google ads
Pancreas: Artificial Intelligence Imaging Pearls - Educational Tools | CT Scanning | CT Imaging | CT Scan Protocols - CTisus
Imaging Pearls ❯ Pancreas ❯ Artificial Intelligence

-- OR --

  • “Abdominal cancers continue to pose daily challenges to clinicians, radiologists and researchers. These challenges are faced at each stage of abdominal cancer management, including early detection, accurate characterization, precise assessment of tumor spread, preoperative planning when surgery is anticipated, prediction of tumor aggressiveness, response to therapy, and detection of recurrence. Technical advances in medical imaging, often in combination with imaging biomarkers, show great promise in addressing such challenges. Information extracted from imaging datasets owing to the application of radiomics can be used to further improve the diagnostic capabilities of imaging. However, the analysis of the huge amount of data provided by these advances is a difficult task in daily practice. Artificial intelligence has the potential to help radiologists in all these challenges. Notably, the applications of AI in the field of abdominal cancers are expanding and now include diverse approaches for cancer detection, diagnosis and classification, genomics and detection of genetic alterations, analysis of tumor microenvironment, identification of predictive biomarkers and follow-up. However, AI currently has some limitations that need further refinement for implementation in the clinical setting. This review article sums up recent advances in imaging of abdominal cancers in the field of image/data acquisition, tumor detection, tumor characterization, prognosis, and treatment response evaluation.”
    CT and MRI of abdominal cancers: current trends and perspectives in the era of radiomics and artificial intelligence
    Maxime Barat · Anna Pellat · Christine Hoeffel · Anthony Dohan · Romain Coriat · Elliot K. Fishman · Stéphanie Nougaret · Linda Chu · Philippe Soyer
    Japanese Journal of Radiology (2024) 42:246–260
  • “Technical advances in medical imaging, often in combination with imaging biomarkers, show great promise in addressing such challenges. Information extracted from imaging datasets owing to the application of radiomics can be used to further improve the diagnostic capabilities of imaging. However, the analysis of the huge amount of data provided by these advances is a difficult task in daily practice. Artificial intelligence has the potential to help radiologists in all these challenges. Notably, the applications of AI in the field of abdominal cancers are expanding and now include diverse approaches for cancer detection, diagnosis and classification, genomics and detection of genetic alterations, analysis of tumor microenvironment, identification of predictive biomarkers and follow-up. However, AI currently has some limitations that need further refinement for implementation in the clinical setting. This review article sums up recent advances in imaging of abdominal cancers in the field of image/data acquisition, tumor detection, tumor characterization, prognosis, and treatment response evaluation.”
    CT and MRI of abdominal cancers: current trends and perspectives in the era of radiomics and artificial intelligence
    Maxime Barat · Anna Pellat · Christine Hoeffel · Anthony Dohan · Romain Coriat · Elliot K. Fishman · Stéphanie Nougaret · Linda Chu · Philippe Soyer
    Japanese Journal of Radiology (2024) 42:246–260
  • “Radiomics can be used for several tasks such as characterizing indeterminate liver lesions in patients with cirrhosis  or pancreatic tumors, grading HCC or pancreatic neuroendocrine tumors (pNETs) , identifying microvascular invasion (MVI) in HCC (TACE)  or transarterial radioembolization. More recently, radiomics has demonstrated utility for the assessment of tumor microenvironment, which is a relatively new concept that refers to an assemblage of multiple elements contained in tissues that surround tumor. Tumor microenvironment is a dynamic and heterogeneous assemblage made of precursor cells, fibroblasts, immune cells, endothelial cells, signaling molecules, and extracellular matrix components that play a major role in cancer biology. Tumor microenvironment is involved in tumor growth, invasion, metastasis but also in response or resistance to systemic therapies and local therapies such as thermal ablation.”
    CT and MRI of abdominal cancers: current trends and perspectives in the era of radiomics and artificial intelligence
    Maxime Barat · Anna Pellat · Christine Hoeffel · Anthony Dohan · Romain Coriat · Elliot K. Fishman · Stéphanie Nougaret · Linda Chu · Philippe Soyer
    Japanese Journal of Radiology (2024) 42:246–260
  • “Radiomics models have been developed to predict response to local intra-arterial therapy of HCC. Park et al. found that HCCs with complete response after TACE show lower homogeneity at CT-texture analysis than those with partial response. A hybrid model combining CT-based radiomic features and three clinical factors (Child–Pugh score, a-fetoprotein level, and HCC size) was a strong predictor of longer survival in patients with HCC treated using TACE (hazard ratio 19.88; 95% CI 6.37–62.02) (p < 0.0001). Interestingly, in a study by Aujay et al., MRI based radiomics outperformed RECIST criteria and Liver Imaging Reporting and Data System treatment response algorithm for the assessment of early response of locally advanced HCC to 90yttrium transarterial radioembolization.”
    CT and MRI of abdominal cancers: current trends and perspectives in the era of radiomics and artificial intelligence
    Maxime Barat · Anna Pellat · Christine Hoeffel · Anthony Dohan · Romain Coriat · Elliot K. Fishman · Stéphanie Nougaret · Linda Chu · Philippe Soyer
    Japanese Journal of Radiology (2024) 42:246–260
  • “Owing to the development of radiomics, CT and MRI can now be used as predictive tools to better estimate response to treatment. Although major advances have been made in abdominal cancer imaging with promising results, these results are still at an early stage and often obtained with local algorithms. Although AI helps extract a huge number of features and classify them, there is a need to bring together all the information to use it in a more efficient way. The next step should be to investigate how all these advances can be implemented in the real-life setting and how they can positively influence care and outcomes in patients with abdominal cancers .State of the art imaging is forcing radiologists to rethink what they do and how they should do it. Current challenges to implementation include reimbursement issues and well-designed translational trials for AI validation that need large volumes of high-quality and representative data for the development of robust AI algorithms.”
    CT and MRI of abdominal cancers: current trends and perspectives in the era of radiomics and artificial intelligence
    Maxime Barat · Anna Pellat · Christine Hoeffel · Anthony Dohan · Romain Coriat · Elliot K. Fishman · Stéphanie Nougaret · Linda Chu · Philippe Soyer
    Japanese Journal of Radiology (2024) 42:246–260
  • “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
  • 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.
  • OBJECTIVE. The objective of our study was to determine the utility of radiomics features in differentiating CT cases of pancreatic ductal adenocarcinoma (PDAC) from normal pancreas.  
    MATERIALS AND METHODS. In this retrospective case-control study, 190 patients with PDAC (97 men, 93 women; mean age ± SD, 66 ± 9 years) from 2012 to 2017 and 190 healthy potential renal donors (96 men, 94 women; mean age ± SD, 52 ± 8 years) without known pancreatic disease from 2005 to 2009 were identified from radiology and pathology databases. The 3D volume of the pancreas was manually segmented from the preoperative CT scans by four trained researchers and verified by three abdominal radiologists. Four hundred seventy-eight radiomics features were extracted to express the phenotype of the pancreas. Forty features were selected for analysis because of redundancy of computed features. The dataset was divided into 255 training cases (125 normal control cases and 130 PDAC cases) and 125 validation cases (65 normal control cases and 60 PDAC cases). A random forest classifier was used for binary classification of PDAC versus normal pancreas of control cases. Accuracy, sensitivity, and specificity were calculated.
    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.
  • 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.
  • 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
  • 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 
  • “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)
  • 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

  • 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) 
  • “Chen et al. tested a machine learning technique for detecting people having cancer in their pancreas at an early phase using medical data that had been collected from digital health records. As shown in eq. 1, they utilized eXtreme Gradient Boosting (XGBoost) to create a prediction model to detect early-stage patients based on 18,220 EHR variables, including diagnoses, procedures, clinical note information, and medicines.”
    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)
  • "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)
  • 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. 
  • “Eleven studies (19%) evaluated differentiation of PCNs by classifying them into their respective subtypes based on their characteristics on imaging. Springer et al developed a multimodality ML model that integrated clinical, radiological and genetic/biochemical markers data to determine whether patients with pancreas cyst should undergo surgery, monitoring, or no further surveillance. The model correctly identified serous cystic neoplasms in 65% of the cases with 99% specificity, clearly outperforming the current standard of care of clinical identification in only 18% of cases. The authors conclude that these systems may serve an adjunct role in clinical practice, enabling the clinician to take better-informed clinical decisions[.”
    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.
  • 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
  • “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 
  • “Major advances in medical AI have had a tremendous impact at two main levels: (1) image recognition and (2) big data analysis. AI can detect very small changes that are difficult for humans to perceive. For example, AI can detect lung cancer up to a year before a physician [3], and AI can correctly diagnose skin cancer with superior diagnostic performance compared to that of a physician [4]. In addition, AI can reach the desired output within seconds and with more “consistent” performance. Doctors may have “inconsistent” performance due to insufficient training or exhaustion from busy clinical demands. A visual assessment by imaging physicians is qualitative, subjective, and prone to errors, and subject to intra-observer and inter-observer variability. AI may have better performance than physicians in some cases [5], and it has great promise to reduce clinician workload and the cost of medical care. However, it is necessary for clinicians to verify the output from AI for patient care.”
    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 

  • 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 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  
  • “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 
  • “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.
  • “Radiomics analysis extracts a large number of features from conventional radiological cross-sectional images that were traditionally undetectable by the naked human eye. It identifies tumor heterogeneity in a comprehensive and noninvasive way, reflecting the biological behaviour of lesions, and thus assists in clinical diagnosis and treatment evaluation. This review describes the radiomics approach and its uses in the evaluation of pancreatic ductal adenocarcinoma (PDAC). This discipline holds the potential to characterize lesions more accurately, assesses the primary tumour and predicts the response to therapy and prognosis in PDAC. Existing studies have provided significant insights into the application of radiomics in managing the PDAC. However, a variety of challenges, including data quality and quantity, imaging segmentation, and the standardization of the radiomics process need to be solved before its widespread clinical implementation.”
    Radiomics in pancreatic ductal adenocarcinoma: a state of art review  
    Ming He et al.
    Journal of Pancreatology (2020) 3:4

  • Radiomics in pancreatic ductal adenocarcinoma: a state of art review  
    Ming He et al.
    Journal of Pancreatology (2020) 3:4
  • "The application of radiomics in PDAC mainly includes the following 3 aspects: lesion characterization, primary tumour assessment and response to therapy and prognosis. It has also been used in other nononcologic conditions associated with PDAC. The initial results of radiomics related to PDAC are promising. However, there are still many problems and challenges that need to be solved, including data quality and quantity, imaging segmentation and the standardization of the radiomics process. Radiologists need to work closely with researchers such as information scientists to establish the standardized process of radiomics analysis. Multi-centre data sharing and public database establishment would provide more high-quality data for radiomics analysis. With the development of the radiomics in PDAC, it has a considerable potential to be a useful assistant in the clinical workflow for PDAC’s personalized medicine.”
    Radiomics in pancreatic ductal adenocarcinoma: a state of art review  
    Ming He et al.
    Journal of Pancreatology (2020) 3:4
  • “The procedure of the radiomics analysis should be carefully evaluated and standardized in every step to eliminate the potential bias and confounding factors. Extensive disclosure of the imaging protocols, evaluation criteria, reproducibility and/ or clinical utility is of great significance. Multiple studies had a limitation of unclear description about the detailed process of radiomics performed pre-processing, reconstruction, variations in feature nomenclature, mathematical definition, methodology, and software implementation of the applied feature extraction algorithms. The process of feature reduction and/or exclusion should be described clearly in the future. designs and a head-to-head comparison of quantitative features against standard diagnostic radiologist assessment are needed in the future.”
    Radiomics in pancreatic ductal adenocarcinoma: a state of art review  
    Ming He et al.
    Journal of Pancreatology (2020) 3:4
  • 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 and radiomics are two broad categories of artificial intelligence (AI) research that have the potential to facilitate automatic disease detection and to provide quantitative imaging biomarkers for individualized disease assessment. The large volumes of digital data inherent in radiology images make radiology a natural field for AI research. Cinematic Rendering is a recently described post-processing technique that uses sophisticated illumination modeling to achieve more photorealistic images, and these images, in turn, have the potential to aid treatment planning. Here we review these AI and advanced visualization techniques and highlight how they can be used to improve the detection and management of pancreatic cancers.”
    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)
  • “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)
  • “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 filter 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 filter 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)

Privacy Policy

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