-risk for PDAC.”
    Radiomics-Based Machine Learning Models Can Detect Pancreatic Cancer on Prediagnostic CTs at a Substantial Lead Time Prior to Clinical Diagnosis
    Sovanlal Mukherjee,et al.
    Gastroenterology (2022),doi:https://doi.org/10.1053/j.gastro.2022.06.066.
  • Objective: Quality gaps in medical imaging datasets lead to profound errors in experiments. Our objective was to characterize such quality gaps in public pancreas imaging datasets (PPIDs), to evaluate their impact on previously published studies, and to provide post-hoc labels and segmentations as a value-add for these PPIDs.
    Conclusion: Substantial quality gaps, sources of bias, and high proportion of CTs unsuitable for AI characterize the available limited PPIDs. Published studies on these PPIDs do not account for these quality gaps. We complement these PPIDs through post-hoc labels and segmentations for public release on the TCIA portal. Collaborative efforts leading to large, well-curated PPIDs supported by adequate documentation are critically needed to translate the promise of AI to clinical practice.
    Quality gaps in public pancreas imaging datasets: Implications & challenges for AI applications
    Garima Suman et al.
    Pancreatology 21 (2021) 1001-1008
  • "Public medical imaging datasets have stimulated widespread interest to explore AI to address unmet healthcare needs. In order to fully leverage these public datasets, there is a critical need to understand their strengths and limitations. Our study of public datasets in the pancreas imaging domain identified only three public datasets. The MSD dataset is the largest one with 420 CTs. Both the NIH-PCT and the TCIA PDA datasets have less than 100 CTs each. These datasets are insufficient for deep learning applications, which require very large volumes of data. There is a general hesitation to share digital assets due to concerns related to data ownership and patient privacy. Ongoing developments in federated learning architecture and privacy-preserving AI could promote wider sharing of such datasets.”
    Quality gaps in public pancreas imaging datasets: Implications & challenges for AI applications
    Garima Suman et al.
    Pancreatology 21 (2021) 1001-1008
  • “Finally, presence of medical devices such as stents is another critical confounding factor. In the context of PDA, a tumor classification, or detection model can learn to associate the presence of a biliary stent with the diagnosis of PDA, which can lead to inadvertent overestimation of the model’s performance. Secondly, the course of such stents through the pancreatic head results in streak, artifacts and can obscure delineation of tumors in the pancreatic head. These challenges can increase the variability in tumor segmentation or result in the stent being included in segmentation mask with consequent errors in AI models. Therefore, if CTs with stents form a part of PPIDs, these should be explicitly specified in the metadata to ensure that users can make an Informed decision regarding their potential use for AI experiments.”
    Quality gaps in public pancreas imaging datasets: Implications & challenges for AI applications
    Garima Suman et al.
    Pancreatology 21 (2021) 1001-1008
  • "In  summary, there is a need for carefully curated public imaging datasets supported by adequate documentation in the pancreas imaging domain. The available datasets for pancreatic pathologies have substantial quality gaps, sources of bias, and high proportion of CTs unsuitable for AI experiments. In our assessment, the factors  responsible for such quality gaps include general hesitation to share highly curated digital assets due to concerns related to data ownership and patient privacy, absence of tangible incentives fordata sharing, limited guidance on the dataset preparation process, inadequate involvement of domain experts in dataset curation process, and lack of awareness of the impact of insufficient documentation on the AI development pipeline.”
    Quality gaps in public pancreas imaging datasets: Implications & challenges for AI applications
    Garima Suman et al.
    Pancreatology 21 (2021) 1001-1008
  • BACKGROUND & AIMS: Our purpose was to detect pancreatic ductal adenocarcinoma (PDAC) at the prediagnostic stage (3-36 months prior to clinical diagnosis) using radiomics based machine learning (ML) models, and to compare performance against radiologists in a case control study.  
    CONCLUSIONS: Radiomics-based ML models can detect PDAC from normal pancreas when it is beyond human interrogation capability at a substantial lead time prior to clinical diagnosis. Journal Pre-proof 6 Prospective validation and integration of such models with complementary fluid-based biomarkers has the potential for PDAC detection at a stage when surgical cure is a possibility
    Radiomics-Based Machine Learning Models Can Detect Pancreatic Cancer on Prediagnostic CTs at a Substantial Lead Time Prior to Clinical Diagnosis,
    Sovanlal Mukherjee et al.
    Gastroenterology 2022 (in press)
  • METHODS
    Volumetric pancreas segmentation was performed on prediagnostic CTs (median interval between CT and PDAC diagnosis: 398 days) of 155 patients and an age-matched cohort of 265 subjects with normal pancreas. Total 88 first order and gray level radiomic features were extracted and 34 features were selected through LASSO-based feature selection method. Dataset was randomly divided into training (292 CTs: 110 prediagnostic and 182 controls) and test subsets (128 CTs: 45 prediagnostic and 83 controls). Four ML classifiers - K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Random Forest (RF) and XGBoost (XGB) - were evaluated. Specificity of model with highest accuracy was further validated on an independent internal dataset (n=176) and the public NIH dataset (n=80). Two radiologists (R4 and R5) independently evaluated the pancreas on a five-point diagnostic scale.
  •  RESULTS
    Median (range) time between prediagnostic CTs of the test subset and PDAC diagnosis was 386 (97-1092) days. SVM had the highest sensitivity (mean; 95% CI) (95.5; 85.5-100.0), specificity (90.3; 84.3-91.5), F1-score (89.5; 82.3-91.7), AUC (0.98; 0.94-0.98) and accuracy (92.2%; 86.7-93.7) for classification of CTs into prediagnostic versus normal. All three other ML models KNN, RF, and XGB had comparable AUCs (0.95, 0.95, and 0.96, respectively). The high specificity of SVM was generalizable to both the independent internal (92.6%) and the NIH dataset (96.2%). In contrast, inter-reader radiologist agreement was only fair (Cohen’s kappa 0.3) and their mean AUC (0.66; 0.46-0.86) was lower than each of the four ML models (AUCs: 0.95-0.98) (p < 0.001). Radiologists also recorded false positive indirect findings of PDAC in control subjects (n=83) (7% R4, 18% R5). 
  • CONCLUSIONS
    Radiomics-based ML models can detect PDAC from normal pancreas when it is beyond human interrogation capability at a substantial lead time prior to clinical diagnosis. Prospective validation and integration of such models with complementary fluid-based biomarkers has the potential for PDAC detection at a stage when surgical cure is a possibility. 
  • “These observations support the biologic insights from prior studies that the prediagnostic stage of PDAC is marked by substantial cellular activity and infiltration, which results in marked tissue heterogeneity . Our study suggests that this tissue heterogeneity is beyond the human perceptive ability but can be captured and leveraged for actionable insights through computational postprocessing techniques such as radiomics.”  
    Radiomics-Based Machine Learning Models Can Detect Pancreatic Cancer on Prediagnostic CTs at a Substantial Lead Time Prior to Clinical Diagnosis,
    Sovanlal Mukherjee et al.
    Gastroenterology 2022 (in press)
  • “The radiomics-based ML classifiers had high discrimination accuracy for classification of pancreas into prediagnostic for PDAC versus normal. The high accuracy of the SVM model was validated on CTs from external institutions. Its high specificity was generalizable on an independent internal cohort and on an external public dataset. In contrast, radiologist readers had low interreader agreement, sensitivity, and discrimination accuracy, which shows that novel AI-based approaches can detect PDAC at a subclinical stage when it is beyond the scope of the human interrogation. Prospective validation of these ML models and their integration with complementary blood and other fluid-based biomarkers has the potential to further improve cancer prediction capabilities at the prediagnostic or symptom-free stage. Such models also have the potential to elucidate the longitudinal changes of carcinogenesis that precede the clinical diagnosis of PDAC.”
    Radiomics-Based Machine Learning Models Can Detect Pancreatic Cancer on Prediagnostic CTs at a Substantial Lead Time Prior to Clinical Diagnosis,
    Sovanlal Mukherjee et al.
    Gastroenterology 2022 (in press)
  • Background The diagnostic performance of CT for pancreatic cancer is interpreter-dependent, and approximately 40% of tumours smaller than 2 cm evade detection. Convolutional neural networks (CNNs) have shown promise in image analysis, but the networks’ potential for pancreatic cancer detection and diagnosis is unclear. We aimed to investigate whether CNN could distinguish individuals with and without pancreatic cancer on CT, compared with radiologist interpretation.
    Interpretation CNN could accurately distinguish pancreatic cancer on CT, with acceptable generalisability to images of patients from various races and ethnicities. CNN could supplement radiologist interpretation.
    Deep learning to distinguish pancreatic cancer tissue from non-cancerous pancreatic tissue: a retrospective study with cross-racial external validation
    Kao-Lang Liu et al.
    Lancet Digital Health 2020; 2: e303–13
  • “The promise of artificial intelligence (AI) to improve and reduce inequities in access, quality, and appropriateness of high-quality diagnosis remains largely unfulfilled. Vast clinical data sets, extensive computational capacity, and highly developed and accessible machine learning tools have resulted in numerous publications that describe high-performing algorithmic approachesfor a variety of diagnostic tasks. However, such approaches remain largely unadopted in clinical practice.”
    Rethinking Algorithm Performance Metrics for Artificial Intelligence in Diagnostic Medicine
    Reyna MA et al.
    JAMA Published online July 8, 2022 
  • Methods In this retrospective, diagnostic study, contrast-enhanced CT images of 370 patients with pancreatic cancer and 320 controls from a Taiwanese centre were manually labelled and randomly divided for training and validation (295 patients with pancreatic cancer and 256 controls) and testing (75 patients with pancreatic cancer and 64 controls; local test set 1). Images were preprocessed into patches, and a CNN was trained to classify patches as cancerous or non-cancerous. Individuals were classified as with or without pancreatic cancer on the basis of the proportion of patches diagnosed as cancerous by the CNN, using a cutoff determined using the training and validation set. The CNN was further tested with another local test set (101 patients with pancreatic cancers and 88 controls; local test set 2) and a US dataset (281 pancreatic cancers and 82 controls). Radiologist reports of pancreatic cancer images in the local test sets were retrieved for comparison.
    Deep learning to distinguish pancreatic cancer tissue from non-cancerous pancreatic tissue: a retrospective study with cross-racial external validation
    Kao-Lang Liu et al.
    Lancet Digital Health 2020; 2: e303–13
  • Findings Between Jan 1, 2006, and Dec 31, 2018, we obtained CT images. In local test set 1, CNN-based analysis hada sensitivity of 0·973, specificity of 1·000, and accuracy of 0·986 (area under the curve [AUC] 0·997 (95% CI 0·992–1·000). In local test set 2, CNN-based analysis had a sensitivity of 0·990, specificity of 0·989, and accuracy of 0·989 (AUC 0·999 [0·998–1·000]). In the US test set, CNN-based analysis had a sensitivity of 0·790, specificity of 0·976, and accuracy of 0·832 (AUC 0·920 [0·891–0·948)]. CNN-based analysis achieved higher sensitivity than radiologists did (0·983 vs 0·929, difference 0·054 [95% CI 0·011–0·098]; p=0·014) in the two local test sets combined. CNN missed three (1·7%) of 176 pancreatic cancers (1·1–1·2 cm). Radiologists missed 12 (7%) of 168 pancreatic cancers (1·0–3·3 cm), of which 11 (92%) were correctly classified using CNN. The sensitivity of CNN for tumours smaller than 2 cm was 92·1% in the local test sets and 63·1% in the US test set.
    Deep learning to distinguish pancreatic cancer tissue from non-cancerous pancreatic tissue: a retrospective study with cross-racial external validation
    Kao-Lang Liu et al.
    Lancet Digital Health 2020; 2: e303–13
  • Added value of this study We trained a CNN using contrast enhanced-CT images of Asian patients to distinguish pancreatic cancer from healthy pancreases. CNN achieved excellent accuracy and improved sensitivity compared with radiologist interpretation in independent Asian test sets, with acceptable performance in a North American test set obtained from patients of various races and ethnicities using diverse scanners and settings. These results provide the first solid proof of concept that CNN can capture the elusive CT features of pancreatic cancer to assist and supplement radiologists in the detection and diagnosis of pancreatic cancer.
    Deep learning to distinguish pancreatic cancer tissue from non-cancerous pancreatic tissue: a retrospective study with cross-racial external validation
    Kao-Lang Liu et al.
    Lancet Digital Health 2020; 2: e303–13
  • “Implications of all the available evidence CNN can accurately differentiate pancreatic cancer from non-cancerous pancreas, and with improvements mightaccommodate variations in patient race and ethnicity and imaging parameters that are inevitable in real-world clinical practice. CNN holds promise for developing computer-aided detection and diagnosis tools for pancreatic cancer to supplement radiologist interpretation.”
    Deep learning to distinguish pancreatic cancer tissue from non-cancerous pancreatic tissue: a retrospective study with cross-racial external validation
    Kao-Lang Liu et al.
    Lancet Digital Health 2020; 2: e303–13
  • "Artificial intelligence (AI) can speed up pancreatic cancer identification, boost tumor clearance, and detect recurrent tumors during postoperative surveillance as a feasible treatment. The capabilities of AI in identifying tumor resectability, differentiating between borderline and locally progressed pancreatic ductal adenocarcinoma (PDAC), and calculating pancreatic fatty infiltration should be further investigated and developed in the future study.”
    Pancreatic Cancer Detection using Machine and Deep Learning Techniques  
    Gupta A et al.
    2022 2nd International Conference on Innovative Practices in Technology and Management (ICIPTM)
  • "According to the findings of this study, there is a lot of interest in using machine and deep learning algorithms to predict pancreatic cancer progression. When compared to other techniques, machine learning outperformed well for various datasets. As demonstrated in figure 3, The Bayesian model produced the most significant auc of 0.94, the genetic algorithm had the best sensitivity and specificity for detecting the pancreatic tumor, with 96.7% and 82.5%, respectively.”
    Pancreatic Cancer Detection using Machine and Deep Learning Techniques  
    Gupta A et al.
    2022 2nd International Conference on Innovative Practices in Technology and Management (ICIPTM)
  • “There’s been a lot of recent AI work involving dermatology and using it for melanoma screening. Will primary care physicians augmented with AI reach a point where patients don’t need to be referred to a dermatologist? Or will dermatologists be the ones using augmented AI models to help them identify which moles need a biopsy? This survey data, which indicates that few dermatologists are using AI compared to more widespread use in primary care, suggests that, at least in some fields, early AI use cases are being used in primary care settings and that there may be more value here.”  
    Growing Use and Confidence in Artificial Intelligence for Care Delivery  
    Gordon W
    NEJM Catalyst Innovations in Care Delivery 2022; 04  10.1056/CAT.22.0095  Vol. 3 No. 4 | April 2022
  • IPMN and Cystic Pancreatic Lesions: Guidelines
    - Do people actually follow the guidelines?
    - Are they numerous interpretations of the guidelines?
    - Do the guidelines actually work and whats its success?
    - Is there a better way than current practice?
  • AI and Pancreatic Cystic Lesions
    - Radiomics
    - Deep Learning algorithmns
    - Combine Radiomics and Deep Learning algorithmns
  • Background: Society consensus guidelines are commonly used to guide management of pancreatic cystic neoplasms( PCNs). However, downsides of these guidelines include unnecessary surgery and missed malignancy. The aim of this study was to use computed tomography (CT)-guided deep learning techniques to predict malignancy of PCNs.
    Materials and Methods: Patients with PCNs who underwent resection were retrospectively reviewed. Axial images of the mucinous cystic neoplasms were collected and based on final pathology were assigned a binary outcome of advanced neoplasia or benign. Advanced neoplasia was defined as adenocarcinoma or intraductal papillary mucinous neoplasm with high-grade dysplasia. A convolutional neural network (CNN) deep learning model was trained on 66% of images, and this trained model was used to test 33% of images. Predictions from the deep learning model were compared to Fukuoka guidelines.
    Results: Twenty-seven patients met the inclusion criteria, with 18 used for training and 9 for model testing. The trained deep learning model correctly predicted 3 of 3 malignant lesions and 5 of 6 benign lesions. Fukuoka guidelines correctly classified 2 of 3 malignant lesions as high risk and 4 of 6 benign lesions as worrisome. Following deep learning model predictions would have avoided 1 missed malignancy and 1 unnecessary operation.
    Discussion: In this pilot study, a deep learning model correctly classified 8 of 9 PCNs and performed better than consensus guidelines. Deep learning can be used to predict malignancy of PCNs; however, further model improvements are necessary before clinical use.
    Use of Artificial Intelligence Deep Learning to Determine the Malignant Potential of Pancreatic Cystic Neoplasms With Preoperative Computed Tomography Imaging
    Michael D. Watson et al.
    The American Surgeon 2021, Vol. 87(4) 602–607
  • “The guidelines describe high-risk and worrisome criteria of PCNs based on preoperative imaging and clinical symptoms. Retrospective studies have demonstrate high specificity; however, these guidelines havepoor sensitivity, and using guidelines alone would haveled to missing approximately 50% of advanced neoplasia in 1 series. This results in nearly 20% of patients with a benign lesion undergoing operations with high morbidity. Given that existing guidelines are insufficient for identification of high-risk features of PCNs, an opportunity exists to leverage innovative new technologies toaid in diagnosis of potentially malignant lesions.”
    Use of Artificial Intelligence Deep Learning to Determine the Malignant Potential of Pancreatic Cystic Neoplasms With Preoperative Computed Tomography Imaging
    Michael D. Watson et al.
    The American Surgeon 2021, Vol. 87(4) 602–607
  • “In conclusion, this pilot study with a small group ofpatients (n = 27) demonstrated that a deep learning model based only on preoperative CT imaging was better able to predict advanced neoplasia than generally accepted  consensus guidelines. Further study should be directed toward creation of a larger, more sophisticated model and ultimately prospective validation of a model for predictionof malignant behavior of PCNs.”
    Use of Artificial Intelligence Deep Learning to Determine the Malignant Potential of Pancreatic Cystic Neoplasms With Preoperative Computed Tomography Imaging
    Michael D. Watson et al.
    The American Surgeon 2021, Vol. 87(4) 602–607
  • “In this pilot study for prediction of advanced neoplasia from preoperative CT imaging, a deep learning model was superior to consensus guidelines. The deep learning model was able to correctly classify 8 of 9 high-risk PCNs,while consensus guidelines were correct 6 of 9 times. In terms of possible patient outcomes, following predictions from the deep learning model would have resulted in 1unnecessary operation, while following consensusguidelines would have resulted in 2 unnecessary operationsand 1 missed neoplasm.”
    Use of Artificial Intelligence Deep Learning to Determine the Malignant Potential of Pancreatic Cystic Neoplasms With Preoperative Computed Tomography Imaging
    Michael D. Watson et al.
    The American Surgeon 2021, Vol. 87(4) 602–607
  • OBJECTIVE: To stratify high risk individuals for PDAC by identifying predictive features in pre-diagnostic abdominal Computed Tomography (CT) scans.
    METHODS: A set of CT features, potentially predictive of PDAC, was identified in the analysis of 4000 raw radiomic parameters extracted from pancreases in pre-diagnostic scans. The naïve Bayes classifier was then developed for automatic classification of CT scans of the pancreas with high risk for PDAC. A set of 108 retrospective CT scans (36 scans from each healthy control, pre-diagnostic, and diagnostic group) from 72 subjects was used for the study. Model development was performed on 66 multiphase CT scans, whereas external validation was performed on 42 venous-phase CT scans.
    RESULTS: The system achieved an average classification accuracy of 86% on the external dataset.
    CONCLUSIONS: Radiomic analysis of abdominal CT scans can unveil, quantify, and interpret micro-level changes in the pre-diagnostic pancreas and can efficiently assist in the stratification of high risk individuals for PDAC.  
    Predicting pancreatic ductal adenocarcinoma using artificial intelligence analysis of pre-diagnostic computed tomography images  
    Qureshia TA et al.
    Cancer Biomarkers 33 (2022) 211–217 
  • OBJECTIVE: To stratify high risk individuals for PDAC by identifying predictive features in pre-diagnostic abdominal Computed Tomography (CT) scans.
    CONCLUSIONS: Radiomic analysis of abdominal CT scans can unveil, quantify, and interpret micro-level changes in the pre-diagnostic pancreas and can efficiently assist in the stratification of high risk individuals for PDAC.  
    Predicting pancreatic ductal adenocarcinoma using artificial intelligence analysis of pre-diagnostic computed tomography images  
    Qureshia TA et al.
    Cancer Biomarkers 33 (2022) 211–217 
  • “In this study, we identified unique features in pre- diagnostic CT scans that are not appreciated by human eyes but are potentially predictive of PDAC and developed a classifier that performed PDAC prediction by automatically identifying pre-diagnostic scans when mixed with healthy control scans. The proposed model is highly stable, and results are satisfactory, encoring researchers to replicate the model for further validation on large dataset.”
    Predicting pancreatic ductal adenocarcinoma using artificial intelligence analysis of pre-diagnostic computed tomography images  
    Qureshia TA et al.
    Cancer Biomarkers 33 (2022) 211–217 
  • – Diagnostic: A CT scan of a patient with histopatho- logically confirmed PDAC and visible tumor on a CT scan. Patients with any type of pancreatectomy were excluded from this group.  
    – Pre-diagnostic: A CT scan from the same patient (as in the Diagnostic group), acquired between 6 months to 3 years prior to PDAC diagnosis, when no sign of PDAC or tumor was present.  
    – Healthy control: A contrast-enhanced abdominal CT scan of a different subject whose pancreas was healthy. The age and gender of each subject in the healthy control group and the year of their scan were matched to those of exactly one unique pa- tient in the pre-diagnostic group to limit morpho- logical and instrumentation variabilities, respec- tively. 
  • “Although the data repositories of both CSMC and KPMC were explored exhaustively, the amount of eligible data found was low as the pre-diagnostic scans are rarely available. Analysis on a limited dataset might suffer an overfitting problem. However, the purpose of the current study was to have proof of the concept and to encourage researchers to establish a large dataset with a collaboration for extensive training and validation of the model. A large dataset will also allow performing a biological interpretation of predictors and forming their correlation with genetic heterogeneity. A rigorous model can be a supporting tool in prospective studies and will help to increase the rate of diagnosis at an early stage.”
    Predicting pancreatic ductal adenocarcinoma using artificial intelligence analysis of pre-diagnostic computed tomography images  
    Qureshia TA et al.
    Cancer Biomarkers 33 (2022) 211–217 
  • The latest advances in AI in gastroenterology and hepatology are promising for aspect many fields of clinical care, from detection of neoplastic lesions on endoscopic assessment and improving current survival models to predicting treatment response. The application of AI to large and complex datasets may assist in the identification of new associations between variables, potentially leading to changes in clinical practice. Furthermore, the use of AI-assisted technologies has the potential to dramatically improve the quality of care. Finally, the time for assisted precision medicine is at hand, with the AI being able to tailor a treatment regimen or potentially predict the response to treatment in a specific patient based on extensive amounts of clinical data from large patient datasets. It is important to realize that, while AI currently does not substitute human clinical reasoning, it has a bright future in the betterment of patient care.
    Artificial intelligence in gastroenterology: A state-of-the-art review  
    Kröner, Paul T et al.  
    World journal of gastroenterology vol. 27,40 (2021): 6794-6824
  • Purpose: Current diagnostic and treatment modalities for pancreatic cysts (PCs) are invasive and are associated with patient morbidity. The purpose of this study is to develop and evaluate machine learning algorithms to delineate mucinous from non-mucinous PCs using non-invasive CT-based radiomics.
    Methods: A retrospective, single-institution analysis of patients with non-pseudocystic PCs, contrast-enhanced computed tomography scans within 1 year of resection, and available surgical pathology were included. A quantitative imaging software platform was used to extract radiomics. An extreme gradient boosting (XGBoost) machine learning algorithm was used to create mucinous classifiers using texture features only, or radiomic/radiologic and clinical combined models. Classifiers were compared using performance scoring metrics. Shapely additive explanation (SHAP) analyses were conducted to identify variables most important in model construction.  
    Results: Overall, 99 patients and 103 PCs were included in the analyses. Eighty (78%) patients had mucinous PCs on surgical pathology. Using multiple fivefold cross validations, the texture features only and combined XGBoost mucinous classifiers demonstrated an area under the curve of 0.72 ± 0.14 and 0.73 ± 0.14, respectively. By SHAP analysis, root mean square, mean attenuation, and kurtosis were the most predictive features in the texture features only model. Root mean square, cyst location, and mean attenuation were the most predictive features in the combined model.  
    Conclusion: Machine learning principles can be applied to PC texture features to create a mucinous phenotype classifier. Model performance did not improve with the combined model. However, specific radiomic, radiologic, and clinical features most predictive in our models can be identified using SHAP analysis. 
  • Purpose: Current diagnostic and treatment modalities for pancreatic cysts (PCs) are invasive and are associated with patient morbidity. The purpose of this study is to develop and evaluate machine learning algorithms to delineate mucinous from non-mucinous PCs using non-invasive CT-based radiomics.
    Methods: A retrospective, single-institution analysis of patients with non-pseudocystic PCs, contrast-enhanced computed tomography scans within 1 year of resection, and available surgical pathology were included. A quantitative imaging software platform was used to extract radiomics. An extreme gradient boosting (XGBoost) machine learning algorithm was used to create mucinous classifiers using texture features only, or radiomic/radiologic and clinical combined models. Classifiers were compared using performance scoring metrics. Shapely additive explanation (SHAP) analyses were conducted to identify variables most important in model construction.  
    Machine learning principles applied to CT radiomics to predict mucinous pancreatic cysts  
    Adam M. Awe et al.
    Abdominal Radiology (2022) 47:221–231 
  • Results: Overall, 99 patients and 103 PCs were included in the analyses. Eighty (78%) patients had mucinous PCs on surgical pathology. Using multiple fivefold cross validations, the texture features only and combined XGBoost mucinous classifiers demonstrated an area under the curve of 0.72 ± 0.14 and 0.73 ± 0.14, respectively. By SHAP analysis, root mean square, mean attenuation, and kurtosis were the most predictive features in the texture features only model. Root mean square, cyst location, and mean attenuation were the most predictive features in the combined model.  
    Conclusion: Machine learning principles can be applied to PC texture features to create a mucinous phenotype classifier. Model performance did not improve with the combined model. However, specific radiomic, radiologic, and clinical features most predictive in our models can be identified using SHAP analysis.  
    Machine learning principles applied to CT radiomics to predict mucinous pancreatic cysts  
    Adam M. Awe et al.
    Abdominal Radiology (2022) 47:221–231
  • “Radiomics is the high throughput extraction of large sets of quantitative data from imaging studies that can be used to characterize healthy and pathological tissues to inform diagnosis and prognosis. Texture analysis, a subtype of radiomics, quantifies gray-level pixels and voxels in a frequency histogram and their spatial relationships to describe lesion heterogeneity within a 2-dimensional region of interest (ROI) or 3-dimensional volume of interest (VOI). Computed tomography (CT) texture analysis has demonstrated promise in diagnosing and risk-stratifying patients with PCs. Predictive ability of radiomics models can be enhanced by integrating clinical features in pancreas and non-pancreas tissues.”  
    Machine learning principles applied to CT radiomics to predict mucinous pancreatic cysts  
    Adam M. Awe et al.
    Abdominal Radiology (2022) 47:221–231
  • "Additional machine learning algorithms were applied to mucinous PCs to create a classifier that distinguishes cysts with HGD from cysts without HGD. Baseline models used for comparisons included minority, majority, random guesser, and stratified guesser models. XGBoost was also explored to evaluate their performance compared to baseline models. In developing the HGD classifier models, 5 and 9 weak learners were used in the decision trees for the texture features only and combined models, respectively. The XGBoost algorithms developed for the HGD classifier used a positive class weight scaling of 1.45 and 2.47, and maximum depth of 4 and 5 for the texture features only and combined models, respectively. The remainder of the decision tree parameters were left at their defaults. Accuracy, F1-score, and G-mean values were determined to compare performance of models.”
    Machine learning principles applied to CT radiomics to predict mucinous pancreatic cysts  
    Adam M. Awe et al.
    Abdominal Radiology (2022) 47:221–231
  • "In conclusion, our study demonstrates that machine learning principles can be applied to radiomics data of PCs to help detect mucinous phenotypes. While this information does not obviate the need for other diagnostic testing, it may help risk stratify patients with PCs. We also demonstrate that integration of radiologic and clinical features with texture feature radiomics data does not improve performance of our mucinous classifier. However, unique radiomic, radiologic, and clinical features were important in building our machine learning mucinous classifiers. These results highlight the potential of machine learning algorithms applied to high-throughput PC radiomics features in helping to detect mucinous cyst phenotype in patients and deserves further study to improve and validate such models.”
    Machine learning principles applied to CT radiomics to predict mucinous pancreatic cysts  
    Adam M. Awe et al.
    Abdominal Radiology (2022) 47:221–231
  • Background: At present, numerous challenges exist in the diagnosis of pancreatic SCNs and MCNs. After the emergence of artificial intelligence (AI), many radiomics research methods have been applied to the identification of pancreatic SCNs and MCNs. Purpose A deep neural network (DNN) model termed Multi-channel-Multiclassifier-Random Forest-ResNet (MMRF- ResNet) was constructed to provide an objective CT imaging basis for differential diagnosis between pancreatic serous cystic neoplasms (SCNs) and mucinous cystic neoplasms (MCNs).  
    Materials and methods: This study is a retrospective analysis of pancreatic unenhanced and enhanced CT images in 63 patients with pancreatic SCNs and 47 patients with MCNs (3 of which were mucinous cystadenocarcinoma) confirmed by pathology from December 2010 to August 2016. Different image segmented methods (single-channel manual outline ROI image and multi-channel image), feature extraction methods (wavelet, LBP, HOG, GLCM, Gabor, ResNet, and AlexNet) and classifiers (KNN, Softmax, Bayes, random forest classifier, and Majority Voting rule method) are used to classify the nature of the lesion in each CT image (SCNs/MCNs). Then, the comparisons of classification results were made based on sensitivity, specificity, precision, accuracy, F1 score, and area under the receiver operating characteristic curve (AUC), with pathological results serving as the gold standard.  
    Results: Multi-channel-ResNet (AUC 0.98) was superior to Manual-ResNet (AUC 0.91).CT image characteristics of lesions extracted by ResNet are more representative than wavelet, LBP, HOG, GLCM, Gabor, and AlexNet. Compared to the use of three classifiers alone and Majority Voting rule method, the use of the MMRF-ResNet model exhibits a better evaluation effect (AUC 0.96) for the classification of the pancreatic SCNs and MCNs.  
    Conclusion: The CT image classification model MMRF-ResNet is an effective method to distinguish between pancreatic SCNs and MCNs.  
    CT classification model of pancreatic serous cystic neoplasms and mucinous cystic neoplasms based on a deep neural network  
    Rong Yang et al.
    Abdominal Radiology (2022) 47:232–241 

  • CT classification model of pancreatic serous cystic neoplasms and mucinous cystic neoplasms based on a deep neural network  
    Rong Yang et al.
    Abdominal Radiology (2022) 47:232–241 
  • “In conclusion, in this study, Multi-channel CT images were obtained through preprocessing based on single-channel manual outline ROI images, and ResNet was used to extract CT image features of pancreatic SCNs and MCNs. The random forest classifier is used to integrate the classification probabilities of the KNN, Bayesian, and Softmax classifiers to determine the CT image properties of pancreatic SCNs and MCNs. Finally, a better classification result was obtained relative to the commonly used radiomics methods, suggesting that MMRF-ResNet is an ideal CT classification model for distinguishing between pancreatic SCNs and MCNs.”
    CT classification model of pancreatic serous cystic neoplasms and mucinous cystic neoplasms based on a deep neural network  
    Rong Yang et al.
    Abdominal Radiology (2022) 47:232–241 
  • Purpose: A deep neural network (DNN) model termed Multi-channel-Multiclassifier-Random Forest-ResNet (MMRF- ResNet) was constructed to provide an objective CT imaging basis for differential diagnosis between pancreatic serous cystic neoplasms (SCNs) and mucinous cystic neoplasms (MCNs).  
    Results: Multi-channel-ResNet (AUC 0.98) was superior to Manual-ResNet (AUC 0.91).CT image characteristics of lesions extracted by ResNet are more representative than wavelet, LBP, HOG, GLCM, Gabor, and AlexNet. Compared to the use of three classifiers alone and Majority Voting rule method, the use of the MMRF-ResNet model exhibits a better evaluation effect (AUC 0.96) for the classification of the pancreatic SCNs and MCNs.  
    Conclusion: The CT image classification model MMRF-ResNet is an effective method to distinguish between pancreatic SCNs and MCNs.
    CT classification model of pancreatic serous cystic neoplasms and mucinous cystic neoplasms based on a deep neural network  
    Rong Yang et al.
    Abdominal Radiology (2022) 47:232–241 
  • “we only analyzed the region of interest in images and did not analyze location information of the lesions (such as the head, body, and tail of the pancreas) and patient clinical information, such as gender, age, family history, and clinical symptoms, and the characteristics of the tumor have not been considered: size, grading, vascularization etc., for example are informations that can complete the clinical situation and they could be very useful notions.”
    CT classification model of pancreatic serous cystic neoplasms and mucinous cystic neoplasms based on a deep neural network  
    Rong Yang et al.
    Abdominal Radiology (2022) 47:232–241 
  •  “In conclusion, in this study, Multi-channel CT images were obtained through preprocessing based on single-channel manual outline ROI images, and ResNet was used to extract CT image features of pancreatic SCNs and MCNs. The random forest classifier is used to integrate the classification probabilities of the KNN, Bayesian, and Softmax classifiers to determine the CT image properties of pancreatic SCNs and MCNs. Finally, a better classification result was obtained relative to the commonly used radiomics methods, suggesting that MMRF-ResNet is an ideal CT classification model for distinguishing between pancreatic SCNs and MCNs.”
    CT classification model of pancreatic serous cystic neoplasms and mucinous cystic neoplasms based on a deep neural network  
    Rong Yang et al.
    Abdominal Radiology (2022) 47:232–241 
  • “In our study, the 2017 Fukuoka criteria performed slightly worse for selecting HRI for surgery compared to patients with sporadic cysts, missing 60% of cysts with invasive carcinoma, or IPMN with HGD, with a low sensitivity of 40%. Furthermore, the 2017 Fukuoka criteria might have resulted in unnecessary surgery of low-grade IPMN in our high risk population, with a modest specificity of 85%, which translates to ~15% of patients undergoing unnecessary or premature pancreatic surgery with its attendant morbidity and mortality. Similarly, the 2019 CAPS criteria missed 40% of resected IPMNs harboring advanced neoplasia while also recommending surgery for 15% of HRI that did not need it.”
    Guidelines on management of pancreatic cysts detected in high-risk individuals: An evaluation of the 2017 Fukuoka guidelines and the 2020 International Cancer of the Pancreas Screening (CAPS) consortium statements  
    Mohamad Dbouk , Olaya I. Brewer Gutierrez , Anne Marie Lennon , Miguel Chuidian , Eun Ji Shin , Ihab R. Kamel , Elliot K. Fishman , Jin He , Richard A. Burkhart , Christopher L. Wolfgang , Ralph H. Hruban , Michael G. Goggins, Marcia Irene Canto  
    Pancreatology 21 (2021) 613-621 
  • “One such approach is the detection of biomarkers in secretin- stimulated pancreatic juice at the time of EUS surveillance. The mutation profile and DNA concentration of pancreatic juice have been shown to be useful in the detection of high-grade PanIN le- sions and early PDAC in the CAPS cohort. Importantly, Yu et al. described the detection of low-abundance SMAD4/TP53 mu- tations from the cancer in the juice of patients under surveillance more than one year prior to the diagnosis of pancreatic mass on imaging. Overall, the analysis of pancreatic juice SMAD4/TP53 mutations could distinguish patients with PDAC or HGD from controls with a sensitivity and specificity of 72.2% and 89.4%, respectively.”
    Guidelines on management of pancreatic cysts detected in high-risk individuals: An evaluation of the 2017 Fukuoka guidelines and the 2020 International Cancer of the Pancreas Screening (CAPS) consortium statements  
    Mohamad Dbouk , Olaya I. Brewer Gutierrez , Anne Marie Lennon , Miguel Chuidian , Eun Ji Shin , Ihab R. Kamel , Elliot K. Fishman , Jin He , Richard A. Burkhart , Christopher L. Wolfgang , Ralph H. Hruban , Michael G. Goggins, Marcia Irene Canto  
    Pancreatology 21 (2021) 613-621 
  • “Finally, artificial intelligence and deep learning technologies applied to multi-detector pancreatic protocol CT may improve the early detection of pancreatic cancer or its precursor lesions.”
    Guidelines on management of pancreatic cysts detected in high-risk individuals: An evaluation of the 2017 Fukuoka guidelines and the 2020 International Cancer of the Pancreas Screening (CAPS) consortium statements  
    Mohamad Dbouk , Olaya I. Brewer Gutierrez , Anne Marie Lennon , Miguel Chuidian , Eun Ji Shin , Ihab R. Kamel , Elliot K. Fishman , Jin He , Richard A. Burkhart , Christopher L. Wolfgang , Ralph H. Hruban , Michael G. Goggins, Marcia Irene Canto  
    Pancreatology 21 (2021) 613-621 
  • “In conclusion, we report that the performance characteristics of the 2019 CAPS and 2017 Fukuoka ICG criteria for managing screen- detected pancreatic cysts are modestly specific but not sufficiently sensitive for selecting HRI for surgical treatment. New approaches, including multimodality algorithms that consider molecular cyst fluid analysis, clinical and genetic patient characteristics, and radiological pancreatic features, are needed to guide the surgical management of cystic lesions in individuals at high risk for pancreatic cancer.”
    Guidelines on management of pancreatic cysts detected in high-risk individuals: An evaluation of the 2017 Fukuoka guidelines and the 2020 International Cancer of the Pancreas Screening (CAPS) consortium statements  
    Mohamad Dbouk , Olaya I. Brewer Gutierrez , Anne Marie Lennon , Miguel Chuidian , Eun Ji Shin , Ihab R. Kamel , Elliot K. Fishman , Jin He , Richard A. Burkhart , Christopher L. Wolfgang , Ralph H. Hruban , Michael G. Goggins, Marcia Irene Canto  
    Pancreatology 21 (2021) 613-621 

  • Guidelines on management of pancreatic cysts detected in high-risk individuals: An evaluation of the 2017 Fukuoka guidelines and the 2020 International Cancer of the Pancreas Screening (CAPS) consortium statements  
    Mohamad Dbouk , Olaya I. Brewer Gutierrez , Anne Marie Lennon , Miguel Chuidian , Eun Ji Shin , Ihab R. Kamel , Elliot K. Fishman , Jin He , Richard A. Burkhart , Christopher L. Wolfgang , Ralph H. Hruban , Michael G. Goggins, Marcia Irene Canto  
    Pancreatology 21 (2021) 613-621 
  • ”Current PDAC surveillance is centered on imaging tests that detect pancreatic abnormalities, but as illustrated above, even individuals undergoing routine surveillance are sometimes diagnosed with advanced interval cancers.37 This fact suggests that improving the ability of imaging tests to identify precursor lesions could be useful in improving early detection. To that end, radiomics is an emerging field that holds promise. Traditionally, interpretation of radiographic images has been performed qualitatively by trained clinicians. The concept behind radiomics is to incorporate quantitative assessment of images by artificial intelligence, which allows for the identification of patterns not detectable visibly.”
    Pancreatic Cancer Surveillance and Novel Strategies for Screening  
    Beth Dudley, Randall E. Brand
    Gastrointest Endoscopy Clin N Am 32 (2022) 13–25 
  • Objective: To demonstrate enabling multi-institutional training without centralizing or sharing the underlying physical data via federated learning (FL). Materials and
    Methods: Deep learning models were trained at each participating institution using local clinical data, and an additional model was trained using FL across all of the institutions.  
    Results: We found that the FL model exhibited superior performance and generalizability to the models trained at single institutions, with an overall performance level that was significantly better than that of any of the institutional models alone when evaluated on held-out test sets from each institution and an outside challenge data- set.  
    Discussion: The power of FL was successfully demonstrated across 3 academic institutions while avoiding the privacy risk associated with the transfer and pooling of patient data.
    Conclusion: Federated learning is an effective methodology that merits further study to enable accelerated development of models across institutions, enabling greater generalizability in clinical use.  
    Federated learning improves site performance in multicenter deep learning without data sharing  
    Karthik V. Sarma et al.
    J Am Med Inform Assoc. 2021 Jun 12;28(6):1259-1264
  • “The power of federated learning was successfully demonstrated across 3 academic institutions using real clinical prostate imaging data. The federated model demonstrated improved performance across both held-out test sets from each institution and an external test set, validating the FL paradigm. This methodology could be ap- plied to a wide variety of DL applications in medical image analysis and merits further study to enable accelerated development of DL models across institutions, enabling greater generalizability in clinical use.”
    Federated learning improves site performance in multicenter deep learning without data sharing  
    Karthik V. Sarma et al.
    J Am Med Inform Assoc. 2021 Jun 12;28(6):1259-1264
  • “Diagnostic AI has not realized its potential to improve diagnostic performance because it has not focused on supporting the diagnostic journey. Knowing the direction of the pathway in a complex environment is important, but the essential decision is determining the next step. A shift to wayfinding AI could help achieve the synergy of human intelligence and AI to achieve diagnostic excellence.”
    Next-Generation Artificial Intelligence for Diagnosis  From Predicting Diagnostic Labels to “Wayfinding”
    Julia Adler-Milstein et al.  
    JAMA( Published online)December 9, 2021 
  • “In this paper, we consider a partially supervised setting, where cheap image-level annotations are provided for all the train- ing data, and the costly per-voxel annotations are only available for a subset of them. We propose an Inductive Attention Guidance Network (IAG-Net) to jointly learn a global image-level classifier for normal/PDAC classification and a local voxel-level classifier for semi-supervised PDAC segmentation. We instantiate both the global and the local classifiers by multiple instance learning (MIL), where the attention guidance, indicating roughly where the PDAC regions are, is the key to bridging them: For global MIL based normal/PDAC classification, attention serves as a weight for each instance (voxel) during MIL pooling, which eliminates the distraction from the background; For local MIL based semi-supervised PDAC segmentation, the attention guidance is inductive, which not only provides bag-level pseudo-labels to training data without per-voxel annotations for MIL training, but also acts as a proxy of an instance-level classifier.”
    Learning Inductive Attention Guidance for Partially Supervised Pancreatic Ductal Adenocarcinoma Prediction  
    Yan Wang , Peng Tang, Yuyin Zhou , Wei Shen, Elliot K. Fishman , Alan L. Yuille,  
    IEEE TRANSACTIONS ON MEDICAL IMAGING, VOL. 40, NO. 10, OCTOBER 2021 

  • Learning Inductive Attention Guidance for Partially Supervised Pancreatic Ductal Adenocarcinoma Prediction  
    Yan Wang , Peng Tang, Yuyin Zhou , Wei Shen, Elliot K. Fishman , Alan L. Yuille,  
    IEEE TRANSACTIONS ON MEDICAL IMAGING, VOL. 40, NO. 10, OCTOBER 2021 

  • Learning Inductive Attention Guidance for Partially Supervised Pancreatic Ductal Adenocarcinoma Prediction  
    Yan Wang , Peng Tang, Yuyin Zhou , Wei Shen, Elliot K. Fishman , Alan L. Yuille,  
    IEEE TRANSACTIONS ON MEDICAL IMAGING, VOL. 40, NO. 10, OCTOBER 2021 
  • “This paper addresses the problem of PDAC prediction i.e., normal/PDAC classification and PDAC segmentation under the partially supervised setting. We present an Inductive Attention Guidance (IAG) strategy for learning a global image-level clas- sifier for normal/PDAC segmentation and a local instance-level classifier for semi-supervised PDAC segmentation, which enjoys the advantages of bridging the MIL-based global and local classifiers. We showed empirically on the JHMI dataset the superiority of the proposed IAG-Net for PDAC predic- tion, which is helpful to computer-assisted clinical diagnoses. Additionally, we verified the generality of IAG-Net on the pancreas tumor segmentation dataset in MSD challenge.”  
    Learning Inductive Attention Guidance for Partially Supervised Pancreatic Ductal Adenocarcinoma Prediction  
    Yan Wang , Peng Tang, Yuyin Zhou , Wei Shen, Elliot K. Fishman , Alan L. Yuille,  
    IEEE TRANSACTIONS ON MEDICAL IMAGING, VOL. 40, NO. 10, OCTOBER 2021
  • “This study aimed to investigate the diagnostic ability of carcinoembryonic antigen (CEA), cytology, and artificial intelligence (AI) by deep learning using cyst fluid in differentiating malignant from benign cystic lesions. We retrospectively reviewed 85 patients who underwent pancreatic cyst fluid analysis of surgical specimens or endoscopic ultrasound-guided fine-needle aspiration specimens. AI using deep learning was used to construct a diagnostic algorithm. CEA, carbohydrate antigen 19-9, carbohydrate antigen 125, amylase in the cyst fluid, sex, cyst location, connection of the pancreatic duct and cyst, type of cyst, and cytology were keyed into the AI algorithm, and the malignant predictive value of the output was calculated. Area under receiver-operating characteristics curves for the diagnostic ability of malignant cystic lesions were 0.719 (CEA), 0.739 (cytology), and 0.966 (AI). In the diagnostic ability of malignant cystic lesions, sensitivity, specificity, and accuracy of AI were 95.7%, 91.9%, and 92.9%, respectively. AI sensitivity was higher than that of CEA (60.9%, p = 0.021) and cytology (47.8%, p = 0.001). AI accuracy was also higher than CEA (71.8%, p < 0.001) and cytology (85.9%, p = 0.210). AI may improve the diagnostic ability in differentiating malignant from benign pancreatic cystic lesions.”
    Diagnostic ability of artificial intelligence using deep learning analysis of cyst fluid in differentiating malignant from benign pancreatic cystic lesions  
    Yusuke Kurita et al.
    Scientific Reports | (2019) 9:6893 
  • "Although cytology had excellent specificity, it has a limited role because of its lack of sensitivity in previous studies30–32. In the present study, the sensitivity of cytology in differentiating malignant from benign cystic lesions was 47.8%. Thus, we constructed AI using deep learning algorithm for differentiating malignant from benign pancreatic cystic lesions based on the analysis of pancreatic cyst fluid and clinical data.”  
    Diagnostic ability of artificial intelligence using deep learning analysis of cyst fluid in differentiating malignant from benign pancreatic cystic lesions  
    Yusuke Kurita et al.
    Scientific Reports | (2019) 9:6893 
  • "In this study, AI using deep learning analyzed pancreatic cyst fluid and clinical data. By using this deep learning method, AI learns the characteristics of malignant cystic lesions by combining cyst fluid analysis and clinical data, and AI can possibly exclude the bias generated by human judgment. Although it is difficult for clinicians to diagnose malignant pancreatic cystic lesions by cyst fluid analysis and clinical data, AI using deep learning achieved adequate diagnostic ability in differentiating malignant from benign cystic lesions compared to cyst fluid analysis such as CEA and cytology. AI and CEA were also significant factor in the multivariate analysis of malignant cystic lesion. Specifically, although it is generally a problem that cytology diagnosis has low sensitivity, AI using deep learning achieved high sensitivity (95.7%).”
    Diagnostic ability of artificial intelligence using deep learning analysis of cyst fluid in differentiating malignant from benign pancreatic cystic lesions  
    Yusuke Kurita et al.
    Scientific Reports | (2019) 9:6893 
  • “Pancreatic cysts are common and often pose a management dilemma, because some cysts are precancerous, whereas others have little risk of developing into invasive cancers. We used supervised machine learning techniques to develop a comprehensive test, CompCyst, to guide the management of patients with pancreatic cysts. The test is based on selected clinical features, imaging characteristics, and cyst fluid genetic and biochemical markers. Using data from 436 patients with pancreatic cysts, we trained CompCyst to classify patients as those who required surgery, those who should be routinely monitored, and those who did not require further surveillance. We then tested CompCyst in an independent cohort of 426 patients, with histopathology used as the gold standard. We found that clinical management informed by the CompCyst test was more accurate than the management dictated by conventional clinical and imaging criteria alone. Application of the CompCyst test would have spared surgery in more than half of the patients who underwent unnecessary resection of their cysts. CompCyst therefore has the potential to reduce the patient morbidity and economic costs associated with current standard-of-care pancreatic cyst management practices.”
    A multimodality test to guide the management of patients with a pancreatic cyst.  
    Springer S, Masica DL, Dal Molin M, et al.  
    Sci Transl Med. 2019;11(501):eaav4772. doi:10.1126/scitranslmed.aav4772
  • “We found that clinical management informed by the CompCyst test was more accurate than the management dictated by conventional clinical and imaging criteria alone. Application of the CompCyst test would have spared surgery in more than half of the patients who underwent unnecessary resection of their cysts. CompCyst therefore has the potential to reduce the patient morbidity and economic costs associated with current standard-of-care pancreatic cyst management practices.”
    A multimodality test to guide the management of patients with a pancreatic cyst.  
    Springer S, Masica DL, Dal Molin M, et al.  
    Sci Transl Med. 2019;11(501):eaav4772. doi:10.1126/scitranslmed.aav4772
  • “Two dilemmas make pancreatic cyst clinical management challenging. First, it is difficult to differentiate IPMNs and MCNs, collectively termed “mucin-producing cysts,” from cysts that have no malignant potential and do not require any follow-up. Second, it can be difficult to differentiate patients with mucin-producing cysts that harbor early invasive cancer or high-grade dysplasia from patients with less advanced mucin-producing cysts. Surgery is recommended for patients with advanced cysts, whereas intermittent surveillance with imaging, rather than surgery, is considered appropriate for patients with less advanced cysts. Currently available clinical tools, however, are imperfect at assigning the most appropriate management strategies for patients with cysts. This is highlighted by the fact that 25% of cyst patients who undergo surgical resection have a pancreatic cyst with no malignant potential, and up to 78% of mucin-producing cysts referred for surgical resection are ultimately found not to be advanced, that is, they do not harbor high-grade dysplasia or cancer.”
    A multimodality test to guide the management of patients with a pancreatic cyst.  
    Springer S, Masica DL, Dal Molin M, et al.  
    Sci Transl Med. 2019;11(501):eaav4772. doi:10.1126/scitranslmed.aav4772

  • A multimodality test to guide the management of patients with a pancreatic cyst.  
    Springer S, Masica DL, Dal Molin M, et al.  
    Sci Transl Med. 2019;11(501):eaav4772. doi:10.1126/scitranslmed.aav4772

  • A multimodality test to guide the management of patients with a pancreatic cyst.  
    Springer S, Masica DL, Dal Molin M, et al.  
    Sci Transl Med. 2019;11(501):eaav4772. doi:10.1126/scitranslmed.aav4772

  • A multimodality test to guide the management of patients with a pancreatic cyst.  
    Springer S, Masica DL, Dal Molin M, et al.  
    Sci Transl Med. 2019;11(501):eaav4772. doi:10.1126/scitranslmed.aav4772
  •  “In conclusion, the use of a comprehensive test that evaluates clinical, imaging, and molecular features is imperfect but appears to offer substantial improvements over standard-of-care management of patients with pancreatic cysts. CompCyst does not replace conventional clinical tools. Instead, it contributes additional information, allowing clinicians to make more informed decisions. How and when tests like CompCyst can be implemented in routine clinical settings remains to be determined, but our results represent the next stage of research required for such implementation. An important next test of the markers presented here could be their validation in a follow-up, prospective study.”
    A multimodality test to guide the management of patients with a pancreatic cyst.  
    Springer S, Masica DL, Dal Molin M, et al.  
    Sci Transl Med. 2019;11(501):eaav4772. doi:10.1126/scitranslmed.aav4772
  • "Pancreatic cystic lesions, particularly IPMN, are the precursors of pancreatic cancer. Kuwahara et al. successfully established an AI-aided EUS using deep learning to distinguish malignant IPMNs from benign ones. The AI-aided EUS could diagnose malignant probability with a high sensitivity of 95.7% and a high accuracy of 94.0%, which was much greater than that of experts’ diagnoses (56.0%). AI-aided diagnosis is under development not only for IPMNs but also for other cystic lesions of the pancreas, such as serous cystic neoplasms, mucinous cystic neoplasms, solid pseudopapillary neoplasms, and cystic pancreatic neuroendocrine neoplasms.”
    A New Dawn for the Use of Artificial Intelligence in Gastroenterology, Hepatology and Pancreatology
    Akihiko Oka  , Norihisa Ishimura and Shunji Ishihara  
    Diagnostics 2021, 11, 1719. https://doi.org/10.3390/diagnostics11091719 
  • “Pancreatic schwannoma is a slowly growing, encapsulated, benign neoplasm that typically arises in the peripheral epineurium of either the sympathetic or parasympathetic autonomic fibers or branches of vagus nerve that extend to the pancreas. Pancreatic schwannomas most frequently involve the pancreas head (40%), followed by body (21%), neck (6%), tail (15%), and uncinate process (13%), respectively.”
    Abdominal schwannomas: review of imaging findings and pathology.
    Lee NJ, Hruban RH, Fishman EK.Abdom Radiol (NY).
    2017 Jul;42(7):1864-1870
  • "The features of pancreatic schwannomas on CT scan include low-density and/or cystic degenerative areas. MR imaging usually shows hypointensity on T1-weighted images and hyperintensity on T2-weighted images but like the CT features, these findings are nonspecific. Two-thirds of pancreatic schwannomas undergo degenerative changes such as cyst formation, necrosis, calcification, and hemorrhage, and these changes can mimic pancreatic cystic tumors.”
    Abdominal schwannomas: review of imaging findings and pathology.
    Lee NJ, Hruban RH, Fishman EK.Abdom Radiol (NY).
    2017 Jul;42(7):1864-1870
  • "In conclusion, 53.4% of patients diagnosed with clinical stage I PDAC demonstrated focal pancreatic abnormalities on pre-diagnostic CT examinations obtained at least one year before the diagnosis of PDAC. The most common focal abnormality on pre-diagnostic CT in patients who developed PDAC was focal parenchymal atrophy, followed by focal faint parenchymal enhancement and focal MPD change. Among these three findings, focal MPD change exhibited the shortest duration between its new development and the subsequent diagnosis of PDAC, while focal atrophy and faint enhancement exhibited more prolonged duration. These observations could facilitate earlier diagnosis of PDAC and thus improve management and prognosis.”
    CT Abnormalities of the Pancreas Associated With the Subsequent Diagnosis of Clinical Stage I Pancreatic Ductal Adenocarcinoma More Than One Year Later: A Case-Control Study  
    Fumihito Toshima et al.
    AJR 2021(in press) https://doi.org/10.2214/AJR.21.26014 
  • “Rigiroli et al provide an important advance in the struggle to select appropriate surgical candidates with pancreatic ductal adenocarcinoma based on preoperative CT imaging. With the increased use of neoadjuvant therapy, this article is particularly relevant given the known challenges in assessing vascular involvement after chemotherapy. However, the reality of neoadjuvant therapy is that the treatment landscape is evolving rapidly, with new drug and external beam radiation trials maturing every year. A persistent challenge in bringing radiomics to clinical practice in patients with cancer is the generalizability of predictive models that are derived from a subset of treatment regimens that may no longer be relevant over time.”
    Radiomics for CT Assessment of Vascular Contact in Pancreatic Adenocarcinoma  
    Richard K.G.Do, Avinash Kambadakone
    Radiology 2021; 00:1–2 • https://doi.org/10.1148/radiol.2021211635
  • Background: Current imaging methods for prediction of complete margin resection (R0) in patients with pancreatic ductal adeno- carcinoma (PDAC) are not reliable.  
    Purpose: To investigate whether tumor-related and perivascular CT radiomic features improve preoperative assessment of arterial involvement in patients with surgically proven PDAC.  
    Conclusion: A model based on tumor-related and perivascular CT radiomic features improved the detection of superior mesenteric artery involvement in patients with pancreatic ductal adenocarcinoma.  
    CT Radiomic Features of Superior Mesenteric Artery Involvement in Pancreatic Ductal Adenocarcinoma: A Pilot Study  
    Francesca Rigiroli et al.
    Radiology 2021; 000:1–13 • https://doi.org/10.1148/radiol.2021210699 
  • • In a retrospective study of 194 patients with pancreatic ductal adenocarcinoma, CT radiomic features demonstrated sensitivity of 62% (33 of 53 patients) and specificity of 77% (108 of 141 patients) in the detection of superior mesenteric artery involvement in patients undergoing surgery for pancreatic ductal adenocarcinoma.  
    • The radiomic model results outperformed the assessment made by expert radiologists in consensus during a multidisciplinary meeting, yielding areas under the curve of 0.71 and 0.54, respectively (P , .001).  
    CT Radiomic Features of Superior Mesenteric Artery Involvement in Pancreatic Ductal Adenocarcinoma: A Pilot Study  
    Francesca Rigiroli et al.
    Radiology 2021; 000:1–13 • https://doi.org/10.1148/radiol.2021210699 
  • “In conclusion, our results suggest that the analysis of tu- mor-related and perivascular radiomic features improves pre- operative assessment of tumor involvement of the superior mesenteric artery in patients with pancreatic ductal adenocar- cinoma, a highly challenging task for even experienced multi- disciplinary teams, particularly after neoadjuvant therapy. To ensure our model is valid and unbiased, it should be validated in a separate independent data set. Future work may also in- corporate more sophisticated modeling techniques, including unsupervised machine learning frameworks and deep learning algorithms that fuse radiomics data with other types of clinical data.”
    CT Radiomic Features of Superior Mesenteric Artery Involvement in Pancreatic Ductal Adenocarcinoma: A Pilot Study  
    Francesca Rigiroli et al.
    Radiology 2021; 000:1–13 • https://doi.org/10.1148/radiol.2021210699 
  • “In our study, the radiomic model showed higher negative predictive value than the multidisciplinary assessment in ruling out SMA tumoral involvement defined by a clearance of 1 mm. Our results and previous studies have shown that predicting margin status using only standard CT criteria is challenging. Recent investigations have emphasized the need for optimal identification of patients with high likelihood of margin- negative resection, such as with a tumor more than 1 mm from the margin, because it yields a better prognosis compared with patients with positive surgical margin (tumor ≤1 mm to the margin or direct involvement). Despite being limited to assessment of the SMA margin, the application of our radiomic model in a clinical setting could help to guide radiologists in predicting margin status.”
    CT Radiomic Features of Superior Mesenteric Artery Involvement in Pancreatic Ductal Adenocarcinoma: A Pilot Study  
    Francesca Rigiroli et al.
    Radiology 2021; 000:1–13 • https://doi.org/10.1148/radiol.2021210699 
  • OBJECTIVE. Pancreatic ductal adenocarcinoma (PDAC) is often a lethal malignancy with limited preoperative predictors of long-term survival. The purpose of this study was to evaluate the prognostic utility of preoperative CT radiomics features in predict- ing postoperative survival of patients with PDAC.  
    RESULTS. The mean age of patients with PDAC was 67 ± 11 (SD) years. The mean tu- mor size was 3.31 ± 2.55 cm. The 10 most relevant radiomics features showed 82.2% ac- curacy in the classification of high-risk versus low-risk groups. The C-index of survival prediction with clinical parameters alone was 0.6785. The addition of CT radiomics features improved the C-index to 0.7414.  
    CONCLUSION. Addition of CT radiomics features to standard clinical factors im- proves survival prediction in patients with PDAC.  
    CT Radiomics–Based Preoperative Survival Prediction in Patients With Pancreatic Ductal Adenocarcinoma  
    Seyoun P, Kawamoto S, Fishman EK, Chu LC et al.
    AJR:217, November 2021 (in press) 
  • “Survival time after the surgical resection was used to stratify patients into a low- risk group (survival time > 3 years) and a high-risk group (survival time < 1 year). The 3D volume of the whole pancreatic tumor and background pancreas were manually seg- mented. A total of 478 radiomics features were extracted from tumors and 11 extra features were computed from pancreas boundaries. The 10 most relevant features were selected by feature reduction. Survival analysis was performed on the basis of clinical parameters both with and without the addition of the selected features. Survival status and time were estimated by a random survival forest algorithm. Concordance index (C-index) was used to evaluate performance of the survival prediction model.”
    CT Radiomics–Based Preoperative Survival Prediction in Patients With Pancreatic Ductal Adenocarcinoma  
    Seyoun P, Kawamoto S, Fishman EK, Chu LC et al.
    AJR:217, November 2021 (in press) 
  • "Tumors are spatially heterogeneous structures that can be characterized at a macro scale, and normal parenchyma can also be affected by the growth of the tumor. Texture analysis using medical images, especially radiomics approaches, is an established tech- nique that describes spatial variations in pixel intensities in images for quantitative assessment. Whereas radiologists may qualitatively describe PDAC enhancement patterns as, for example, homogeneously isoattenuating or heterogeneously hypoattenuating, tex- ture analysis can capture more subtle underlying differences that may reflect important pathologic differences and thereby help predict patient survival.”
    CT Radiomics–Based Preoperative Survival Prediction in Patients With Pancreatic Ductal Adenocarcinoma  
    Seyoun P, Kawamoto S, Fishman EK, Chu LC et al.
    AJR:217, November 2021 (in press) 
  •  “The entire 3D volume of the pancreas was segmented based on thin-slice venous phase images. The 3D volume of the whole tumor and background pancreas was manually segmented by four trained researchers using a commercial annotation software (Velocity, Varian Medical Systems). The boundaries were verified by three abdominal radiologists with 5–30 years of experience. Each case was randomly assigned to one of the researchers and a radiologist. The researcher and radiologist had face-to-face sessions to review each case. Any disagreement or errors identified during this review were corrected.”
    CT Radiomics–Based Preoperative Survival Prediction in Patients With Pancreatic Ductal Adenocarcinoma  
    Seyoun P, Kawamoto S, Fishman EK, Chu LC et al.
    AJR:217, November 2021 (in press) 
  • "Based on the selected radiomics features, a random survival forest was applied for survival prediction in a multivariate dataset with missing variables. Each decision node was divided until three unique deaths (d = 3) remained in the leaf node. Ten thousand trees were built by the training set using the AUC for the split of internal nodes. Each end node stored the survival sta- tus (dead or alive), survival time, and a Cox proportional hazard function of the assigned cases. The survival time and survival status predictions in the validation cohort were determined by majority voting based on the trained trees.”
    CT Radiomics–Based Preoperative Survival Prediction in Patients With Pancreatic Ductal Adenocarcinoma  
    Seyoun P, Kawamoto S, Fishman EK, Chu LC et al.
    AJR:217, November 2021 (in press)  

  • CT Radiomics–Based Preoperative Survival Prediction in Patients With Pancreatic Ductal Adenocarcinoma  
    Seyoun P, Kawamoto S, Fishman EK, Chu LC et al.
    AJR:217, November 2021 (in press) 
  • "The 10 most relevant radiomics features were selected to distinguish the high- and low-risk groups and are listed in Table 4. To determine the classification power of the selected features, binary classification was performed using a random forest. Among 90 patients, 45 (50.0%, 22 low-risk and 23 high-risk) randomly select- ed patients were included in the training set, and the remaining 45 (50.0%, 23 low-risk and 22 high-risk) were included in the validation set. The overall accuracy of classification of patients into high- and low-risk groups based on selected image features was 82.2%. The high-risk group showed a higher classification performance, with 86.4% accuracy, compared with the low-risk group, with 78.3% accuracy.”
    CT Radiomics–Based Preoperative Survival Prediction in Patients With Pancreatic Ductal Adenocarcinoma  
    Seyoun P, Kawamoto S, Fishman EK, Chu LC et al.
    AJR:217, November 2021 (in press) 
  •  "We found that radiomics features extracted from tumors and from the nonneoplastic pancreas can be used to improve survival prediction models of patients who underwent surgery for PDAC. This algorithm could be combined with other pathologic and genetic biomarkers.”
    CT Radiomics–Based Preoperative Survival Prediction in Patients With Pancreatic Ductal Adenocarcinoma  
    Seyoun P, Kawamoto S, Fishman EK, Chu LC et al.
    AJR:217, November 2021 (in press)  

  • CT Radiomics–Based Preoperative Survival Prediction in Patients With Pancreatic Ductal Adenocarcinoma  
    Seyoun P, Kawamoto S, Fishman EK, Chu LC et al.
    AJR:217, November 2021 (in press) 
  • “Pancreatic ductal adenocarcinoma (PDAC) is a leading cause of mortality among all cancers. It ranked fifth among all cancers in terms of mortality and its overall 5-year survival rate was just 6% in Korea for 2015. Surgical resection is essential for its cure but only a small proportion of its cases are found at an early stage enough for the procedure. Moreover, its recurrence rate after surgery is estimated to be 50%–60%, while its 5-year survival rate after surgery is reported to be just 20%–30% . The mean disease-free period in imaging studies is 267 ± 158 d with negative surgical margins, but 72 ± 47 d with positive margins. Therefore the survival of patients with PDAC is closely related to recurrence, and recurrence after surgery is one of the typical characteristics of PDAC .”
    Usefulness of artificial intelligence for predicting recurrence following surgery for pancreatic cancer: Retrospective cohort study  
    Kwang-Sig Lee et al.
    International Journal of Surgery 93 (2021) 106050 
  • "It is very important to prevent the recurrence of pancreatic cancer after surgery and there has been strong endeavor to identify major predictors of its disease-free survival after surgery. However, the results of existing literature were inconsistent and predictors in these studies were unmodifiable in general. Predictive nomograms were developed to combine and visualize the findings of traditional statistical models such as logistic regression and the Cox model regarding the recurrence of pancreatic cancer after surgery. But the predictive nomograms still require unrealistic assumptions of the traditional statistical models, i.e., ceteris paribus, “all the other variables staying constant”. In this context, this study used the random forest and multi-center registry data to analyze the recurrence of pancreatic cancer after surgery and its major determinants.”
    Usefulness of artificial intelligence for predicting recurrence following surgery for pancreatic cancer: Retrospective cohort study  
    Kwang-Sig Lee et al.
    International Journal of Surgery 93 (2021) 106050 
  • "Secondly, it was beyond the scope of this study to combine deep learning and the Cox model for predicting the recurrence of pancreatic cancer after surgery. Deep learning can be defined as “a sub-group of the artificial neural network whose number of hidden layers is larger than five, e.g., ten”. The last three years have seen the emergence of new strands of research to combine the Cox model with different types of its deep-learning counterparts. The continued development and application of these cutting-edge approaches would break new ground and bring more profound clinical insights regarding the recurrence of pancreatic cancer after surgery and its major determinants.”
    Usefulness of artificial intelligence for predicting recurrence following surgery for pancreatic cancer: Retrospective cohort study  
    Kwang-Sig Lee et al.
    International Journal of Surgery 93 (2021) 106050 
  • “This study aimed to investigate the diagnostic ability of carcinoembryonic antigen (CEA), cytology, and artificial intelligence (AI) by deep learning using cyst fluid in differentiating malignant from benign cystic lesions. We retrospectively reviewed 85 patients who underwent pancreatic cyst fluid analysis of surgical specimens or endoscopic ultrasound-guided fine-needle aspiration specimens. AI using deep learning was used to construct a diagnostic algorithm. CEA, carbohydrate antigen 19-9, carbohydrate antigen 125, amylase in the cyst fluid, sex, cyst location, connection of the pancreatic duct and cyst, type of cyst, and cytology were keyed into the AI algorithm, and the malignant predictive value of the output was calculated. Area under receiver-operating characteristics curves for the diagnostic ability of malignant cystic lesions were 0.719 (CEA), 0.739 (cytology), and 0.966 (AI). In the diagnostic ability of malignant cystic lesions, sensitivity, specificity, and accuracy of AI were 95.7%, 91.9%, and 92.9%, respectively. AI sensitivity was higher than that of CEA (60.9%, p = 0.021) and cytology (47.8%, p = 0.001). AI accuracy was also higher than CEA (71.8%, p < 0.001) and cytology (85.9%, p = 0.210). AI may improve the diagnostic ability in differentiating malignant from benign pancreatic cystic lesions.”
    Diagnostic ability of artificial intelligence using deep learning analysis of cyst fluid in differentiating malignant from benign pancreatic cystic lesions  
    Yusuke Kurita et al.
    Scientific Reports | (2019) 9:6893 
  • "Although cytology had excellent specificity, it has a limited role because of its lack of sensitivity in previous studies30–32. In the present study, the sensitivity of cytology in differentiating malignant from benign cystic lesions was 47.8%. Thus, we constructed AI using deep learning algorithm for differentiating malignant from benign pancreatic cystic lesions based on the analysis of pancreatic cyst fluid and clinical data.”  
    Diagnostic ability of artificial intelligence using deep learning analysis of cyst fluid in differentiating malignant from benign pancreatic cystic lesions  
    Yusuke Kurita et al.
    Scientific Reports | (2019) 9:6893 
  • "In this study, AI using deep learning analyzed pancreatic cyst fluid and clinical data. By using this deep learning method, AI learns the characteristics of malignant cystic lesions by combining cyst fluid analysis and clinical data, and AI can possibly exclude the bias generated by human judgment. Although it is difficult for clinicians to diagnose malignant pancreatic cystic lesions by cyst fluid analysis and clinical data, AI using deep learning achieved adequate diagnostic ability in differentiating malignant from benign cystic lesions compared to cyst fluid analysis such as CEA and cytology. AI and CEA were also significant factor in the multivariate analysis of malignant cystic lesion. Specifically, although it is generally a problem that cytology diagnosis has low sensitivity, AI using deep learning achieved high sensitivity (95.7%).”
    Diagnostic ability of artificial intelligence using deep learning analysis of cyst fluid in differentiating malignant from benign pancreatic cystic lesions  
    Yusuke Kurita et al.
    Scientific Reports | (2019) 9:6893 
  • "Although only a few studies describing the use of radiomics in risk stratification of PCLs have been published, these studies have demonstrated that radiomics can be utilized to non-invasively discriminate between low-risk and high-risk PCLs before resection. This cost-effective approach would enable us to accurately recommend lifesaving surgery for individuals with malignant cysts and spare those with benign lesions the morbidity, mortality and high costs associated with pancreatic surgeries. Consequently, more studies are warranted to develop these imaging biomarkers which can be used to differentiate between benign and malignant PCLs.”
    Radiomics in stratification of pancreatic cystic lesions: Machine learning in action  
    Vipin Dalala et al.
    Cancer Letters,Volume 469,2020,Pages 228-237
  • "Chakraborty et al. utilized radiomics features extracted from pre- surgical CT images, as markers for assessment of malignancy risk of BD- IPMNs. Similar to the previous studies, they categorized their cohort of 103 patients into low-risk and high-risk IPMNs based on final pathological findings after cyst resection. They extracted four new radio- graphically inspired features (enhanced boundary fraction, enhanced inside fraction, filled largest connected component fraction and average weighted eccentricity), along with intensity and orientation-based texture features from the CT images.”
    Radiomics in stratification of pancreatic cystic lesions: Machine learning in action  
    Vipin Dalala et al.
    Cancer Letters,Volume 469,2020,Pages 228-237
  • "This has led to an increased interest in radiomics, a high-throughput extraction of comprehensible data from standard of care images. Radiomics can be used as a diagnostic and prognostic tool in personalized medicine. It utilizes quantitative image analysis to extract features in conjunction with machine learning and artificial intelligence (AI) methods like support vector machines, random forest, and convolutional neural network for feature se- lection and classification. Selected features can then serve as imaging biomarkers to predict high-risk PCLs. Radiomics studies conducted heretofore on PCLs have shown promising results.”
    Radiomics in stratification of pancreatic cystic lesions: Machine learning in action  
    Vipin Dalala et al.
    Cancer Letters,Volume 469,2020,Pages 228-237
  • "IPMNs and MCNs are the only radiographically identifiable precursors of pancreatic cancer. Consequently, accurate assessment of the malignant potential of these cystic lesions may allow early detection of resectable PCLs prior to oncogenesis. The latest guidelines propose a practical approach for their management and surveillance, yet the clinical management of these mucinous cystic lesions remains challenging. The variable risk of malignant transformation combined with elevated risks associated with pancreatic surgery have led to conflicting recommendations for the management of mucinous cystic lesions.”
    Radiomics in stratification of pancreatic cystic lesions: Machine learning in action  
    Vipin Dalala et al.
    Cancer Letters,Volume 469,2020,Pages 228-237
  • “The multivariable logistic regression model included sex, size, location, shape, cyst characteristic, and cystic wall thickening. The individualized prediction nomogram showed good discrimination in the training sample (AUC 0.89; 95% CI 0.83–0.95) and in the validation sample (AUC 0.81; 95% CI 0.70–0.94). If the threshold probability is between 0.03 and 0.9, and > 0.93 in the prediction model, using the nomogram to predict SCN and MCN is more beneficial than the treat-all- patients as SCN scheme or the treat-all-patients as MCN scheme. The prediction model showed better discrimination than the radiologists’ diagnosis (AUC = 0.68).”
    A nomogram for predicting pancreatic mucinous cystic neoplasm and serous cystic neoplasm  
    Chengwei Shao et al.
    Abdominal Radiology https://doi.org/10.1007/s00261-021-03038-3 
  • All tumors were evaluated for the following characteristics: (1) CT-reported tumor size (i.e., the maximum cross-sectional diameter of the tumor [13]); (2) tumor location: pancreatic head, body, or tail; (3) shape: round or lobulated (lobulation was defined as the presence of rounded contours that could not be described as the borders of the same circle [9]); (4) cyst characteristic: oligocystic or polycystic; (5) cystic wall: thin or thick (thin was defined as < 2 mm while thick was defined as ≥ 2 mm [9]); (6) calcification; (7) enhanced mural nodule; (8) parenchymal atrophy; (9) common bile duct cutoff and dila- tion (> 10 mm); (10) main pancreatic duct (MPD) cutoff and dilation (> 3 mm); (11) pancreatitis identified by stranding of the peripancreatic fat tissue, ill-defined parenchymal contours, and fluid collections in the peripancreatic region; (12) contour abnormality; and (13) number of lesions: 1 or ≥ 2.  
    A nomogram for predicting pancreatic mucinous cystic neoplasm and serous cystic neoplasm  
    Chengwei Shao et al.
    Abdominal Radiology https://doi.org/10.1007/s00261-021-03038-3 
  • “There were several limitations to this study. First, the number of patients was relatively small. Second, this was a single-center, retrospective analysis. In the future, we will expand the number of cases and perform a multi-center validation of the model. Third, the predicted model in this study only focused on SCN and MCN, and did not include other cystic lesions of the pancreas such as IPMN, pseudocyst, and retention cyst. Lastly, we only used CT characteristics to develop the model. We did not combine radiomics features, although artificial intelligence is becoming a hot topic. In the future, we will combine the CT characteristics and radiomics features to develop a more accurate model.”
    A nomogram for predicting pancreatic mucinous cystic neoplasm and serous cystic neoplasm  
    Chengwei Shao et al.
    Abdominal Radiology https://doi.org/10.1007/s00261-021-03038-3 
  • “Lastly, we only used CT characteristics to develop the model. We did not combine radiomics features, although artificial intelligence is becoming a hot topic. In the future, we will combine the CT characteristics and radiomics features to develop a more accurate model.”
    A nomogram for predicting pancreatic mucinous cystic neoplasm and serous cystic neoplasm  
    Chengwei Shao et al.
    Abdominal Radiology https://doi.org/10.1007/s00261-021-03038-3  
  • “Pancreatic cancer (pancreatic ductal adenocarcinoma [PDAC]) is associated with a dire prognosis and a 5-year survival rate of only 10%. This statistic is somewhat misleading given that 52% of the patients will develop metastatic disease, with a resulting 2.9%, 5-year relative survival rate. However, for those patients with localized cancer where the tumor is confined to the primary site, the 5-year relative survival rate is 39.4%. It is estimated that in 2020, there will be 57,600 new cases of PDAC  and an estimated 47,050 will die of this disease.”  
    Artificial Intelligence and Early Detection of Pancreatic Cancer: 2020 Summative Review  
    Barbara Kenner, PhD,* Suresh T. Chari, MD,† David Kelsen, MD, Fishman EK et al.
    Pancreas. 2021 Mar 1;50(3):251-279
  • "Pancreatic ductal adenocarcinoma has the poorest overall survival of all the major cancer types, with a 5-year relative  survival rate that just reached 10%. This is due in part to the latestage at presentation, so that 49.6% of cases of newly diagnosed PDAC present with distant metastases, 29.1% present with re- gional lymph node involvement, and only 10.8% have tumors that are localized solely within the pancreas.”
    Artificial Intelligence and Early Detection of Pancreatic Cancer: 2020 Summative Review  
    Barbara Kenner, PhD,* Suresh T. Chari, MD,† David Kelsen, MD, Fishman EK et al.
    Pancreas. 2021 Mar 1;50(3):251-279

  • Artificial Intelligence and Early Detection of Pancreatic Cancer: 2020 Summative Review  
    Barbara Kenner, PhD,* Suresh T. Chari, MD,† David Kelsen, MD, Fishman EK et al.
    Pancreas. 2021 Mar 1;50(3):251-279
  • "In this context, the big data field provides a conceptual framework for analysis across the full spectrum of disease that may better capture patient subcategories, in particular when considering longitudinal disease development in a lifelong perspective. Here, variation in “healthy” diagnosis-free routes toward disease and later differences in disease comorbidities are currently of high interest. Using health care sector, socioeconomic, and consumer data, the precision medicine field works increasingly toward such a disease spectrum-wide approach. Ideally, this involves data describing healthy individuals, many of whom will later become sick—to have long-range correlations that relate to outcomes available for analysis. This notion extends the traditional disease trajectory concept into healthy life-course periods potentially enabling stratification of patient cohorts by systematically observed differences present before the onset and diagnosis of disease.”
    Artificial Intelligence and Early Detection of Pancreatic Cancer: 2020 Summative Review  
    Barbara Kenner, PhD,* Suresh T. Chari, MD,† David Kelsen, MD, Fishman EK et al.
    Pancreas. 2021 Mar 1;50(3):251-279
  • "Ultimately, it is likely that AI will transform much of the practice of medicine. AI will be used to interpret radiographs, ultrasounds, CT, and MRI, either as an adjunct to the clinician's interpretation or as the standalone reading.88 Health care organizations will use AI systems to extract and analyze electronic health record (EHR) data to better allocate staff and other resources, identify patients at risk for acute decompensation, and prevent medication errors.148 Using sensors on commodity devices such as smartphones, wearables, smart speakers, laptops, and tablets, individuals will be able to share health data during their daily lives and help generate a longitudinal personal health record, with pertinent information incorporated into their EHR. By extracting information from the EHR and incorporating data during an encounter with a patient, clinicians can be provided with a differential diagnosis in real-time with probabilities included.”
    Artificial Intelligence and Early Detection of Pancreatic Cancer: 2020 Summative Review  
    Barbara Kenner, PhD,* Suresh T. Chari, MD,† David Kelsen, MD, Fishman EK et al.
    Pancreas. 2021 Mar 1;50(3):251-279
  • "Because of the “black box” quality of many deep learning algorithms, clinicians and patients may be hesitant to depend on AI-based solutions. This fear is not unfounded. For example, it was discovered that an algorithm evaluating data from images of skin lesions was more likely to classify the lesion as malignant if a ruler was included in the photograph.149 The reticence by clinicians to embrace AI-based medical devices may also be explained by the paucity of peer-reviewed prospective studies assessing the efficacy of these systems.Finally, regulatory assessment of the effectiveness and safety of AI-based products is different from that of traditional medical devices.Regulatory agencies are working to find the best processes for determining whether an AI medical device should be cleared for clinical use.”
    Artificial Intelligence and Early Detection of Pancreatic Cancer: 2020 Summative Review  
    Barbara Kenner, PhD,* Suresh T. Chari, MD,† David Kelsen, MD, Fishman EK et al.
    Pancreas. 2021 Mar 1;50(3):251-279
  • "The ability to reliably detect very early-stage PDAC in asymptomatic patients should result in a major improvement in survival. This hypothesis is based on the observation that the prognosis for PDAC is clearly related to the pathological stage of the tumor at the time of diagnosis. Using the SEER database, Ansari et al reported that 5-year survival for patients with lymph node–negative primary PDAC less than 1-cm cancers is ~60%; with primary tumors of 2 cm or larger even without lymph node metastasis, survival was less than 20%. However, less than 1% of patients are found with primary PDAC less than 1 centimeter in size. Pancreatic ductal adenocarcinoma is diagnosed in the large majority of even stage IA patients because of symptoms, not as a result of an early detection program. The hypothesis that the earlier the stage of a PDAC, the better the outcome, is in concert with data from many other solid tumors, including breast, non–small cell lung, colorectal, prostate, and gastric cancers.”
    Artificial Intelligence and Early Detection of Pancreatic Cancer: 2020 Summative Review  
    Barbara Kenner, PhD,* Suresh T. Chari, MD,† David Kelsen, MD, Fishman EK et al.
    Pancreas. 2021 Mar 1;50(3):251-279
  • "Project Felix is a Lustgarten Foundation initiative led by Elliott Fishman at Johns Hopkins University to develop deep learning tools that can detect pancreatic tumors when they are smaller and with greater reliability than human readers alone. This effort has involved meticulous manual segmentation of thousands of abdominal CT scans to serve as a training and testing cohort, which represents the largest effort in this domain in the world. In collaboration with the computer scientist Alan Yuille. Project Felix has produced at least 17 articles on techniques to automatically detect and characterize lesions within the pancreas (https://www.ctisus.com/responsive/deep-learning/felix.asp).”
    Artificial Intelligence and Early Detection of Pancreatic Cancer: 2020 Summative Review  
    Barbara Kenner, PhD,* Suresh T. Chari, MD,† David Kelsen, MD, Fishman EK et al.
    Pancreas. 2021 Mar 1;50(3):251-279
  • "Eugene Koay from The University of Texas MD Anderson Cancer Center (MDACC) has previously characterized subtypes of PDAC on CT scans, whereby conspicuous (high delta) PDAC tumors are more likely to have aggressive biology, a higher rate of common pathway mutations, and poorer clinical outcomes compared with inconspicuous (low delta) tumors.His group has recently completed an analysis, currently under review, that shows that high-delta tumors demonstrate higher growth rates and shorter initiation times than their low-delta counterparts in the prediagnostic period. Although not strictly an AI initiative, his work serves as a rich foundation for future AI initiatives in this space. Drs Koay and Anirban Maitra at the MDACC are leading the NCI-sponsored EDRN initiative to assemble a prediagnosis pancreatic cancer cohort that could facilitate AI research into screening and early detection.”
    Artificial Intelligence and Early Detection of Pancreatic Cancer: 2020 Summative Review  
    Barbara Kenner, PhD,* Suresh T. Chari, MD,† David Kelsen, MD, Fishman EK et al.
    Pancreas. 2021 Mar 1;50(3):251-279
  • “Pancreatic cancer remains a major health problem, and only less than 20% of patients have resectable disease at the time of initial diagnosis. Systemic chemotherapy is often used in the patients with borderline resectable, locally advanced unresectable disease and metastatic disease. CT is often used to assess for therapeutic response; however, conventional imaging including CT may not correctly reflect treatment response after chemotherapy.”
    Assessment of iodine uptake by pancreatic cancer following chemotherapy using dual-energy CT.  
    Kawamoto S, Fuld MK, Laheru D, Huang P, Fishman EK.  
    Abdom Radiol (NY). 2018;43(2):445-456. 
  • "Dual-energy (DE) CT can acquire datasets at two different photon spectra in a single CT acquisition, and permits separating materials and extract iodine by applying a material decomposition algorithm. Quantitative iodine mapping may have an added value over conventional CT imaging for monitoring the treatment effects in patients with pancreatic cancer and potentially serve as a unique biomarker for treatment response. In this pictorial essay, we will review the technique for iodine quantification of pancreatic cancer by DECT and discuss our observations of iodine quantification at baseline and after systemic chemotherapy with conventional cytotoxic agents.”
    Assessment of iodine uptake by pancreatic cancer following chemotherapy using dual-energy CT.  
    Kawamoto S, Fuld MK, Laheru D, Huang P, Fishman EK.  
    Abdom Radiol (NY). 2018;43(2):445-456. 
  • “The parameters obtained using tumor segmentation software included (1) RECIST diameter (mm), (2) tumor volume (mL), (3) mean CT number of tumor (HU) at simulated weighted-average 120-kVp images, (4) iodine uptake by tumor per volume of tissue (mg/mL), and (5) normalized tumor iodine uptake (tumor iodine uptake normalized to the reference value acquired using region of interest place in the abdominal aorta at the level of the pancreatic tumor, calculated by tumor iodine uptake [mg/dL]/abdominal aortic uptake [mg/dL]).”
  • “In conclusion, iodine uptake by pancreatic adenocarcinoma using DECT may add supplemental information for assessment of treatment response, although tumor iodine uptake by pancreatic adenocarcinoma is small, and it may be difficult to apply to each case. Normalized tumor iodine uptake might be more sensitive than iodine concentration to measure treatment response. More data are necessary to confirm these observations.”
    Assessment of iodine uptake by pancreatic cancer following chemotherapy using dual-energy CT.  
    Kawamoto S, Fuld MK, Laheru D, Huang P, Fishman EK.  
    Abdom Radiol (NY). 2018;43(2):445-456.
  • Purpose: Evaluate utility of dual energy CT iodine material density images to identify preoperatively nodal positivity in pancreatic cancer patients who underwent neoadjuvant therapy.
    Conclusion: The dual energy based minimum normalized iodine value of all nodes in the surgical field on preoperative studies has modest utility in differentiating N0 from N1/2, and generally outperformed conventional features for identifying nodal metastases.
    CT features predictive of nodal positivity at surgery in pancreatic cancer patients following neoadjuvant therapy in the setting of dual energy CT.  
    Le O, Javadi S, Bhosale PR et al.  
    Abdom Radiol (NY). 2021 Jan 20. doi: 10.1007/s00261-020-02917-5. Epub ahead of print. PMID: 33471129.
  • Background: The diagnostic performance of CT for pancreatic cancer is interpreter-dependent, and approximately 40% of tumours smaller than 2 cm evade detection. Convolutional neural networks (CNNs) have shown promise in image analysis, but the networks’ potential for pancreatic cancer detection and diagnosis is unclear. We aimed to investigate whether CNN could distinguish individuals with and without pancreatic cancer on CT, compared with radiologist interpretation. Interpretation CNN could accurately distinguish pancreatic cancer on CT, with acceptable generalisability to images of patients from various races and ethnicities. CNN could supplement radiologist interpretation.
    Deep learning to distinguish pancreatic cancer tissue from non-cancerous pancreatic tissue: a retrospective study with cross-racial external validation
    Kao-Lang Liu et al.
    Lancet Digital Health 2020; 2: e303–13
  • “Findings Between Jan 1, 2006, and Dec 31, 2018, we obtained CT images. In local test set 1, CNN-based analysis had a sensitivity of 0·973, specificity of 1·000, and accuracy of 0·986 (area under the curve [AUC] 0·997 (95% CI 0·992–1·000). In local test set 2, CNN-based analysis had a sensitivity of 0·990, specificity of 0·989, and accuracy of 0·989 (AUC 0·999 [0·998–1·000]). In the US test set, CNN-based analysis had a sensitivity of 0·790, specificity of 0·976, and accuracy of 0·832 (AUC 0·920 [0·891–0·948)]. CNN-based analysis achieved higher sensitivity than radiologists did (0·983 vs 0·929, difference 0·054 [95% CI 0·011–0·098]; p=0·014) in the two local test sets combined. CNN missed three (1·7%) of 176 pancreatic cancers (1·1–1·2 cm). Radiologists missed 12 (7%) of 168 pancreatic cancers (1·0–3·3 cm), of which 11 (92%) were correctly classified using CNN. The sensitivity of CNN for tumours smaller than 2 cm was 92·1% in the local test sets and 63·1% in the US test set.”
    Deep learning to distinguish pancreatic cancer tissue from non-cancerous pancreatic tissue: a retrospective study with cross-racial external validation
    Kao-Lang Liu et al.
    Lancet Digital Health 2020; 2: e303–13
  • Findings: CNN-based analysis achieved higher sensitivity than radiologists did (0·983 vs 0·929, difference 0·054 [95% CI 0·011–0·098]; p=0·014) in the two local test sets combined. CNN missed three (1·7%) of 176 pancreatic cancers (1·1–1·2 cm). Radiologists missed 12 (7%) of 168 pancreatic cancers (1·0–3·3 cm), of which 11 (92%) were correctly classified using CNN. The sensitivity of CNN for tumours smaller than 2 cm was 92·1% in the local test sets and 63·1% in the US test set.
    Deep learning to distinguish pancreatic cancer tissue from non-cancerous pancreatic tissue: a retrospective study with cross-racial external validation
    Kao-Lang Liu et al.
    Lancet Digital Health 2020; 2: e303–13
  • “CNN can accurately differentiate pancreatic cancer from non-cancerous pancreas, and with improvements might accommodate variations in patient race and ethnicity and imaging parameters that are inevitable in real-world clinical practice. CNN holds promise for developing computer-aided detection and diagnosis tools for pancreatic cancer to supplement radiologist interpretation.”
    Deep learning to distinguish pancreatic cancer tissue from non-cancerous pancreatic tissue: a retrospective study with cross-racial external validation
    Kao-Lang Liu et al.
    Lancet Digital Health 2020; 2: e303–13
  • “In conclusion, this study provided a proof of concept that CNN can accurately distinguish pancreatic cancer on portal venous CT images. The CNN model holds promise as a compute r­aided diagnostic tool to assist radiologists and clinicians in diagnosing pancreatic cancer.”
    Deep learning to distinguish pancreatic cancer tissue from non-cancerous pancreatic tissue: a retrospective study with cross-racial external validation
    Kao-Lang Liu et al.
    Lancet Digital Health 2020; 2: e303–13
  • “Interpretation CNN could accurately distinguish pancreatic cancer on CT, with acceptable generalisability to images of patients from various races and ethnicities. CNN could supplement radiologist interpretation.”
    Deep learning to distinguish pancreatic cancer tissue from non-cancerous pancreatic tissue: a retrospective study with cross-racial external validation
    Kao-Lang Liu et al.
    Lancet Digital Health 2020; 2: e303–13
  • “Deep learning is a type of machine learning method in which algorithms are trained to perform tasks by learning patterns from data rather than by explicit programming. Deep neural networks are inspired by biological neural networks and use a matrix of interconnected nodes to mimic the function of a biologic neuron. The basic unit of an artificial neural network is a node. It takes a set of input features, multiplies these features by corresponding weights in the form of mathematical equations, and then passes the output to the next layer of nodes. The deep network architecture uses multiple layers of interconnected nodes to develop a mathematical model that best fits the data. The outputs are compared with the “ground truth,” and errors are used as feedback to adjust the weights in the network to minimize error in subsequent iterations.”
    Pancreatic Cancer Imaging: A New Look at an Old Problem
    Linda C. Chu MD, Seyoun Park, Satomi Kawamoto, Alan L. Yuille , Ralph H. Hruban, Elliot K. Fishman
    Current Problems in Diagnostic Radiology (in press)

  • Automatic detection of pancreatic ductal adenocarcinoma (PDAC) with deep learning. (Left panel) Axial IV contrast- enhanced CT image shows a hypoenhancing mass in the pancreatic body (arrow) with dilated pancreatic duct (arrowhead). (Middle panel) Manual segmentation of the tumor (red), pancreatic duct (green), and background pancreas (blue). (Right panel) Deep network prediction of tumor (red), pancreatic duct (green) and background pancreas (blue).

  • Automatic detection of pancreatic neuroendocrine tumor (PanNET) with deep learning. (Left panel) Axial IV contrast-enhanced CT image shows a subtle hyperenhancing mass within the head of the pancreas (arrow). (Middle panel) Manual segmentation of tumor (pink) and background pancreas (blue). (Right panel) Deep network prediction of tumor (pink) and background pancreas (blue).

  • Automatic detection of intraductal papillary mucinous neoplasm (IPMN) with deep learning. (Left panel) Axial IV contrast-enhanced CT image shows multiple well-circumscribed cystic lesions in the pancreas (arrow). (Middle panel) Manual segmentation of cystic tumors (yellow) and background pancreas (blue). (Right panel) Deep network prediction of cystic tumors (yellow) and background pancreas (blue).

  • A schematic illustrating the radiomics feature extraction and analysis process. Radiomics features can be classified into signal intensity, shape, texture, and filtered features (e.g., wavelets and Laplacian of Gaussian [LoG]). (Left panel) Input of imaging datasets (normal vs. abnormal) with annotation of regions of interest. (Middle panel) Extraction of radiomics features, including histogram of voxel signal intensities, shape features based on surface rendering of region of interest, and filtered features. (Right panel) The raw data are processed through feature selection to identify the most relevant features. These features can be correlated with clinical outcomes in classification tasks.
  • “Radiomics features have also been used to predict PanNET grade, one of the most important prognostic factors in predicting patient survival. Qualitative features such as ill-defined margins, heterogeneous enhancement, low- level enhancement, vascular involvement, and main pancreatic duct dilatation have been reported to be helpful features in predicting higher tumor grade. Radiomics features achieved equivalent or superior performance compared to traditional clinical and imaging features. in most, but not all studies, with higher tumor grades in the majority of these studies, and with worse progression free survival. The addition of radiomics features to traditional CT features may improve the accuracy of PanNET grade prediction.”
    Pancreatic Cancer Imaging: A New Look at an Old Problem
    Linda C. Chu MD, Seyoun Park, Satomi Kawamoto, Alan L. Yuille , Ralph H. Hruban, Elliot K. Fishman
    Current Problems in Diagnostic Radiology (in press)
  • “Radiomics features have also been reported to be predictive of overall survival in patients with unresectable or locally advanced PDAC. Not surprisingly, the presence of metastatic disease at presentation was the most predictive of poor overall survival. factors. Radiomics features associated with tumor heterogeneity were also found to be poor prognostic factors. There is speculation that tumor hypoattenuation may reflect areas of hypoxic necrosis, which may suggest more aggressive underlying tumor biology as well as impaired response to chemotherapy and radiation therapy. Low attenuation may also be evidence of extensive venous invasion by the cancer.”
    Pancreatic Cancer Imaging: A New Look at an Old Problem
    Linda C. Chu MD, Seyoun Park, Satomi Kawamoto, Alan L. Yuille , Ralph H. Hruban, Elliot K. Fishman
    Current Problems in Diagnostic Radiology (in press)
  • "While VR uses a simple ray cast method to generate 3D images, CR uses Monte Carlo path tracing that takes direct and indirect illumination into account. With CR, each pixel is formed by thousands of rays passing through the volumetric dataset and includes effects of light rays from scatter and from voxels adjacent to the paths of the rays. CR has the potential to more accurately depict complex anatomy. When applied to pancreatic imaging, CR can be used to accentuate focal textural change and enhance appreciation of internal architecture (e.g., septations, mural nodules) to improve their visualization and assist in tumor classification.”
    Pancreatic Cancer Imaging: A New Look at an Old Problem
    Linda C. Chu MD, Seyoun Park, Satomi Kawamoto, Alan L. Yuille , Ralph H. Hruban, Elliot K. Fishman
    Current Problems in Diagnostic Radiology (in press)
  • “Augmented reality (AR) is another advanced visualization technique that may improve treatment planning as well as intraoperative navigation. AR can superimpose holographic representations of imaging data onto the real-world environment through the use of handheld displays or head-mounted see-through glasses. Preliminary studies on AR applications in pancreatic surgery have shown that these holographic images may be helpful in proper selection of resection margin and in defining the spatial relationship between the tumor and adjacent organs and vasculature. AR surgical navigation may be particularly valuable during laparoscopic or robotic-assisted surgery due to limited visualization and tactile feedback during surgery.”
    Pancreatic Cancer Imaging: A New Look at an Old Problem
    Linda C. Chu MD, Seyoun Park, Satomi Kawamoto, Alan L. Yuille , Ralph H. Hruban, Elliot K. Fishman
    Current Problems in Diagnostic Radiology (in press)
  • “Although radiomics has the potential to provide personalized imaging biomarkers for risk stratification and prognostication, there are currently no standards for image acquisition or feature extraction. Published studies differ regarding image acquisition, segmentation, and the types and numbers of radiomics features that were extracted. Each of these factors can affect the reproducibility of radiomics signatures. Although some of this variability may be mitigated through image compensation methods,86 further work is needed to define the optimal image acquisition and feature extraction protocols. While these preliminary studies appear promising, many of them lack internal and external validation to ensure the generalizability of the results. Several studies also lack head-to-head comparisons between radiomics and expert radiologists to demonstrate the incremental clinical benefit of radiomics as opposed to current standard of care. The potential of advanced visualization techniques in guiding patient management has been explored in small single-center case-series, and these results also require further validation.”
    Pancreatic Cancer Imaging: A New Look at an Old Problem
    Linda C. Chu MD, Seyoun Park, Satomi Kawamoto, Alan L. Yuille , Ralph H. Hruban, Elliot K. Fishman
    Current Problems in Diagnostic Radiology (in press)
  • “Pancreatic ductal adenocarcinoma (PDAC) segmentation is one of the most challenging tumor segmentation tasks, yet critically important for clinical needs. Previous work on PDAC segmentation is limited to the moderate amounts of annotated patient images (n<300) from venous or venous+arterial phase CT scans. Based on a new self-learning framework, we propose to train the PDAC segmentation model using a much larger quantity of patients (n≈1,000), with a mix of annotated and un- annotated venous or multi-phase CT images. Pseudo annotations are generated by combining two teacher models with different PDAC segmentation specialties on unannotated images, and can be further refined by a teaching assistant model that identifies associated vessels around the pancreas.”
    Robust Pancreatic Ductal Adenocarcinoma Segmentation with Multi-Institutional Multi-Phase Partially-Annotated CT Scans
    Ling Zhang et al.
    arXiv: August 2020 (in press)
  • “Fully automated and accurate segmentation of pancreatic ductal adenocarcinoma (PDAC) is one of the most challenging tumor segmentation tasks, in the aspects of complex abdominal structures, large variations in morphology and appearance, low image contrast and fuzzy/uncertain boundary, etc. Previous studies introduce the cascade UNet for segmenting venous phase CT and hyperpairing network for segmenting venous+arterial phases CT and achieving mean Dice scores of 0.52 and 0.64, respectively. By incorporating nnUNet into a new self-learning framework with two teachers and one teaching assistant to segment three-phases of CT scans, our method reaches a Dice coefficient of 0.71, similar to the inter-observer variability between radiologists. This provides promise that a radiologist-level performance for accurate PDAC tumor segmentation in multi-phase CT imaging can be achieved through our computerized method.”
    Robust Pancreatic Ductal Adenocarcinoma Segmentation with Multi-Institutional Multi-Phase Partially-Annotated CT Scans
    Ling Zhang et al.
    arXiv: August 2020 (in press)

  • Robust Pancreatic Ductal Adenocarcinoma Segmentation with Multi-Institutional Multi-Phase Partially-Annotated CT Scans
    Ling Zhang et al.
    arXiv: August 2020 (in press)
  • Background: To identify preoperative computed tomography radiomics texture features which correlate with resection margin status and prognosis in resected pancreatic head adenocarcinoma.
    Methods: Improved prognostication methods utilizing novel non-invasive radiomic techniques may accurately predict resection margin status preoperatively. In an ongoing concerning pancreatic head adenocarcinoma, the venous enhanced CT images of 86 patients who underwent pancreaticoduodenectomy were selected, and the resection margin (>1 mm or ≤1 mm) was identified by pathological examination. Three regions of interests (ROIs) were then taken from superior to inferior facing the superior mesenteric vein and artery. Subsequent Laplacian-Dirichlet based texture analysis methods extracting algorithm of texture features within ROIs were analyzed and assessed in relation to patient prognosis.
    Results: Patients with >1 mm resection margin had an overall improved survival compared to ≤1 mm (P < 0.05). Distance 1 and 2 of Gray level co-occurrence matrix, high Gray-level run emphasis of run-length matrix and average of wavelet transform (all P < 0.05) were correlated with resection margin status (Area under the curve was 0.784, sensitivity was 75% and specicity was 79%). The energy of wavelet transform, the measure of smoothness of histogram and the variance in 2 direction of Gabor transform are independent predictors of overall survival prognosis, independent of resection margin.
    Conclusions: Resection margin status (>1 mm vs ≤1 mm) is a key prognostic factor in pancreatic adenocarcinoma and CT radiomic analysis have the potential to predict resection margin status preoperatively, and the radiomic labels may improve selection neoadjucant therapy.
    Radiomics Signatures of Computed Tomography Imaging for Predicting Resection Margin Status in Pancreatic Head Adenocarcinoma
    Jinheng Liu et al.
    BMC Surgery (in press)
  • Results: Patients with >1 mm resection margin had an overall improved survival compared to ≤1 mm (P < 0.05). Distance 1 and 2 of Gray level co-occurrence matrix, high Gray-level run emphasis of run-length matrix and average lter of wavelet transform (all P < 0.05) were correlated with resection margin status (Area under the curve was 0.784, sensitivity was 75% and specificity was 79%). The energy of wavelet transform, the measure of smoothness of histogram and the variance in 2 direction of Gabor transform are independent predictors of overall survival prognosis, independent of resection margin.
    Conclusions: Resection margin status (>1 mm vs ≤1 mm) is a key prognostic factor in pancreatic adenocarcinoma and CT radiomic analysis have the potential to predict resection margin status preoperatively, and the radiomic labels may improve selection neoadjucant therapy.
    Radiomics Signatures of Computed Tomography Imaging for Predicting Resection Margin Status in Pancreatic Head Adenocarcinoma
    Jinheng Liu et al.
    BMC Surgery (in press)
  • Background: To identify preoperative computed tomography radiomics texture features which correlate with resection margin status and prognosis in resected pancreatic head adenocarcinoma.
    Methods: Improved prognostication methods utilizing novel non-invasive radiomic techniques may accurately predict resection margin status preoperatively. In an ongoing concerning pancreatic head adenocarcinoma, the venous enhanced CT images of 86 patients who underwent pancreaticoduodenectomy were selected, and the resection margin (>1 mm or ≤1 mm) was identified by pathological examination. Three regions of interests (ROIs) were then taken from superior to inferior facing the superior mesenteric vein and artery. Subsequent Laplacian-Dirichlet based texture analysis methods extracting algorithm of texture features within ROIs were analyzed and assessed in relation to patient prognosis.
    Radiomics Signatures of Computed Tomography Imaging for Predicting Resection Margin Status in Pancreatic Head Adenocarcinoma
    Jinheng Liu et al.
    BMC Surgery (in press)
  • “Radiomic texture analysis of pre-operative enhanced CT images can be used for accurate preoperative assessment of resection margins in patients with pancreatic ahead adenocarcinoma providing clinicians alongside patients a more non-invasive means of perioperative prognostication to guide management.”
    Radiomics Signatures of Computed Tomography Imaging for Predicting Resection Margin Status in Pancreatic Head Adenocarcinoma
    Jinheng Liu et al.
    BMC Surgery (in press)

  • Radiomics Signatures of Computed Tomography Imaging for Predicting Resection Margin Status in Pancreatic Head Adenocarcinoma
    Jinheng Liu et al.
    BMC Surgery (in press)

  • Radiomics Signatures of Computed Tomography Imaging for Predicting Resection Margin Status in Pancreatic Head Adenocarcinoma
    Jinheng Liu et al.
    BMC Surgery (in press)
  • “PDAC is the most common pancreatic malig- nancy, accounting for more than 85% of pancreatic tumors. It is typically a disease of elderly patients, with a mean age at presentation of 68 years and a male-to-female ratio of 1.6:1. After colorectal cancer, it is the second most common cancer of the digestive system in the United States, and its incidence is rising sharply.The development of pancreatic cancer is strongly related to smoking, family history, obesity, long-standing diabetes, and chronic pancreatitis. Early stages of PDAC are clinically silent. Abdominal pain is the most frequently reported clinical symptom, even when the tumor is small (<2 cm).”
    Pancreatic Ductal Adenocarcinoma and Its Variants: Pearls and Perils
    Schawkat K et al.
    RadioGraphics 2020; 40:0000–0000
  • "With the development of AI and all its potential wonders in terms of increasing the accuracy of our diagnostic capabilities and potentially improving patient care, we must also be concerned about the potential dark side by bad actors. The sooner organized radiology and organized medicine address these issues with clarity, the more stable and protected the health care system and our patients will be from those intent on creating harm and havoc by abusing AI. The acceleration of data sharing during the current pandemic exposes critical vulnerabilities in data security. It reminds us of the pervasive threat that bad actors can and will exploit any technology for their selfish gains. Doing nothing is not a viable strategy, but acting in a concerted effort will lead us to the protection we need and is important as we push AI development over the next several years.”
    The Potential Dangers of Artificial Intelligence for Radiology and Radiologists
    Linda C. Chu, MD, Anima Anandkumar, PhD, Hoo Chang Shin, PhD, Elliot K. Fishman, MD
    JACR (in press)
  • “Pancreatic cancer continues to be one of the deadliest malignancies and is the third leading cause of cancer-related mortality in the United States. Based on several models, it is projected to become the second leading cause of cancer-related deaths by 2030. Although the overall survival rate for patients diagnosed with pancreatic cancer is less than 10%, survival rates are increasing in those whose cancers are detected at an early stage, when intervention is possible. There are, however, no reli- able biomarkers or imaging technology that can detect early-stage pancreatic cancer or accurately identify precursors that are likely to progress to malignancy.”
    Prediagnostic Image Data, Artificial Intelligence, and Pancreatic Cancer A Tell-Tale Sign to Early Detection
    Matthew R. Young et al.
    Pancreas 2020;49: 882–886
  • "The challenge now is to develop imaging biomarkers and models that can further improve sensitivity for the detection of early-stage PDACs and aggressive neoplasms while mitigating diagnostic uncertainty in evaluation of premalignant abnormalities. Augmented reality, artificial intelligence (AI), and related computa- tional techniques can uncover these subtle patterns, improve image interpretation, and streamline diagnostic workflows.”
    Prediagnostic Image Data, Artificial Intelligence, and Pancreatic Cancer A Tell-Tale Sign to Early Detection
    Matthew R. Young et al.
    Pancreas 2020;49: 882–886
  • "Currently, identification of localized pancreatic cancer is mostly incidental as localized pancreatic cancer is asymptomatic. What is urgently needed are minimally invasive screening strategies with a high clinical sensitivity and specificity to identity early-stage cancer and improve these grim statistics. To this end, it is particularly important to develop tests that have high specificity because a false-positive test may trigger unnecessary invasive procedures, which add their own risk of morbidity and mortality.”
    Prediagnostic Image Data, Artificial Intelligence, and Pancreatic Cancer A Tell-Tale Sign to Early Detection
    Matthew R. Young et al.
    Pancreas 2020;49: 882–886
  • There are many challenges that need to be mitigated in the development of an image repository to enable AI system development. These include the following:
    (1) What are the requirements for defining image annotation? 
    (2) What are the main concerns with depositing patient imaging data?
    (3) What are the definitions of an AI-specific clinical use cases?
    (4) What are the benefits and drawbacks of alternative data sharing in facilitating AI development? 

  • Prediagnostic Image Data, Artificial Intelligence, and Pancreatic Cancer A Tell-Tale Sign to Early Detection
    Matthew R. Young et al.
    Pancreas 2020;49: 882–886

  • Prediagnostic Image Data, Artificial Intelligence, and Pancreatic Cancer A Tell-Tale Sign to Early Detection
    Matthew R. Young et al.
    Pancreas 2020;49: 882–886
  • “The AI-driven diagnostic software has the potential to trans- form early detection of pancreatic cancer by improving accuracy and consistency of interpretation of radiologic imaging scans and related patient data. The development of reproducible AI systems requires access to current, large, diverse, and multisite data sets, which are subject to numerous data sharing limitations. Future efforts are likely to involve alternative data sharing solutions to enable the development of both public and private AI-ready data resources. Early detection of pancreatic cancer represents an attractive AI use case, well matched to benefit from the MTD challenge approach. This approach will significantly expand the use of sensitive data to improve early detection of pancreatic cancer and lay the foundation for the development of federated architectures for real-world medical data in general.”
    Prediagnostic Image Data, Artificial Intelligence, and Pancreatic Cancer A Tell-Tale Sign to Early Detection
    Matthew R. Young et al.
    Pancreas 2020;49: 882–886
  • Purpose: The purpose of this study was to determine whether computed tomography (CT)-based machine learning of radiomics features could help distinguish autoimmune pancreatitis (AIP) from pancreatic ductal adenocarcinoma (PDAC).
    Results: The pancreas was diffusely involved in 37 (37/89; 41.6%) patients with AIP and not diffusely in 52(52/89; 58.4%) patients. Using machine learning, 95.2% (59/62; 95% confidence interval [CI]: 89.8–100%),83.9% (52:67; 95% CI: 74.7–93.0%) and 77.4% (48/62; 95% CI: 67.0–87.8%) of the 62 test patients werecorrectly classified as either having PDAC or AIP with thin-slice venous phase, thin-slice arterial phase, and thick-slice venous phase CT, respectively. Three of the 29 patients with AIP (3/29; 10.3%) were incorrectly classified as having PDAC but all 33 patients with PDAC (33/33; 100%) were correctly classified with thin-slice venous phase with 89.7% sensitivity (26/29; 95% CI: 78.6–100%) and 100% specificity (33/33;95% CI: 93–100%) for the diagnosis of AIP, 95.2% accuracy (59/62; 95% CI: 89.8–100%) and area under the curve of 0.975 (95% CI: 0.936–1.0).
    Conclusions: Radiomic features help differentiate AIP from PDAC with an overall accuracy of 95.2%.
  • Purpose: The purpose of this study was to determine whether computed tomography (CT)-based machine learning of radiomics features could help distinguish autoimmune pancreatitis (AIP) from pancreatic ductal adenocarcinoma (PDAC).
    Conclusions: Radiomic features help differentiate AIP from PDAC with an overall accuracy of 95.2%.
    Differentiating autoimmune pancreatitis from pancreatic ductal adenocarcinoma with CT radiomics features
    S. Park, L.C. Chu, R.H. Hruban, Vogelstein, K.W. Kinzler, A.L. Yuille, Fouladi, S. Shayesteh, S. Ghandili, C.L. Wolfgang, R. Burkhart, J. He, E.K. Fishman, S. Kawamoto
    Diagnostic and Interventional Imaging (in press)
  • •CT radiomics differentiates AIP from PDAC with 89.7% sensitivity and 100% specificity.
    •Thin slice CT radiomics better differentiates AIP from PDAC than thick slice CT radiomics.
    •Venous phase CT radiomics better differentiates AIP from PDAC than arterial phase radiomics.
    Differentiating autoimmune pancreatitis from pancreatic ductal adenocarcinoma with CT radiomics features
    S. Park, L.C. Chu, R.H. Hruban, Vogelstein, K.W. Kinzler, A.L. Yuille, Fouladi, S. Shayesteh, S. Ghandili, C.L. Wolfgang, R. Burkhart, J. He, E.K. Fishman, S. Kawamoto
    Diagnostic and Interventional Imaging (in press)
  • “AIP has clinical and imaging features that overlap with those of pancreatic ductal adenocarcinoma (PDAC) and can pose a significant diagnostic dilemma even for experienced radiologists . The management of these two conditions is markedly different. Patients with AIP are initially treated with oral corticosteroids, while patients with PDAC are treated with a combination of surgical resection and chemotherapy. The most common presentation of AIP is obstructive jaundice and pancreatic enlargement, which mimics that of PDAC and 2–6% of patients undergoing surgical resection for suspected pancreatic cancer are actually diagnosed with AIP upon histopathological analysis. Computed tomography (CT) plays an important role in the evaluation of suspected pancreatic cancer, and is often the initial diagnostic imaging modality. It is of utmost importance to correctly differentiate AIP from PDAC early in the disease process so as to administer the proper treatment and avoid unnecessary pancreatic resections in patients with AIP.”
    Differentiating autoimmune pancreatitis from pancreatic ductal adenocarcinoma with CT radiomics features
    S. Park, L.C. Chu, R.H. Hruban, Vogelstein, K.W. Kinzler, A.L. Yuille, Fouladi, S. Shayesteh, S. Ghandili, C.L. Wolfgang, R. Burkhart, J. He, E.K. Fishman, S. Kawamoto
    Diagnostic and Interventional Imaging (in press)

  • Differentiating autoimmune pancreatitis from pancreatic ductal adenocarcinoma with CT radiomics features
    S. Park, L.C. Chu, R.H. Hruban, Vogelstein, K.W. Kinzler, A.L. Yuille, Fouladi, S. Shayesteh, S. Ghandili, C.L. Wolfgang, R. Burkhart, J. He, E.K. Fishman, S. Kawamoto
    Diagnostic and Interventional Imaging (in press)
  • "In conclusion, radiomics analysis of CT images is reasonably accurate in differentiating AIP from PDAC. Using such features, in combination with clinical and standard radiologic analyses, may improve the accuracy of AID diagnosis and spare patients’ unnecessary surgical procedure.”
    Differentiating autoimmune pancreatitis from pancreatic ductal adenocarcinoma with CT radiomics features
    S. Park, L.C. Chu, R.H. Hruban, Vogelstein, K.W. Kinzler, A.L. Yuille, Fouladi, S. Shayesteh, S. Ghandili, C.L. Wolfgang, R. Burkhart, J. He, E.K. Fishman, S. Kawamoto
    Diagnostic and Interventional Imaging (in press)
  • "Our results showed that by combining radiomics features, AIP could be distinguished from PDAC with a sensitivity of 89.7% and a specificity of 100%, and an overall accuracy of 95.2%. Among 3 patients with focal AIP were falsely classified as PDAC using radiomics features, two patients had focal AIP in the head with a plastic stent in the common bile duct, which can sensitively affect to the quantitative feature computation. In our study, the accuracy was higher than that in a previous study that evaluated CT to differentiate AIP from PDAC based on morphological features. In that study, the mean accuracies for diagnosing AIP and PDAC were 68% and 83%, respectively. In our study, AIP was considered as a diagnosis or differential diagnosis by the radiologists in only in 67% of patients with AIP not already suspected to be AIP at the time of CT examination.”
    Differentiating autoimmune pancreatitis from pancreatic ductal adenocarcinoma with CT radiomics features
    S. Park, L.C. Chu, R.H. Hruban, Vogelstein, K.W. Kinzler, A.L. Yuille, Fouladi, S. Shayesteh, S. Ghandili, C.L. Wolfgang, R. Burkhart, J. He, E.K. Fishman, S. Kawamoto
    Diagnostic and Interventional Imaging (in press)
  • “We found that radiomics features were better at distinguishing AIP from PDAC using venous phase CT images than using arterial phase images. We also performed radiomics analysis on both thin- and thick-slice reconstructions. We found that thin-slice CT based radiomics signature had better diagnostic performance than thick-slice, as reported in pulmonary nodules and lung cancer in prior studies.”
    Differentiating autoimmune pancreatitis from pancreatic ductal adenocarcinoma with CT radiomics features
    S. Park, L.C. Chu, R.H. Hruban, Vogelstein, K.W. Kinzler, A.L. Yuille, Fouladi, S. Shayesteh, S. Ghandili, C.L. Wolfgang, R. Burkhart, J. He, E.K. Fishman, S. Kawamoto
    Diagnostic and Interventional Imaging (in press)
  • Purpose: The purpose of this study is to evaluate diagnostic performance of a commercially available radiomics research prototype vs. an in-house radiomics software in the binary classification of CT images from patients with pancreatic ductal adenocarcinoma (PDAC) vs. healthy controls.
    Conclusion: Commercially available and in-house radiomics software achieve similar diagnostic performance, which may lower the barrier of entry for radiomics research and allow more clinician-scientists to perform radiomics research.
    Diagnostic performance of commercially available vs. in‐house radiomics software in classification of CT images from patients with pancreatic ductal adenocarcinoma vs. healthy controls
    Linda C. Chu · Berkan Solmaz · Seyoun Park · Satomi Kawamoto · Alan L. Yuille · Ralph H. Hruban · Elliot K. Fishman
    Abdominal Radiology https://doi.org/10.1007/s00261-020-02556-w
  • “Results: When 40 radiomics features were used in the random forest classification, in-house software achieved superior sensitivity (1.00) and accuracy (0.992) compared to the commercially available research prototype (sensitivity = 0.950, accuracy = 0.968). When the number of features was reduced to five features, diagnostic performance of the in-house soft- ware decreased to sensitivity (0.950), specificity (0.923), and accuracy (0.936). Diagnostic performance of the commercially available research prototype was unchanged.”
    Diagnostic performance of commercially available vs. in‐house radiomics software in classification of CT images from patients with pancreatic ductal adenocarcinoma vs. healthy controls
    Linda C. Chu · Berkan Solmaz · Seyoun Park · Satomi Kawamoto · Alan L. Yuille · Ralph H. Hruban · Elliot K. Fishman
    Abdominal Radiology https://doi.org/10.1007/s00261-020-02556-w
  • “Radiomics has the potential to generate imaging biomarkers for classification and prognostication. Technical parameters from image acquisition to feature extraction and analysis have the potential to affect radiomics features. The current study used the same CT images with manual segmentation on both a commercially available research prototype and in-house radiomics software to control for any variability at the image acquisition step and compared the diagnostic performance of the two programs. Both programs achieved similar diagnostic performance in the binary classification of CT images from patients with PDAC and healthy control subjects, despite differences in the radiomics fea-tures they employed (854 features in commercial program vs. 478 features in in-house program).”
    Diagnostic performance of commercially available vs. in‐house radiomics software in classification of CT images from patients with pancreatic ductal adenocarcinoma vs. healthy controls
    Linda C. Chu · Berkan Solmaz · Seyoun Park · Satomi Kawamoto · Alan L. Yuille · Ralph H. Hruban · Elliot K. Fishman
    Abdominal Radiology https://doi.org/101007/s00261-020-02556-w
  • "This is reassuring that even though there may be variations in the computed values for radiomics features, the differences do not seem to significantly impact the overall diagnostic performance of the constellation of radiomics features. This is important for the broader implementation of radiomics research. Currently, many radiomics studies have been performed using proprietary in-house software, which requires in-house expertise in computer science, a luxury that only a few academic centers can afford. The results of this study show that commercially available radiomics software may be a viable alternative to in-house computer science expertise, which can lower the barrier of entry for radiomics research and allow clinicians to validate findings of the published studies with their own local datasets.”
    Diagnostic performance of commercially available vs. in‐house radiomics software in classification of CT images from patients with pancreatic ductal adenocarcinoma vs. healthy controls
    Linda C. Chu · Berkan Solmaz · Seyoun Park · Satomi Kawamoto · Alan L. Yuille · Ralph H. Hruban · Elliot K. Fishman
    Abdominal Radiology https://doi.org/101007/s00261-020-02556-w
  • “This study showed that a commercially available radiomics software may be able to achieve similar diagnostic performance as an in-house radiomics software. The results obtained from one radiomics software may be transferrable to another system. Availability of commercial radiom ics software may lower the barrier of entry for radiomics research and allow more researchers to engage in this exciting area of research.”
    Diagnostic performance of commercially available vs. in‐house radiomics software in classification of CT images from patients with pancreatic ductal adenocarcinoma vs. healthy controls
    Linda C. Chu · Berkan Solmaz · Seyoun Park · Satomi Kawamoto · Alan L. Yuille · Ralph H. Hruban · Elliot K. Fishman
    Abdominal Radiology https://doi.org/101007/s00261-020-02556-w
  • “Accurate and robust segmentation of abdominal organs on CT is essential for many clinical applications such as computer-aided diagnosis and computer-aided surgery. But this task is challenging due to the weak boundaries of organs, the complexity of the background, and the variable sizes of different organs. To address these challenges, we introduce a novel framework for multi-organ segmentation of abdominal regions by using organ-attention networks with reverse connections (OAN-RCs) which are applied to 2D views, of the 3D CT volume, and output estimates which are combined by statistical fusion exploiting structural similarity. More specifically, OAN is a two-stage deep convolutional network, where deep net- work features from the first stage are combined with the original image, in a second stage, to reduce the complex background and enhance the discriminative information for the target organs.”
    Abdominal multi-organ segmentation with organ-attention networks and statistical fusion
    Wang Y, Zhou Y, Shen W, Park S, Fishman EK, Yuille AL.
    Med Image Anal. 2019 Jul;55:88-102. doi: 10.1016/j.media.2019.04.005. Epub 2019 Apr 18.
  • "First, many abdominal organs have weak boundaries between spatially adjacent structures on CT, e.g. between the head of the pancreas and the duodenum. In addition, the entire CT volume includes a large variety of different complex structures. Morpho- logical and topological complexity includes anatomically connected structures such as the gastrointestinal (GI) track (stomach, duodenum, small bowel and colon) and vascular structures. The correct anatomical borders between connected structures may not be always visible in CT, especially in sectional images (i.e., 2D slices), and may be indicated only by subtle texture and shape change, which causes uncertainty even for human experts. This makes it hard for deep networks to distinguish the target organs from the complex background.”
    Abdominal multi-organ segmentation with organ-attention networks and statistical fusion
    Wang Y, Zhou Y, Shen W, Park S, Fishman EK, Yuille AL.
    Med Image Anal. 2019 Jul;55:88-102. doi: 10.1016/j.media.2019.04.005. Epub 2019 Apr 18.
  • “In general, 3D deep networks face far greater complex challenges than 2D deep networks. Both approaches rely heavily on graphics processing units (GPUs) but these GPUs have limited memory size which makes it difficult when dealing with full 3D CT volumes compared to 2D CT slices (which require much less memory). In addition, 3D deep networks typically require many more parameters than 2D deep networks and hence require much more training data, unless they are re- stricted to patches.”
    Abdominal multi-organ segmentation with organ-attention networks and statistical fusion
    Wang Y, Zhou Y, Shen W, Park S, Fishman EK, Yuille AL.
    Med Image Anal. 2019 Jul;55:88-102. doi: 10.1016/j.media.2019.04.005. Epub 2019 Apr 18.

  • Abdominal multi-organ segmentation with organ-attention networks and statistical fusion
    Wang Y, Zhou Y, Shen W, Park S, Fishman EK, Yuille AL.
    Med Image Anal. 2019 Jul;55:88-102. doi: 10.1016/j.media.2019.04.005. Epub 2019 Apr 18.
  • “In this paper, we proposed a novel framework for multi- organ segmentation using OAN-RCs with statistical fusion exploit- ing structural similarity. Our two-stage organ-attention network reduces uncertainties at weak boundaries, focuses attention on or- gan regions with simple context, and adjusts FCN error by training the combination of original images and OAMs. Reverse connections deliver abstract level semantic information to lower layers so that hidden layers can be assisted to contain more semantic information and give good results even for small organs.”
    Abdominal multi-organ segmentation with organ-attention networks and statistical fusion
    Wang Y, Zhou Y, Shen W, Park S, Fishman EK, Yuille AL.
    Med Image Anal. 2019 Jul;55:88-102. doi: 10.1016/j.media.2019.04.005. Epub 2019 Apr 18.

  • Abdominal multi-organ segmentation with organ-attention networks and statistical fusion
    Wang Y, Zhou Y, Shen W, Park S, Fishman EK, Yuille AL.
    Med Image Anal. 2019 Jul;55:88-102. doi: 10.1016/j.media.2019.04.005. Epub 2019 Apr 18.

  • Abdominal multi-organ segmentation with organ-attention networks and statistical fusion
    Wang Y, Zhou Y, Shen W, Park S, Fishman EK, Yuille AL.
    Med Image Anal. 2019 Jul;55:88-102. doi: 10.1016/j.media.2019.04.005. Epub 2019 Apr 18.
  • “In addition to traditional methods, cinematic rendering (CR) as a novel 3D rendering technique can be used to generate photorealistic with more accurate information regarding the anatomical details. CR can assist clinicians to visualize precisely the extent of tumor vascular invasion, which might be critical for surgical planning; however, the feasibility of this method and other novel techniques in routine clinical practice is yet to be studied.”
    Pitfalls in the MDCT of pancreatic cancer: strategies for minimizing errors
    Arya Haj‐Mirzaian · Satomi Kawamoto · Atif Zaheer · Ralph H. Hruban · Elliot K. Fishman · Linda C. Chu
    Abdominal Radiology 2020 (in press)
  • Purpose: The purpose of this study was to report procedures developed to annotate abdominal computed tomography (CT) images from subjects without pancreatic disease that will be used as the input for deep convolutional neural networks (DNN) for development of deep learning algorithms for automatic recognition of a normal pancreas.
    Results: A total of 1150 dual-phase CT datasets from 575 subjects were annotated. There were 229 men and 346 women (mean age: 45 ± 12 years; range: 18—79 years). The mean intra- observer intra-subject dual-phase CT volume difference of all annotated structures was 4.27 mL (7.65%). The deep network prediction for multi-organ segmentation showed high fidelity with 89.4% and 1.29 mm in terms of mean Dice similarity coefficients and mean surface distances, respectively.
    Annotated normal CT data of the abdomen for deep learning: Challenges and strategies for implementation
    S. Park, L.C. Chu, E.K. Fishman, A.L. Yuille, B. Vogelstein,, K.W. Kinzler et al
    Diagn Interv Imaging. 2020 Jan;101(1):35-44.
  • “Conclusions: A reliable data collection/annotation process for abdominal structures was devel- oped. This process can be used to generate large datasets appropriate for deep learning.”
    Annotated normal CT data of the abdomen for deep learning: Challenges and strategies for implementation
    S. Park, L.C. Chu, E.K. Fishman, A.L. Yuille, B. Vogelstein,, K.W. Kinzler et al
    Diagn Interv Imaging. 2020 Jan;101(1):35-44.
  • Annotated normal CT data of the abdomen for deep learning: Challenges and strategies for implementation S. Park, L.C. Chu, E.K. Fishman, A.L. Yuille, B. Vogelstein,, K.W. Kinzler et al Diagn Interv Imaging. 2020 Jan;101(1):35-44.
  • Annotated normal CT data of the abdomen for deep learning: Challenges and strategies for implementation
    S. Park, L.C. Chu, E.K. Fishman, A.L. Yuille, B. Vogelstein,, K.W. Kinzler et al
    Diagn Interv Imaging. 2020 Jan;101(1):35-44.

  • “In conclusion, we developed a reliable and unique data collection and annotation process for abdominal structures using volumetric CT. The collected data can be used to train the deep learning network for automated recognition of normal abdominal organs. The success of this effort was dependent on a multidisciplinary team including radiologists, computer scientists, oncologists, and pathologists that have worked closely together. Pathologists confirmed that the pancreas in all subjects were normal without pancreatic neoplasms or other pathology. Oncologists provided expert guidance in experimental deign and data analysis.”
    Annotated normal CT data of the abdomen for deep learning: Challenges and strategies for implementation
    S. Park, L.C. Chu, E.K. Fishman, A.L. Yuille, B. Vogelstein,, K.W. Kinzler et al
    Diagn Interv Imaging. 2020 Jan;101(1):35-44.

  • Assessing Radiology Research on Artificial Intelligence:
    A Brief Guide for Authors, Reviewers, and Readers—From the Radiology Editorial Board
    David A.Bluemke et al.
    Radiology 2019; (in press) https://doi.org/10.1148/radiol.2019192515

  • Application of Deep Learning to Pancreatic Cancer Detection: Lessons Learned From Our Initial Experience.
    Chu LC, Park S, Kawamoto S, Wang Y, Zhou Y, Shen W, Zhu Z, Xia Y, Xie L, Liu F, Yu Q, Fouladi DF, Shayesteh S, Zinreich E, Graves JS, Horton KM, Yuille AL, Hruban RH, Kinzler KW, Vogelstein B, Fishman EK.
    J Am Coll Radiol. 2019 Sep;16(9 Pt B):1338-1342
  • “There is a common perception that one can simply provide any number of unprocessed cases to the computer, and AI can then easily perform the discovery or classification task. This approach is referred to as unsupervised learning, in which the deep-learning algorithm is presented with unlabeled data and learns to group the data by similarities or differences. Although this approach is plausible, complex image analysis, such as the detection of pancreatic cancer, may require supervised learning to achieve acceptable results.”
    Application of Deep Learning to Pancreatic Cancer Detection: Lessons Learned From Our Initial Experience.
    Chu LC, Park S, Kawamoto S, et al
    J Am Coll Radiol. 2019 Sep;16(9 Pt B):1338-1342
  • In supervised learning, the algorithm is provided with labeled data, referred to as ground truth, which is used as feedback to improve the algorithm during each iteration. The degree of data labeling can range from a per case level of normal versus abnormal to more detailed labeling in which the boundaries of each region of interest are drawn on the image on every image slice; this boundary drawing is referred to as “segmentation.” Because we have chosen to tackle a difficult AI application, we decided that supervised learning with high- quality input data would yield the best chance of success.
    Application of Deep Learning to Pancreatic Cancer Detection: Lessons Learned From Our Initial Experience.
    Chu LC, Park S, Kawamoto S, et al
    J Am Coll Radiol. 2019 Sep;16(9 Pt B):1338-1342

  • Application of Deep Learning to Pancreatic Cancer Detection: Lessons Learned From Our Initial Experience.
    Chu LC, Park S, Kawamoto S, et al
    J Am Coll Radiol. 2019 Sep;16(9 Pt B):1338-1342

  • Application of Deep Learning to Pancreatic Cancer Detection: Lessons Learned From Our Initial Experience.
    Chu LC, Park S, Kawamoto S, et al
    J Am Coll Radiol. 2019 Sep;16(9 Pt B):1338-1342
  • “Our initial decision to train the deep network to recognize all major abdominal organs instead of focusing on the pancreas proved to be a wise investment of time and resources. As we reviewed the false positives, the deep network occasionally predicted the duodenum or jejunum as an exophytic tumor. This was especially problematic in thin patients with poor fat planes. As we trained the deep network to recognize and segment the major abdominal organs, we were able to use this algorithm to prune out false- positive predictions that overlapped with other organs.”
    Application of Deep Learning to Pancreatic Cancer Detection: Lessons Learned From Our Initial Experience.
    Chu LC, Park S, Kawamoto S, et al
    J Am Coll Radiol. 2019 Sep;16(9 Pt B):1338-1342
  • “In the future, we envision that that AI system for automatic PDAC detection will be seamlessly integrated into the radiology workflow as a “second reader,” similar to how computer-aided diagnosis operates in mammographic screening. The AI system will directly receive the CT data sets from the PACS, automatically segment the abdominal organs, and annotate any suspicious pancreatic pathology. These annotated cases will be sent back to the PACS for the radiologist to review. The “second reader” can improve diagnostic confidence and has the potential to identify subtle cases that can be missed by a busy radiologist. By increasing the sensitivity and accuracy of PDAC detection, AI- integrated workflow has the potential to significantly improve patient outcomes. As radiologists, we should not sit on the sidelines. Instead, we should actively engage the AI revolution, hoping to enhance our efficiency and reduce our errors, eventually improving patient outcomes.”
    Application of Deep Learning to Pancreatic Cancer Detection: Lessons Learned From Our Initial Experience.
    Chu LC, Park S, Kawamoto S, et al
    J Am Coll Radiol. 2019 Sep;16(9 Pt B):1338-1342
  • “In the future, we envision that that AI system for automatic PDAC detection will be seamlessly integrated into the radiology workflow as a “second reader,” similar to how computer-aided diagnosis operates in mammographic screening. The AI system will directly receive the CT data sets from the PACS, automatically segment the abdominal organs, and annotate any suspicious pancreatic pathology. These annotated cases will be sent back to the PACS for the radiologist to review. The “second reader” can improve diagnostic confidence and has the potential to identify subtle cases that can be missed by a busy radiologist.”
    Application of Deep Learning to Pancreatic Cancer Detection: Lessons Learned From Our Initial Experience.
    Chu LC, Park S, Kawamoto S, et al
    J Am Coll Radiol. 2019 Sep;16(9 Pt B):1338-1342
  • “We aim at segmenting a wide variety of organs, including tiny targets (e.g., adrenal gland) and neoplasms (e.g., pancreatic cyst), from abdominal CT scans. This is a challenging task in two aspects. First, some organs (e.g., the pancreas), are highly variable in both anatomy and geometry, and thus very difficult to depict. Second, the neoplasms often vary a lot in its size, shape, as well as its location within the organ. Third, the targets (organs and neoplasms) can be considerably small compared to the human body, and so standard deep networks for segmentation are often less sensitive to these targets and thus predict less accurately especially around their boundaries.”
    Recurrent Saliency Transformation Network for Tiny Target Segmentation in Abdominal CT Scans
    Lingxi Xie, Qihang Yu, Yan Wang, Yuyin Zhou, Elliot K. Fishman, and Alan L. Yuille
    IEEE Trans Med Imaging. 2019 Jul 23. doi: 10.1109/TMI.2019.2930679
  • In this paper, we present an end-to-end framework named Recurrent Saliency Transformation Network (RSTN) for seg- menting tiny and/or variable targets. RSTN is a coarse-to-fine approach, which uses prediction from the first (coarse) stage to shrink the input region for the second (fine) stage. A saliency transformation module is inserted between these two stages, so that (i) the coarse-scaled segmentation mask can be transferred as spatial weights and applied to the fine stage; and (ii) the gradients can be back-propagated from the loss layer to the entire network, so that the two stages are optimized in a joint manner. In the testing stage, we perform segmentation iteratively to improve accuracy.
    Recurrent Saliency Transformation Network for Tiny Target Segmentation in Abdominal CT Scans
    Lingxi Xie, Qihang Yu, Yan Wang, Yuyin Zhou, Elliot K. Fishman, and Alan L. Yuille
    IEEE Trans Med Imaging. 2019 Jul 23. doi: 10.1109/TMI.2019.2930679
  • “In this extended journal paper, we allow a gradual optimization to improve the stability of RSTN, and introduce a hierarchical version named H-RSTN to segment tiny and variable neoplasms such as pancreatic cysts. Experiments are performed on several CT datasets, including a public pancreas segmentation dataset, our own multi-organ dataset, and a cystic pancreas dataset. In all these cases, RSTN outperforms the baseline (a stage-wise coarse-to-fine approach) significantly. Confirmed by the radiologists in our team, these promising segmentation results can help early diagnosis of pancreatic cancer.”
    Recurrent Saliency Transformation Network for Tiny Target Segmentation in Abdominal CT Scans
    Lingxi Xie, Qihang Yu, Yan Wang, Yuyin Zhou, Elliot K. Fishman, and Alan L. Yuille
    IEEE Trans Med Imaging. 2019 Jul 23. doi: 10.1109/TMI.2019.2930679
  • “Motivated by the above, we propose a Recurrent Saliency Transformation Network (RSTN) for segmenting very small targets. The chief innovation lies in the mechanism to relate the coarse and fine stages with a saliency transformation module, which repeatedly transforms the segmentation probability map as spatial weights, from the previous iterations to the current iteration. In the training process, the differentiability of this module makes it possible to optimize the coarse-scaled and fine-scaled networks in a joint manner, so that the overall mod- el gets improved after being aware of a global optimization goal.”
    Recurrent Saliency Transformation Network for Tiny Target Segmentation in Abdominal CT Scans
    Lingxi Xie, Qihang Yu, Yan Wang, Yuyin Zhou, Elliot K. Fishman, and Alan L. Yuille
    IEEE Trans Med Imaging. 2019 Jul 23. doi: 10.1109/TMI.2019.2930679

  • Recurrent Saliency Transformation Network for Tiny Target Segmentation in Abdominal CT Scans
    Lingxi Xie, Qihang Yu, Yan Wang, Yuyin Zhou, Elliot K. Fishman, and Alan L. Yuille
    IEEE Trans Med Imaging. 2019 Jul 23. doi: 10.1109/TMI.2019.2930679

  • Recurrent Saliency Transformation Network for Tiny Target Segmentation in Abdominal CT Scans
    Lingxi Xie, Qihang Yu, Yan Wang, Yuyin Zhou, Elliot K. Fishman, and Alan L. Yuille
    IEEE Trans Med Imaging. 2019 Jul 23. doi: 10.1109/TMI.2019.2930679

  • Recurrent Saliency Transformation Network for Tiny Target Segmentation in Abdominal CT Scans
    Lingxi Xie, Qihang Yu, Yan Wang, Yuyin Zhou, Elliot K. Fishman, and Alan L. Yuille
    IEEE Trans Med Imaging. 2019 Jul 23. doi: 10.1109/TMI.2019.2930679
  • “We present the Recurrent Saliency Transformation Network, which enjoys three advantages. (i) Benefited by a (recurrent) global energy function, it is easier to generalize our models from training data to testing data. (ii) With joint optimization over two networks, both of them get improved individually. (iii) By incorporating multi-stage visual cues, more accurate segmentation results are obtained.”
    Recurrent Saliency Transformation Network for Tiny Target Segmentation in Abdominal CT Scans
    Lingxi Xie, Qihang Yu, Yan Wang, Yuyin Zhou, Elliot K. Fishman, and Alan L. Yuille
    IEEE Trans Med Imaging. 2019 Jul 23. doi: 10.1109/TMI.2019.2930679
  • ”We aim at segmenting a wide variety of organs, including tiny targets (e.g., adrenal gland) and neoplasms (e.g., pancreatic cyst), from abdominal CT scans. This is a challenging task in two aspects. First, some organs (e.g., the pancreas), are highly variable in both anatomy and geometry, and thus very difficult to depict. Second, the neoplasms often vary a lot in its size, shape, as well as its location within the organ. Third, the targets (organs and neoplasms) can be considerably small compared to the human body, and so standard deep networks for segmentation are often less sensitive to these targets and thus predict less accurately especially around their boundaries.”
    Recurrent Saliency Transformation Network for Tiny Target Segmentation in Abdominal CT Scans
    Lingxi Xi, Qihang Yu, Yan Wang, Yuyin Zhou, Elliot K. Fishman, and Alan L. Yuille
    IEEE TRANSACTIONS ON MEDICAL IMAGING (in press)
  • “In conclusion, our study provided preliminary evidence that textural features derived from CT images were useful in differential diagnosis of pancreatic mucinous cystadenomas and serous cystadenomas, which may provide a non-invasive approach to determine whether surgery is needed in clinical practice. However, multicentre studies with larger sample size are needed to confirm these results.”
    Discrimination of Pancreatic Serous Cystadenomas From Mucinous Cystadenomas With CT Textural Features: Based on Machine Learning
    Yang J et al.
    Front. Oncol., 12 June 2019 /doi.org/10.3389/fonc.2019.00494
  • Results: Only 31 of 102 serous cystic neoplasm cases in this study were recognized correctly by clinicians before the surgery. Twenty-two features were selected from the radiomics system after 100 bootstrapping repetitions of the least absolute shrinkage selection operator regression. The diagnostic scheme performed accurately and robustly, showing the area under the receiver operating characteristic curve 1⁄4 0.767, sensitivity 1⁄4 0.686, and specificity 1⁄4 0.709. In the independent validation cohort, we acquired similar results with receiver operating characteristic curve 1⁄4 0.837, sensitivity 1⁄4 0.667, and specificity 1⁄4 0.818.
    Conclusion: The proposed radiomics-based computer-aided diagnosis scheme could increase preoperative diagnostic accuracy and assist clinicians in making accurate management decisions.
    Computer-Aided Diagnosis of Pancreas Serous Cystic Neoplasms: A Radiomics Method on Preoperative MDCT Images
    Ran Wei et al.
    Technology in Cancer Research & Treatment
    Volume 18: 1-9; 2019
  • “A total of 17 intensity and texture features were selected, showing difference between SCNs and non-SCNs. Typically, the intensity T-range, wavelet intensity T-median, and wavelet neighborhood gray-tone difference matrix (NGTDM) busyness were the most distinguishable.”
    Computer-Aided Diagnosis of Pancreas Serous Cystic Neoplasms: A Radiomics Method on Preoperative MDCT Images
    Ran Wei et al.
    Technology in Cancer Research & Treatment
    Volume 18: 1-9; 2019
  • “In our retrospective study of 260 patients with PCN, we were surprised to find that the overall preoperative diagnostic accuracy by clinicians was 37.3% (97 of 260), and only 30.4% (31 of 102) of SCN cases were correctly diagnosed. This meant that more than two-thirds of patients with SCN suffered unnecessary pancreatic resection.”
    Computer-Aided Diagnosis of Pancreas Serous Cystic Neoplasms: A Radiomics Method on Preoperative MDCT Images
    Ran Wei et al.
    Technology in Cancer Research & Treatment
    Volume 18: 1-9; 2019
  • “Furthermore, radiomics high-throughput features containing intensity features, texture features, and their wavelet decomposition forms fully utilized image information and obtained more image details that were hard to discover with the naked human eyes.”
    Computer-Aided Diagnosis of Pancreas Serous Cystic Neoplasms: A Radiomics Method on Preoperative MDCT Images
    Ran Wei et al.
    Technology in Cancer Research & Treatment
    Volume 18: 1-9; 2019
  • “In conclusion, our study proposed a radiomics-based CAD scheme and stressed the role of radiomics analysis as a novel noninvasive method for improving the preoperative diagnostic accuracy of SCNs. In all, 409 quantitative features were auto- matically extracted, and a feature subset containing the 22 most statistically significant features was selected after 100 boot- strapping repetitions. Our proposed method improved the diag- nostic accuracy and performed well in all metrics, with AUC of 0.767 in the cross-validation cohort and 0.837 in the independent validation cohort. This demonstrated that our CAD scheme could provide a powerful reference for the diagnosis of clinicians to reduce misjudgment and avoid overtreatment.”
    Computer-Aided Diagnosis of Pancreas Serous Cystic Neoplasms: A Radiomics Method on Preoperative MDCT Images
    Ran Wei et al.
    Technology in Cancer Research & Treatment
    Volume 18: 1-9; 2019
  • “In conclusion, our study proposed a radiomics-based CAD scheme and stressed the role of radiomics analysis as a novel noninvasive method for improving the preoperative diagnostic accuracy of SCNs. In all, 409 quantitative features were auto- matically extracted, and a feature subset containing the 22 most statistically significant features was selected after 100 boot- strapping repetitions. Our proposed method improved the diag- nostic accuracy and performed well in all metrics, with AUC of 0.767 in the cross-validation cohort and 0.837 in the independent validation cohort. This demonstrated that our CAD scheme could provide a powerful reference for the diagnosis of clinicians to reduce misjudgment and avoid overtreatment.”
    Computer-Aided Diagnosis of Pancreas Serous Cystic Neoplasms: A Radiomics Method on Preoperative MDCT Images
    Ran Wei et al.
    Technology in Cancer Research & Treatment
    Volume 18: 1-9; 2019
  • “In this paper, we adopt 3D CNNs to segment the pancreas in CT images. Although deep neural networks have been proven to be very effective on many 2D vision tasks, it is still challenging to apply them to 3D applications due to the limited amount of annotated 3D data and limited computational resources. We propose a novel 3D-based coarse- to-fine framework for volumetric pancreas segmentation to tackle these challenges. The proposed 3D-based framework outperforms the 2D counterpart to a large margin since it can leverage the rich spatial information along all three axes.”


    A 3D Coarse-to-Fine Framework for Automatic Pancreas Segmentation 
Zhuotun Zhu, Yingda Xia, Wei Shen, Elliot K. Fishman, Alan L. Yuille
arXiv:1712.00201v1 [cs.CV] 1 Dec 2017 

  • “In this work, we proposed a novel 3D network called “ResDSN” integrated with a coarse-to-fine framework to simultaneously achieve high segmentation accuracy and low time cost. The backbone network “ResDSN” is carefully designed to only have long residual connections for efficient inference. To our best knowledge, we are the first to segment the challenging pancreas using 3D networks which leverage the rich spatial information to achieve the state-of- the-art.”

    
A 3D Coarse-to-Fine Framework for Automatic Pancreas Segmentation 
Zhuotun Zhu, Yingda Xia, Wei Shen, Elliot K. Fishman, Alan L. Yuille
arXiv:1712.00201v1 [cs.CV] 1 Dec 2017 

  • “To address these issues, we propose a concise and effective framework based on 3D deep networks for pancreas segmentation, which can simultaneously achieve high seg- mentation accuracy and low time cost. Our framework is formulated in a coarse-to-fine manner. In the training stage, we first train a 3D FCN from the sub-volumes sampled from an entire CT volume. We call this ResDSN Coarse model, which aims to obtain the rough location of the target pancreas from the whole CT volume by making full use of the overall 3D context. Then, we train another 3D FCN from the sub-volumes sampled only from the ground truth bound- ing boxes of the target pancreas. We call this the ResDSN Fine model, which can refine the segmentation based on the coarse result.”


    A 3D Coarse-to-Fine Framework for Automatic Pancreas Segmentation 
Zhuotun Zhu, Yingda Xia, Wei Shen, Elliot K. Fishman, Alan L. Yuille
arXiv:1712.00201v1 [cs.CV] 1 Dec 2017 

  • “This work is motivated by the difficulty of small organ segmentation. As the target is often small, it is required to 
focus on a local input region, but sometimes the network is confused due to the lack of contextual information. We present the Recurrent Saliency Transformation Network, which enjoys three advantages. (i) Benefited by a (recurrent) global energy function, it is easier to generalize our models from training data to testing data. (ii) With joint optimization over two networks, both of them get improved individually. (iii) By incorporating multi-stage visual cues, more accurate segmentation results are obtained. As the fine stage is less likely to be confused by the lack of contexts, we also observe better convergence during iterations.”


    Recurrent Saliency Transformation Network: Incorporating Multi-Stage Visual Cues for Small Organ Segmentation 
Qihang Yu, Lingxi Xie, Yan Wang, Yuyin Zhou, Elliot K. Fishman, Alan L. Yuille
arXiv:1709.04518v3 [cs.CV] 18 Nov 2017
  • “This paper presents a Recurrent Saliency Transforma- tion Network. The key innovation is a saliency transfor- mation module, which repeatedly converts the segmentation probability map from the previous iteration as spatial weights and applies these weights to the current iteration. This brings us two-fold benefits. In training, it allows joint optimization over the deep networks dealing with different input scales. In testing, it propagates multi-stage visual information throughout iterations to improve segmentation accuracy.”


    Recurrent Saliency Transformation Network: Incorporating Multi-Stage Visual Cues for Small Organ Segmentation 
Qihang Yu, Lingxi Xie, Yan Wang, Yuyin Zhou, Elliot K. Fishman, Alan L. Yuille
arXiv:1709.04518v3 [cs.CV] 18 Nov 2017
  • “Automatic segmentation of an organ and its cystic region is a prerequisite of computer-aided diagnosis. In this paper, we focus on pancreatic cyst segmentation in abdominal CT scan. This task is important and very useful in clinical practice yet challenging due to the low contrast in boundary, the variability in location, shape and the different stages of the pancreatic cancer. Inspired by the high relevance between the location of a pancreas and its cystic region, we introduce extra deep supervision into the segmentation network, so that cyst segmentation can be improved with the help of relatively easier pancreas segmentation.”


    Deep Supervision for Pancreatic Cyst Segmentation in Abdominal CT Scans 
Yuyin Zhou, Lingxi Xie, Elliot K. Fishman, and Alan L. Yuille 
(in) Medical Image Computing and Computer Assisted Intervention − MICCAI 2017
page 222-231
  • “This paper presents the first system for pancreatic cyst segmentation which can work without human assistance on the testing stage. Motivated by the high relevance of a cystic pancreas and a pancreatic cyst, we formulate pancreas segmentation as an explicit variable in the formulation, and introduce deep supervision to assist the network training process. The joint optimization can be factorized into two stages, making our approach very easy to implement. We collect a dataset with 131 pathological cases. Based on a coarse-to-fine segmentation algorithm, our approach produces reasonable cyst segmentation results. It is worth emphasizing that our approach does not require any extra human annotations on the testing stage, which is especially practical in assisting common patients in cheap and periodic clinical applications.”

    
Deep Supervision for Pancreatic Cyst Segmentation in Abdominal CT Scans 
Yuyin Zhou, Lingxi Xie, Elliot K. Fishman, and Alan L. Yuille 
(in) Medical Image Computing and Computer Assisted Intervention − MICCAI 2017
page 222-231
  • “The pancreas is a highly deformable organ that has a shape and location that is greatly influenced by the presence of adjacent struc- tures. This makes automated image analysis of the pancreas extremely challenging. A number of different approaches have been taken to automated pancreas analysis, in- cluding the use of anatomic atlases, the loca- tion of the splenic and portal veins, and state- of-the-art computer science methods such as deep learning.”

    Progress in Fully Automated Abdominal CT Interpretation
Summers RM
AJR 2016; 207:67–79
  • “A recent advance in computer science is the refinement of neural networks, a type of machine learning classifier used to make decisions from data. This refine- ment, known generically as deep learn- ing but more specifically as convolutional neural networks, has shown dramatic improvements in automated intelligence applications. Initially drawing attention for impressive improvements in speech recognition and natural image interpretation, deep learning is now being applied to medical images, as described already in the sections on the pancreas and colitis.” 


    Progress in Fully Automated Abdominal CT Interpretation
Summers RM
AJR 2016; 207:67–79

Privacy Policy

Copyright © 2024 The Johns Hopkins University, The Johns Hopkins Hospital, and The Johns Hopkins Health System Corporation. All rights reserved.