Imaging Pearls ❯ October 2024
|
-- OR -- |
|
Chest
Congenital Lung Anomalies in Adults
Marcos Mestas Nuñez, et al.
RadioGraphics 2024; 44(9):e240017- “CPAMs, previously known as congenital cystic adenomatoid malformations, are a heterogeneous group of cystic and noncystic congenital pulmonary lesions. While CPAM is the most commonly diagnosed CLA in the pediatric population, it is increasingly being recognized in adults. CPAM results from early airway maldevelopment at various stages and is characterized by the overgrowth of primary bronchioles that communicate with an abnormal bronchial tree lacking cartilage.”
Congenital Lung Anomalies in Adults
Marcos Mestas Nuñez, et al.
RadioGraphics 2024; 44(9):e240017 - “At imaging, CPAM appears as a unilocular or multilocular thin-walled cystic lesion with or without air-fluid levels, more commonly in the lower lobes. Cyst size can help differentiate CPAM type 1 from type 2, favoring type 1 when the cyst is larger than 2.5 cm and type 2 when it is smaller than 2.0 cm. However, on pathologic resection specimens, more than one CPAM subtype coexisting in the same lesion can be seen.”
Congenital Lung Anomalies in Adults
Marcos Mestas Nuñez, et al.
RadioGraphics 2024; 44(9):e240017 - “CPAMs typically have a pulmonary arterial blood supply; however, in some cases, systemic arteries may supply the malformation, indicating a coexisting intralobar sequestration . These malformations are termed hybrid lesions (see “Hybrid Lesions” section). Type 2 CPAM may be associated with other congenital malformations, including renal agenesis, cardiovascular anomalies (truncus arteriosus, tetralogy of Fallot), diaphragmatic hernia, and esophageal and jejunal atresia. Findings of thickened cyst walls, surrounding ground-glass opacities, or consolidation may indicate superimposedinfection or hemorrhage .”
Congenital Lung Anomalies in Adults
Marcos Mestas Nuñez, et al.
RadioGraphics 2024; 44(9):e240017
- Objective: To evaluate the accuracy and quality of AI-generated chest radiograph interpretations in the emergency department setting.
Design, setting, and participants: This was a retrospective diagnostic study of 500 randomly sampled emergency department encounters at a tertiary care institution including chest radiographs interpreted by both a teleradiology service and on-site attending radiologist from January 2022 to January 2023. An AI interpretation was generated for each radiograph. The 3 radiograph interpretations were each rated in duplicate by 6 emergency department physicians using a 5-point Likert scale.
Main outcomes and measures: The primary outcome was any difference in Likert scores between radiologist, AI, and teleradiology reports, using a cumulative link mixed model. Secondary analyses compared the probability of each report type containing no clinically significant discrepancy with further stratification by finding presence, using a logistic mixed-effects model. Physician comments on discrepancies were recorded.
Generative Artificial Intelligence for Chest Radiograph Interpretation in the Emergency Department.
Huang J, Neill L, Wittbrodt M, et al..
JAMA Netw Open. 2023 Oct 2;6(10):e2336100. - Results: A total of 500 ED studies were included from 500 unique patients with a mean (SD) age of 53.3 (21.6) years; 282 patients (56.4%) were female. There was a significant association of report type with ratings, with post hoc tests revealing significantly greater scores for AI (mean [SE] score, 3.22 [0.34]; P < .001) and radiologist (mean [SE] score, 3.34 [0.34]; P < .001) reports compared with teleradiology (mean [SE] score, 2.74 [0.34]) reports. AI and radiologist reports were not significantly different. On secondary analysis, there was no difference in the probability of no clinically significant discrepancy between the 3 report types. Further stratification of reports by presence of cardiomegaly, pulmonary edema, pleural effusion, infiltrate, pneumothorax, and support devices also yielded no difference in the probability of containing no clinically significant discrepancy between the report types.
Conclusions and relevance: In a representative sample of emergency department chest radiographs, results suggest that the generative AI model produced reports of similar clinical accuracy and textual quality to radiologist reports while providing higher textual quality than teleradiologist reports. Implementation of the model in the clinical workflow could enable timely alerts to life-threatening pathology while aiding imaging interpretation and documentation.
Generative Artificial Intelligence for Chest Radiograph Interpretation in the Emergency Department.
Huang J, Neill L, Wittbrodt M, et al..
JAMA Netw Open. 2023 Oct 2;6(10):e2336100. - Key Points
Question How do emergency department physicians rate artificial intelligence (AI)–generated chest radiograph reports for quality and accuracy, compared with in-house radiologist and teleradiology reports?
Findings In this diagnostic study of the developed generative AI model on a representative sample of 500 emergency department chest radiographs from 500 unique patients, the AI model produced reports of similar clinical accuracy and textual quality to radiology reports while providing higher textual quality than teleradiology reports.
Meaning Results suggest that use of the generative AI tool may facilitate timely interpretation of chest radiography by emergency department physicians.
Generative Artificial Intelligence for Chest Radiograph Interpretation in the Emergency Department.
Huang J, Neill L, Wittbrodt M, et al..
JAMA Netw Open. 2023 Oct 2;6(10):e2336100. - “In this diagnostic study accounting for both clinical accuracy and textual quality, results suggest that our AI tool produced reports similar in performance to a radiologist and better than a teleradiology service in a representative sample of ED chest radiographs. AI report ratings were comparable with those of on-site radiologists across all evaluated pathology categories. Model integration in clinical workflows could enable timely alerts to life-threatening pathology while aiding physician imaging interpretation and speeding up documentation. Further efforts to prospectively evaluate clinical impact and generalizability are needed.”
Generative Artificial Intelligence for Chest Radiograph Interpretation in the Emergency Department.
Huang J, Neill L, Wittbrodt M, et al..
JAMA Netw Open. 2023 Oct 2;6(10):e2336100. - Huang et al. developed a multimodal generative AI model and evaluated its ability to produce full radiology reports for chest radiographs in the emergency department (ED) setting. An encoder-decoder model was trained on 900,000 chest radiographs and generated a report when given an input chest radiograph and its most recent prior radiograph. A retrospective analysis was performed on 500 unique ED encounters with chest radiographs interpreted by three reader categories: a teleradiology service (all with U.S. residency and board experience), 12 ED radiologists (mean, 14.6 ± 12.5 [SD] years of post residency clinical practice experience), and the AI model. Six ED physicians (10.6 ± 6.4 years of postresidency clinical practice experience) rated the AI, radiologist, and teleradiology reports in a blinded fashion using a 5-point Likert scale.
Beyond the AJR: Early Applications of Generative Artificial Intelligence for Radiology Report Interpretation.
Doo FX, Parekh VS.
AJR Am J Roentgenol. 2024 Aug;223(2):e2330696. - “The results indicated that the AI-generated reports and radiologist reports were of similar quality and accuracy (on a Likert scale, AI reports: 3.22 ± 0.34 [SD], radiologist reports: 3.34 ± 0.34, both of which scored significantly higher than teleradiology reports: 2.74 ± 0.34) (p < .001). There was no significant difference in the probability of reports containing clinically significant discrepancies among the three report types, even when stratified by specific findings. This study suggests that generative AI models can produce chest radiograph reports with clinical accuracy and textual quality comparable with those produced by radiologists, showing the potential of AI to enhance radiology services in EDs, especially in settings in which access to radiology services is limited.”
Beyond the AJR: Early Applications of Generative Artificial Intelligence for Radiology Report Interpretation.
Doo FX, Parekh VS.
AJR Am J Roentgenol. 2024 Aug;223(2):e2330696. - “This study represents a step toward clinical application of generative AI. A key strength is the evaluation of an AI model’s capability to generate full radiology reports, compared with prior narrow AI applications. However, one important factor affecting the generalizability of this Huang et al. study is that clinical quality was scored by referring ED physicians, rather than expert radiologists. A recent study on GPT-4 (OpenAI)-generated radiology report impressions has shown that radiologists overall graded AI impressions to be less coherent, less comprehensive, more factually inconsistent, and more medically harmful, whereas referring providers favored GPT-4 impressions for coherence and diminished harmfulness.”
Beyond the AJR: Early Applications of Generative Artificial Intelligence for Radiology Report Interpretation.
Doo FX, Parekh VS.
AJR Am J Roentgenol. 2024 Aug;223(2):e2330696. - “The debate about AI potentially replacing human radiologists has since shifted toward recognizing AI’s role as a supportive, rather than a substitutive, tool . Even when using AI as an adjunct, radiologists may not necessarily save time, especially if needing to study and correct errors . Although generative AI introduces additional ways that AI can augment radiologist workflow, this study also shows the need to further refine the technology to understand its limitations as an adjunct to human expertise and to apply it to more diverse care settings and patient populations . Also, we must carefully consider factors such as patient privacy, consistency of generated outputs, and the potential impact on clinical workflows .”
Beyond the AJR: Early Applications of Generative Artificial Intelligence for Radiology Report Interpretation.
Doo FX, Parekh VS.
AJR Am J Roentgenol. 2024 Aug;223(2):e2330696. - Takeaway Point
“A generative AI model for chest radiograph interpretations was comparable to radiologists and superior to teleradiology services in the ED setting, when judged by ED physicians, highlighting its potential as a supportive tool in emergency radiology.”
Beyond the AJR: Early Applications of Generative Artificial Intelligence for Radiology Report Interpretation.
Doo FX, Parekh VS.
AJR Am J Roentgenol. 2024 Aug;223(2):e2330696.
Deep Learning
- “The experience reported by Del Gaizo et al has important implications and lessons for anyone planning to introduce AI solutions into clinical radiology practice or undertake similar research. Prospective users should assess whether their patient population is a close enough match to the population on which an AI program was developed for it to be used: They should assess the potential impact of prevalence on accuracy and predictive value. For a given combination of sensitivity and specificity, lower prevalence will result in lower estimates of PPV. Other important issues to assess are the impact on radiologists’ interpretation times and, for many clinical scenarios, impact on time to therapy. Conservatively, radiology practices introducing AI applications into their clinical operations should always undertake an assessment after implementation to determine how well the program is functioning in their respective unique environments.”
Challenges of Implementing Artificial Intelligence–enabled Programs in the Clinical Practice of Radiology
James H. Thrall
Radiology: Artificial Intelligence 2024; 6(5):e240411 - “A striking finding in the study reported by Del Gaizo et al was a positive predictive value (PPV) of only 21.1%. PPV is a function of sensitivity, specificity, and prevalence: It is the probability that a patient with a positive (abnormal) test result actually has the disease. The authors observe that the low prevalence of 2.7% in their study is the likely reason for the low PPV. Of note, McLouth et al reported a prevalence of ICH of 31% (255 of 814), indicating a different patient population than the current study. The corresponding PPV in the McLouth et al study was 91.4%. McLouth et al modeled different levels of prevalence, holding sensitivity and specificity constant, which showed PPV ranged from 80.2% at 10% prevalence to 97.3% at 50% prevalence.”
Challenges of Implementing Artificial Intelligence–enabled Programs in the Clinical Practice of Radiology
James H. Thrall
Radiology: Artificial Intelligence 2024; 6(5):e240411
- Summary
The performance of an artificial intelligence clinical decision support solution for intracranial hemorrhage detection was low in a low prevalence environment; falsely flagged studies led to increased radiologist interpretation time, potentially reducing system efficiency.
Key Points
■ An artificial intelligence (AI) clinical decision support solution for intracranial hemorrhage detection yielded a positive predictive value of 21.1% in a low prevalence (2.70%) environment.
■ Falsely flagged studies by the AI solution led to lengthened radiologist read times and system inefficiencies (median read time increased 1 minute 14 seconds [P < .001] for examinations with false-positive findings and 1 minute 5 seconds [P = .04] for examinations with false-negative findings).
■ Factoring in prevalence of a condition in varying clinical settings and the impact that falsely flagged studies will have on system efficiency may aid institutional decision-making for use of an AI solution and help set clearer expectations for end users.
Deep Learning to Detect Intracranial Hemorrhage in a National Teleradiology Program and the Impact on Interpretation Time
Andrew James Del Gaizo, et al.
Radiology: Artificial Intelligence 2024; 6(5):e240067 - The diagnostic performance of an artificial intelligence (AI) clinical decision support solution for acute intracranial hemorrhage (ICH) detection was assessed in a large teleradiology practice. The impact on radiologist read times and system efficiency was also quantified. A total of 61 704 consecutive noncontrast head CT examinations were retrospectively evaluated. System performance was calculated along with mean and median read times for CT studies obtained before (baseline, pre-AI period; August 2021 to May 2022) and after (post-AI period; January 2023 to February 2024) AI implementation. The AI solution had a sensitivity of 75.6%, specificity of 92.1%, accuracy of 91.7%, prevalence of 2.70%, and positive predictive value of 21.1%. Of the 56 745 post-AI CT scans with no bleed identified by a radiologist, examinations falsely flagged as suspected ICH by the AI solution (n = 4464) took an average of 9 minutes 40 seconds (median, 8 minutes 7 seconds) to interpret as compared with 8 minutes 25 seconds (median, 6 minutes 48 seconds) for unremarkable CT scans before AI (n = 49 007) (P < .001) and 8 minutes 38 seconds (median, 6 minutes 53 seconds) after AI when ICH was not suspected by the AI solution (n = 52 281) (P < .001).
Deep Learning to Detect Intracranial Hemorrhage in a National Teleradiology Program and the Impact on Interpretation Time
Andrew James Del Gaizo, et al.
Radiology: Artificial Intelligence 2024; 6(5):e240067 - The AI solution had a sensitivity of 75.6%, specificity of 92.1%, accuracy of 91.7%, prevalence of 2.70%, and positive predictive value of 21.1%. Of the 56 745 post-AI CT scans with no bleed identified by a radiologist, examinations falsely flagged as suspected ICH by the AI solution (n = 4464) took an average of 9 minutes 40 seconds (median, 8 minutes 7 seconds) to interpret as compared with 8 minutes 25 seconds (median, 6 minutes 48 seconds) for unremarkable CT scans before AI (n = 49 007) (P < .001) and 8 minutes 38 seconds (median, 6 minutes 53 seconds) after AI when ICH was not suspected by the AI solution (n = 52 281) (P < .001). CT scans with no bleed identified by the AI but reported as positive for ICH by the radiologist (n = 384) took an average of 14 minutes 23 seconds (median, 13 minutes 35 seconds) to interpret as compared with 13 minutes 34 seconds (median, 12 minutes 30 seconds) for CT scans correctly reported as a bleed by the AI (n = 1192) (P = .04). With lengthened read times for falsely flagged examinations, system inefficiencies may outweigh the potential benefits of using the tool in a high volume, low prevalence environment.
Deep Learning to Detect Intracranial Hemorrhage in a National Teleradiology Program and the Impact on Interpretation Time
Andrew James Del Gaizo, et al.
Radiology: Artificial Intelligence 2024; 6(5):e240067 - “CT scans with no bleed identified by the AI but reported as positive for ICH by the radiologist (n = 384) took an average of 14 minutes 23 seconds (median, 13 minutes 35 seconds) to interpret as compared with 13 minutes 34 seconds (median, 12 minutes 30 seconds) for CT scans correctly reported as a bleed by the AI (n = 1192) (P = .04). With lengthened read times for falsely flagged examinations, system inefficiencies may outweigh the potential benefits of using the tool in a high volume, low prevalence environment.”
Deep Learning to Detect Intracranial Hemorrhage in a National Teleradiology Program and the Impact on Interpretation Time
Andrew James Del Gaizo, et al.
Radiology: Artificial Intelligence 2024; 6(5):e240067 - “In conclusion, use of an AI tool for ICH detection in our teleradiology practice yielded reduced sensitivity and specificity compared with the published literature. However, a low prevalence of ICH in our patients contributed to a substantially lower positive predictive value. Noncontrast head CT examinations falsely flagged by an AI solution lengthened mean and median read times. In aggregate, this led to system inefficiencies that reduced the potential benefit of using the AI tool in our environment. A broader understanding of an AI solution’s impact on system efficiency may aid institutional decision-making and help set clearer expectations for end users.”
Deep Learning to Detect Intracranial Hemorrhage in a National Teleradiology Program and the Impact on Interpretation Time
Andrew James Del Gaizo, et al.
Radiology: Artificial Intelligence 2024; 6(5):e240067
Preoperative Prediction of Lymph Node Metastases in Nonfunctional Pancreatic Neuroendocrine Tumors Using a Combined CT Radiomics-Clinical Model.
Ahmed TM, Zhu Z, Yasrab M, Blanco A, Kawamoto S, He J, Fishman EK, Chu L, Javed AA.
Ann Surg Oncol. 2024 Aug 23. doi: 10.1245/s10434-024-16064-4. Epub ahead of print.- Background: When determining the initial chemotherapy regimen for advanced or metastatic pancreatic cancer, various factors must be evaluated. The decision between FOLFIRINOX and Gemcitabine/Nab-paclitaxel (GnP) is challenging, as patient survival hinges on the efficacy and toxicity profiles of these treatments, alongside individual patient characteristics and vulnerabilities. This study aims to guide the selection of an appropriate first-line chemotherapy regimen for advanced or metastatic pancreatic cancer by leveraging machine learning (ML) methods to predict survival outcomes.
Conclusions: We developed the ML models that can compute the probability of OS based on the routinely collected data from patients with advanced or metastatic pancreatic cancer. To the best of our knowledge, this is the first ML solution aimed at aiding clinicians in the selection of the first-line chemotherapy regimen for pancreatic cancer.
Predicting chemotherapy response in patients with advanced or metastatic pancreatic cancer using machine learning.
Moonho Kim, Gyucheol Choi, Jamin Koo
American Society of Clinical Oncology. Sept 2024 - Results: The median age of the patients was 66 years, with 62.3% being male. The MLnmodels achieved the ROC-AUC of 0.81 when predicting OS after 12 months following the initial administration of FOLFIRINOX (n=61) or GnP (n=47). Five (peritoneal metastases, other metastases, bilirubin level, white blood cell counts, and retroperitoneal lymph node metastases) or four (age, tumor location, sex, and metastatic status) covariates were used to achieve the predictive accuracy for the two regimens, respectively. The median OS of the high versus low risk groups of FOLFIRINOX predicted by the ML models were significantly different (7 vs 18 months, P, 0.01), recording the hazard ratio (HR) of 2.79 (95% CI, 1.47-5.26). Similarly, the median OS of the high and low risk groups of GnP were significantly different (8 vs 16 months,P , 0.001, HR 3.50, 95% CI, 1.60-7.66).
Predicting chemotherapy response in patients with advanced or metastatic pancreatic cancer using machine learning.
Moonho Kim, Gyucheol Choi, Jamin Koo
American Society of Clinical Oncology. Sept 2024
- “The overall risk of malignancy in pancreatic cysts may be as low as 0.5 to 1.5%, and the annual risk of progression is 0.5%.7,15 Conversely, studies estimate that 15% of all pancreatic adenocarcinomas originate from mucinous cysts, and these cysts are the sole recognizable precursors of malignant transformation that can be identified on cross-sectional imaging.16-18 Thus, identification of cysts at risk for progression provides an opportunity for prevention or early detection of cancer. Although surgical resection is the only curative treatment option, it carries a risk of major complications, despite technical advances.”
Pancreatic Cysts
Tamas A. Gonda, Djuna L. Cahen, and James J. Farrell
N Engl J Med 2024;391:832-43. - “There are more than 20 types of epithelial and nonepithelial pancreatic cysts, but the majority belong to the six most common histologic categories. The two most prevalent benign lesions, pseudocysts and serous cystadenomas, account for 15 to 25% of all pancreatic cysts. The two types of mucinous cysts, intraductal papillary mucinous neoplasms (IPMNs) and mucinous cystic neoplasms (MCNs), are the predominant premalignant cystic lesions and account for approximately50% of cysts that are found incidentally on imaging for other indications. Solid pseudopapillary neoplasms and cystic pancreatic neuroendocrine tumors are two less common malignant cystic neoplasms.”
Pancreatic Cysts
Tamas A. Gonda, Djuna L. Cahen, and James J. Farrell
N Engl J Med 2024;391:832-43. 
Pancreatic Cysts
Tamas A. Gonda, Djuna L. Cahen, and James J. Farrell
N Engl J Med 2024;391:832-43.- Pancreas Cysts: Key Points
• Pancreatic cysts are common and are being discovered at an increasing rate on cross-sectional imaging, but only a minority progress to cancer.
• The most important goal is to identify the small percentage of cystic lesions associated with a substantialrisk of cancer, and this should be done through a multidisciplinary evaluation based on an algorithmic approach.
• In many cases, imaging, symptom assessment, and laboratory tests can help distinguish benign cysts from those associated with a low, intermediate, or high risk of malignant transformation.
• Endoscopic ultrasonography should be considered for equivocal findings or intermediate-risk cysts.
• Endoscopic ultrasonography and fluid aspiration for cytologic and molecular analysis may help in risk stratification for patients with intermediate-risk cysts.
• Surgical evaluation is warranted for high-risk cysts and for intermediate-risk cysts with multiple risk features, whereas surveillance is used for low-risk cysts - “Serous cystadenomas are benign, slow-growing lesions that predominantly affect women innthe fifth to seventh decades of life.25 These cystsncommonly have a microcystic (honeycomb) appearancenbut may be manifested as solid, macrocysticnor unilocular lesions. A central scar on computed tomography (CT) or magnetic resonance imaging (MRI) is a pathognomonic feature, but it is observed in only 30% of cases. In the absence of typical morphologic features, further evaluation may be necessary to confirm the diagnosis. Although most cases are asymptomatic,large serous cystadenomas can cause abdominal pain, pancreatitis, and biliary obstruction.”
Pancreatic Cysts
Tamas A. Gonda, Djuna L. Cahen, and James J. Farrell
N Engl J Med 2024;391:832-43. - “MCNs are the less common type of mucinous cysts. They characteristically contain ovarian like stroma and almost exclusively affect women in the fourth to sixth decades of life. MCNs are single, thick-walled, mostly unilocular cysts that are generally situated in the distal pancreas. In contrast to intraductal papillary neoplasms, which are much more common, MCNs have no communication with the pancreatic ducts. Although rare, the presence of peripheral (eggshell) calcifications is a diagnostic hallmark. The risk of advanced neoplasia (high-grade dysplasia or cancer) in patients with MCNs was previously reported to be as high as 30 to 40%, but when the presence of pathognomonic ovariantype stroma is confirmed, only 5 to 15% of MCNs contain invasive cancer.”
Pancreatic Cysts
Tamas A. Gonda, Djuna L. Cahen, and James J. Farrell
N Engl J Med 2024;391:832-43. - “IPMNs are the most common type of mucinous cystic lesions, with an equal sex distribution and a peak incidence between the fifth and seventh decades of life. These neoplasms, which arise from the ductal cells, are often multifocal and located throughout the pancreas. IPMNs are classified according to ductal involvement as main-duct, branch-duct, or mixedtype IPMNs. Main-duct IPMNs, which are less common than the branch-duct and mixed-duct types, are characterized by diffuse or segmental dilatation of the main duct (often due to excessive intraductal mucin production) in the absence of a cystic lesion.”
Pancreatic Cysts
Tamas A. Gonda, Djuna L. Cahen, and James J. Farrell
N Engl J Med 2024;391:832-43. 
Pancreatic Cysts
Tamas A. Gonda, Djuna L. Cahen, and James J. Farrell
N Engl J Med 2024;391:832-43.- “The risk of malignant transformation depends on the histologic and anatomical subtypes and ranges from 1 to 38% for branchduct IPMNs and 33 to 85% for main-duct or mixed-type IPMNs. These estimates are mostly from surgical series, and more recent data suggest the risk may be lower. The probable field defect responsible for the multifocality also provides a small concomitant risk of pancreatic cancer, separate from the cyst of interest.”
Pancreatic Cysts
Tamas A. Gonda, Djuna L. Cahen, and James J. Farrell
N Engl J Med 2024;391:832-43. - “Solid pseudopapillary neoplasms most often develop in women in their second or third decade of life. These lesions, which can be located throughout the pancreas, have a well demarcated, heterogeneous appearance, with both solid and cystic components and, in some cases, irregular calcifications. The majority of solid pseudopapillary neoplasms are associated with a low risk of metastasis, and 10 to 15% are classified on histologic evaluation as solid pseudopapillary carcinoma.”
Pancreatic Cysts
Tamas A. Gonda, Djuna L. Cahen, and James J. Farrell
N Engl J Med 2024;391:832-43. - “Cystic pancreatic endocrine neoplasms arise from the pancreatic endocrine cells and are essentially a cystic degeneration of pancreatic neuroendocrine tumors, often with thick, enhancing walls on radiologic imaging Although most of these neoplasms are sporadic and nonfunctioning, up to 10% arise in patients with multiple endocrine neoplasia type 1. More than 80% of cystic pancreatic endocrine neoplasms express somatostatin receptors, which can be detected by means of positron-emission tomography with octreotide or dotatate tracers. Features associated with a poor prognosis, which are similar to those for solid pancreatic endocrine tumors, include a high histologic grade, a diameter of 2 cm or more, symptoms, a Ki-67 proliferation index of 3% or higher, and lymphovascular invasion.”
Pancreatic Cysts
Tamas A. Gonda, Djuna L. Cahen, and James J. Farrell
N Engl J Med 2024;391:832-43. - “A subsequent evaluation of symptoms can aid in risk stratification, although a minority of cysts are symptomatic. Jaundice that is caused by biliary obstruction is considered a high-risk feature. Pancreatitis (due to obstruction of the pancreatic duct by the cyst or produced mucin) and abdominal pain are considered intermediate- risk factors when they are related to the cyst, which is often difficult to confirm. With respect to laboratory testing, an elevation in levels of the serum marker CA 19-9 has been associated with an increased risk of malignant transformation. Similarly, new-onset diabetes is associated with an increased risk of advanced neoplasia. Therefore, an elevation in CA 19-9 and newly abnormal levels of glycated hemoglobin are both associated with an intermediate risk.”
Pancreatic Cysts
Tamas A. Gonda, Djuna L. Cahen, and James J. Farrell
N Engl J Med 2024;391:832-43. 
- “DNA can be isolated from cyst fluid, and the detection of mutations associated with specific neoplasms can be helpful, particularly when other findings are inconclusive and the amount of fluid obtained is small (≤0.5 ml). The presence of a VHL mutation is nearly 100% specific for serous cystadenoma but is identified in only 25 to 50% of cases.The KRAS mutation,which is considered a founder mutation, is more than 95% specific for either type of mucinous cyst, with a sensitivity of 60 to 70%. Mutations in GNAS are specific for IPMNs (but not MCNs). and are detected in 30 to 60% of cases. The absence of a VHL mutation combined with the presence of a KRAS or GNAS mutation is nearly 100% specific for mucinous cysts, with an accuracy of 97%. Detection of a CT NB1 mutation has high specificity for solid pseudopapillary tumors, and the presence of a MEN1 mutation has high specificity for cystic pancreatic endocrine neoplasms.”
Pancreatic Cysts
Tamas A. Gonda, Djuna L. Cahen, and James J. Farrell
N Engl J Med 2024;391:832-43. - “ For most low-risk cysts, surveillance is recommended, with its intensity depending on thebaseline risk. Follow-up every 6 months is advised in the first year, with yearly follow-up thereafter, but the interval can be lengthened with continued stability of the lesion. Surveillance is typically performed with cross-sectional imaging (preferably MRI with magnetic resonance cholangiopancreatography or, if that is unfeasible, with contrast-enhanced CT) or, for larger cysts and cysts with worrisome features, MRI and endoscopic ultrasonography on analternating schedule or combined.”
Pancreatic Cysts
Tamas A. Gonda, Djuna L. Cahen, and James J. Farrell
N Engl J Med 2024;391:832-43. - “Cyst stability is typically defined as less than a 20% increase in the greatest diameter or growth of less than 2.5 mm per year. Faster growth or the development of new intermediate-risk or highrisk features should warrant reconsideration of endoscopic ultrasonography, with or without guided fine-needle aspiration or biopsy, or surgical resection. Current data do not unequivocally support discontinuing surveillance. However, for low-risk lesions that have remained stable for years, the risk of progression is minimal, and cessation of surveillance becomes a reasonable option. Also, a patient’s health status needs to be reevaluated regularly, since a change in health status may warrant adjustment of surveillance goals.”
Pancreatic Cysts
Tamas A. Gonda, Djuna L. Cahen, and James J. Farrell
N Engl J Med 2024;391:832-43. - “Current data do not unequivocally support discontinuing surveillance. However, for low-risk lesions that have remained stable for years, the risk of progression is minimal, and cessation of surveillance becomes a reasonable option. Also, a patient’s health status needs to be reevaluated regularly, since a change in health status may warrant adjustment of surveillance goals.”
Pancreatic Cysts
Tamas A. Gonda, Djuna L. Cahen, and James J. Farrell
N Engl J Med 2024;391:832-43. - “Pancreatic cysts are strikingly common, mostly incidental findings. Although the majority of these cysts are associated with a very low risk of malignant transformation, a minority may offer an opportunity to recognize and eliminate highrisk precursors of pancreatic cancer. Several guidelines provide recommendations for evaluation, treatment, and surveillance, but they are based on expert opinion rather than solid evidence. Fortunately, an initiative to develop a unified global guideline in the next 1 to 2 years is widely endorsed.”
Pancreatic Cysts
Tamas A. Gonda, Djuna L. Cahen, and James J. Farrell
N Engl J Med 2024;391:832-43. - “An important goal in the management of pancreatic cysts is to reduce the surveillance burden for low-risk lesions while improving the recognition of malignant and premalignant cysts. To accomplish this, prospective studies are needed to determine the true predictive value of known risk factors for cancer. Also, advances in our understanding of the molecular evolution of cystic precursors will lead to the identification of increasingly sensitive biomarkers derived from either cyst fluid, pancreatic juice, or blood. The integration of radiomics (machine learning and artificial intelligence) and advances in endoscopic imaging, such as needle-based, intracystic confocal microscopy, may enhance the sensitivity of risk stratification. Although surgery has become much safer, alternative and less invasive techniques are needed, especially for prophylactic interventions.”
Pancreatic Cysts
Tamas A. Gonda, Djuna L. Cahen, and James J. Farrell
N Engl J Med 2024;391:832-43. - “The current approach to management relies on identifying the cyst type and conducting a multimodal assessment of the risk of cancer, an assessment that is mostly noninvasive, with selective use of endoscopic ultrasonography and tissue sampling. The best personalized approach will be provided by models that combine risk factors, clinical variables, imaging characteristics, and molecular markers. Treatment and surveillance decisions should follow an algorithmic framework that is overseen by a multidisciplinary team and that incorporates shared decision making with the patient.”
Pancreatic Cysts
Tamas A. Gonda, Djuna L. Cahen, and James J. Farrell
N Engl J Med 2024;391:832-43. 
- Background. PanNETs are a rare group of pancreatic tumors that display heterogeneous histopathological and clinical behavior. Nodal disease has been established as one of the strongest predictors of patient outcomes in PanNETs. Lack of accurate preoperative assessment of nodal disease is a major limitation in the management of these patients, in particular those with small (< 2 cm) low-grade tumors. The aim of the study was to evaluate the ability of radiomic features (RF) to preoperatively predict the presence of nodal disease in pancreatic neuroendocrine tumors (PanNETs).
Preoperative Prediction of Lymph Node Metastases in Nonfunctional Pancreatic Neuroendocrine Tumors Using a Combined CT Radiomics-Clinical Model.
Ahmed TM, Zhu Z, Yasrab M, Blanco A, Kawamoto S, He J, Fishman EK, Chu L, Javed AA
Ann Surg Oncol. 2024 Aug 23. doi: 10.1245/s10434-024-16064-4. Epub ahead of print - Results. Of the 320 patients included in the study, 92 (28.8%) had nodal disease based on histopathological assessment of the surgical specimen. A radiomic signature based on ten selected RF was developed. Clinicopathological characteristics predictive of nodal disease included tumor grade and size. Upon internal validation the combined radiomics and clinical feature model demonstrated adequate performance (AUC 0.80) in identifying nodal disease. The modelmaccurately identified nodal disease in 85% of patients with small tumors (< 2 cm).
Conclusions. Non-invasive preoperative assessment of nodal disease using RF and clinicopathological characteristics is feasible.
Preoperative Prediction of Lymph Node Metastases in Nonfunctional Pancreatic Neuroendocrine Tumors Using a Combined CT Radiomics-Clinical Model.
Ahmed TM, Zhu Z, Yasrab M, Blanco A, Kawamoto S, He J, Fishman EK, Chu L, Javed AA
Ann Surg Oncol. 2024 Aug 23. doi: 10.1245/s10434-024-16064-4. Epub ahead of print - ”In conclusion, this study presents a novel tool on the basis of RFs and clinical factors for accurate prediction of nodal disease in NF-PanNETs. Furthermore, we demonstrated that addition of RFs to clinical factors can make this model more robust and accurate. Further validation of this model is required to assess its performance in external cohorts. If validated, this tool could allow for non-invasive serial assessment of nodal disease in patients with well differentiated nonfunctioning PanNETs to tailor management plans and provide precise therapy on the basis of each patient’s disease biology.”
Preoperative Prediction of Lymph Node Metastases in Nonfunctional Pancreatic Neuroendocrine Tumors Using a Combined CT Radiomics-Clinical Model.
Ahmed TM, Zhu Z, Yasrab M, Blanco A, Kawamoto S, He J, Fishman EK, Chu L, Javed AA
Ann Surg Oncol. 2024 Aug 23. doi: 10.1245/s10434-024-16064-4. Epub ahead of print 
- Purpose: The purpose of this study was to develop a radiomics-based algorithm to identify small pancreatic neuroendocrine tumors(PanNETs) on CT and evaluate its robustness across manual and automated segmentations, exploring the feasibility of automated screening.
Conclusion: Radiomics features identify small PanNETs, with stable performance when extracted using automated segmentations. These models demonstrate high sensitivity, complementing the high specificity of radiologists, and could serve as opportunistic screeners.
Radiomics machine learning algorithm facilitates detection of small pancreatic neuroendocrine tumors on CT.
Lopez-Ramirez F, Soleimani S, Azadi JR, Sheth S, Kawamoto S, Javed AA, Tixier F, Hruban RH, Fishman EK, Chu LC.
Diagn Interv Imaging. 2024 Sep 14:S2211-5684(24)00172-4. doi: 10.1016/j.diii.2024.08.003. Epub ahead of print. PMID: 39278763 . - Results:A total of 135 patients with 142 PanNETs,and135 healthy controls were included.There were 168 women and 102 men,with a mean age of 55.4 +/-11.6(standard deviation) years(range:20−85years). Median PanNET size was 1.3cm (Q1,1.0;Q3,1.5;range:0.5−1.9).The arterial phase Light GBM model achieved the best performance in the test set,with 90% sensitivity (95% confidence interval[CI]:80−98),76% specificity (95%CI:62−88)and an AUC of 0.87 (95% CI:0.79−0.94).Using features from the automated segmentations,this model achieved an AUC of 0.86(95%CI:0.79−0.93). In comparison, the radiologists achieved a mean 50% sensitivity and 100% specificity using arterial phase CT images.
Radiomics machine learning algorithm facilitates detection of small pancreatic neuroendocrine tumors on CT.
Lopez-Ramirez F, Soleimani S, Azadi JR, Sheth S, Kawamoto S, Javed AA, Tixier F, Hruban RH, Fishman EK, Chu LC.
Diagn Interv Imaging. 2024 Sep 14:S2211-5684(24)00172-4. doi: 10.1016/j.diii.2024.08.003. Epub ahead of print. 
Radiomics machine learning algorithm facilitates detection of small pancreatic neuroendocrine tumors on CT.
Lopez-Ramirez F, Soleimani S, Azadi JR, Sheth S, Kawamoto S, Javed AA, Tixier F, Hruban RH, Fishman EK, Chu LC.
Diagn Interv Imaging. 2024 Sep 14:S2211-5684(24)00172-4. doi: 10.1016/j.diii.2024.08.003. Epub ahead of print.
Radiomics machine learning algorithm facilitates detection of small pancreatic neuroendocrine tumors on CT.
Lopez-Ramirez F, Soleimani S, Azadi JR, Sheth S, Kawamoto S, Javed AA, Tixier F, Hruban RH, Fishman EK, Chu LC.
Diagn Interv Imaging. 2024 Sep 14:S2211-5684(24)00172-4. doi: 10.1016/j.diii.2024.08.003. Epub ahead of print.
Radiomics machine learning algorithm facilitates detection of small pancreatic neuroendocrine tumors on CT.
Lopez-Ramirez F, Soleimani S, Azadi JR, Sheth S, Kawamoto S, Javed AA, Tixier F, Hruban RH, Fishman EK, Chu LC.
Diagn Interv Imaging. 2024 Sep 14:S2211-5684(24)00172-4. doi: 10.1016/j.diii.2024.08.003. Epub ahead of print.- “In conclusion, this study demonstrates the feasibility of radiomics-based tools, with features extracted from manual and automatic pancreas segmentations, to detect small PanNETs with higher sensitivity than two experienced radiologists.These preliminary results suggest that radiomics could potentially serve as a second reader or opportunist screener for detection of low-stage disease and ultimately impact clinical care.”
Radiomics machine learning algorithm facilitates detection of small pancreatic neuroendocrine tumors on CT.
Lopez-Ramirez F, Soleimani S, Azadi JR, Sheth S, Kawamoto S, Javed AA, Tixier F, Hruban RH, Fishman EK, Chu LC.
Diagn Interv Imaging. 2024 Sep 14:S2211-5684(24)00172-4. doi: 10.1016/j.diii.2024.08.003. Epub ahead of print.
- Background: We identified computed tomography (CT)-derived radiomic features predictive of tumor progression within three months, then examined their ability to prognosticate overall survival (OS) along with clinical features in pancreatic cancer. We evaluated these features in patients with unresected pancreatic cancer who underwent stereotactic body radiation therapy (SBRT) in sequence with chemotherapy, but not surgery.
Conclusions: CT-derived radiomic features predict rapid tumor progression following SBRT, confer nearly a twofold increase in mortality risk, and, along with patient age, enhance the identification of patients with stage II-IIIpancreatic cancer with poor OS.
Utility of radiomic features in predicting clinical outcomes in stage II-III pancreatic cancer.
Haruka Itakura,et al
American Society of Clinical Oncology Sept 2024 (abstract) - “In this retrospective study, we examined a cohort of 101 patients with stage II-III pancreatic cancer who underwent SBRT with sequential chemotherapy at a single institution (Stanford Health Care) between 1999- 2020. From their pre-SBRT contrast-enhanced CT images with segmented tumors, delineating regions-of-interest, we extracted 900 radiomic (quantitative pixel-level imaging characteristic) features. In the first phase, we identified radiomic features that predicted rapid tumor progression within three months following SBRT.”
Utility of radiomic features in predicting clinical outcomes in stage II-III pancreatic cancer.
Haruka Itakura,et al
American Society of Clinical Oncology Sept 2024 (abstract) - Background: When determining the initial chemotherapy regimen for advanced or metastatic pancreatic cancer, various factors must be evaluated. The decision between FOLFIRINOX and Gemcitabine/Nab-paclitaxel (GnP) is challenging, as patient survival hinges on the efficacy and toxicity profiles of these treatments, alongside individual patient characteristics and vulnerabilities. This study aims to guide the selection of an appropriate first-line chemotherapy regimen for advanced or metastatic pancreatic cancer by leveraging machine learning (ML) methods to predict survival outcomes. Conclusions: We developed the ML models that can compute the probability of OS based on the routinely collected data from patients with advanced or metastatic pancreatic cancer. To the best of our knowledge, this is the first ML solution aimed at aiding clinicians in the selection of the first-line chemotherapy regimen for pancreatic cancer.
Predicting chemotherapy response in patients with advanced or metastatic pancreatic cancer using machine learning.
Moonho Kim, Gyucheol Choi, Jamin Koo
American Society of Clinical Oncology. Sept 2024 - Results: The median age of the patients was 66 years, with 62.3% being male. The MLnmodels achieved the ROC-AUC of 0.81 when predicting OS after 12 months following the initial administration of FOLFIRINOX (n=61) or GnP (n=47). Five (peritoneal metastases, other metastases, bilirubin level, white blood cell counts, and retroperitoneal lymph node metastases) or four (age, tumor location, sex, and metastatic status) covariates were used to achieve the predictive accuracy for the two regimens, respectively. The median OS of the high versus low risk groups of FOLFIRINOX predicted by the ML models were significantly different (7 vs 18 months, P, 0.01), recording the hazard ratio (HR) of 2.79 (95% CI, 1.47-5.26). Similarly, the median OS of the high and low risk groups of GnP were significantly different (8 vs 16 months,P , 0.001, HR 3.50, 95% CI, 1.60-7.66).
Predicting chemotherapy response in patients with advanced or metastatic pancreatic cancer using machine learning.
Moonho Kim, Gyucheol Choi, Jamin Koo
American Society of Clinical Oncology. Sept 2024
- “Between June 2012 and December 2022, a total of 4039 patients’ multiphase (arterial phase and portal venous phase) contrastenhanced CT images from six hospitals were included under the following inclusion criteria: Patients (1) were eighteen years or older; (2) did not have a history of hepatectomy, transarterial chemotherapy (TACE), or radiofrequency ablation (RFA) before CT imaging; (3) had pathologically confirmed malignant tumors; and (4) had benign tumors confirmed either by consensus among three radiologists or by follow-up of at least six months using two imaging modalities. The method used for retrospective data collection and basic patientinformation including sex and age are depicted in Fig. 1a and Table 1, respectively. Furthermore, clinical testing was conducted on two real world clinical evaluation queues (Fig. 1b): West China Tianfu Center and Sanya People’s Hospital. At Tianfu Center, we examined 184 cases, while at Sanya People’s Hospital, 235 cases were assessed. Gender andAge assignment was based on government-issued IDs.”
Focal liver lesion diagnosis with deep learning and multistage CT imaging
Yi Wei et al.
Nature Communications | ( 2024) 15:7040 - Background/objectives: Pancreatic cyst management can be distilled into three separate pathways -- discharge, monitoring or surgery based on the risk of malignant transformation. This study compares the performance of artificial intelligence (AI) models to clinical care for this task.
Methods: Two explainable boosting machine (EBM) models were developed and evaluated using clinical features only, or clinical features and cyst fluid molecular markers (CFMM) using a publicly available dataset, consisting of 850 cases (median age 64; 65 % female) with independent training (429 cases) and holdout test cohorts (421 cases). There were 137 cysts with no malignant potential, 114 malignant cysts, and 599 IPMNs and MCNs.
Performance of explainable artificial intelligence in guiding the management of patients with a pancreatic cyst.
Lavista Ferres JM, Oviedo F, Robinson C, Chu L, Kawamoto S, Afghani E, He J, Klein AP, Goggins M, Wolfgang CL, Javed AA, Dodhia R, Papadopolous N, Kinzler K, Hruban RH, Weeks WB, Fishman EK, Lennon AM.
Pancreatology. 2024 Sep 2:S1424-3903(24)00730-0. doi: 10.1016/j.pan.2024.09.001. Epub ahead of print. PMID: 39261223. - Results: The EBM and EBM with CFMM models had higher accuracy for identifying patients requiring monitoring (0.88 and 0.82) and surgery (0.66 and 0.82) respectively compared with current clinical care (0.62 and 0.58). For discharge, the EBM with CFMM model had a higher accuracy (0.91) than either the EBM model (0.84) or current clinical care (0.86). In the cohort of patients who underwent surgical resection, use of the EBM-CFMM model would have decreased the number of unnecessary surgeries by 59 % (n=92), increased correct surgeries by 7.5 % (n=11), identified patients who require monitoring by 122 % (n=76), and increased the number of patients correctly classified for discharge by 138 % (n=18) compared to clinical care.
Conclusions: EBM models had greater sensitivity and specificity for identifying the correct management compared with either clinical management or previous AI models. The model predictions are demonstrated to be interpretable by clinicians.
Performance of explainable artificial intelligence in guiding the management of patients with a pancreatic cyst.
Lavista Ferres JM, Oviedo F, Robinson C, Chu L, Kawamoto S, Afghani E, He J, Klein AP, Goggins M, Wolfgang CL, Javed AA, Dodhia R, Papadopolous N, Kinzler K, Hruban RH, Weeks WB, Fishman EK, Lennon AM.
Pancreatology. 2024 Sep 2:S1424-3903(24)00730-0. doi: 10.1016/j.pan.2024.09.001. Epub ahead of print. PMID: 39261223. - “Conclusions: EBM models had greater sensitivity and specificity for identifying the correct management compared with either clinical management or previous AI models. The model predictions are demonstrated to be interpretable by clinicians.”
Performance of explainable artificial intelligence in guiding the management of patients with a pancreatic cyst.
Lavista Ferres JM, Oviedo F, Robinson C, Chu L, Kawamoto S, Afghani E, He J, Klein AP, Goggins M, Wolfgang CL, Javed AA, Dodhia R, Papadopolous N, Kinzler K, Hruban RH, Weeks WB, Fishman EK, Lennon AM.
Pancreatology. 2024 Sep 2:S1424-3903(24)00730-0. doi: 10.1016/j.pan.2024.09.001. Epub ahead of print. PMID: 39261223. - “The management of patients with pancreatic cysts can be distilled into three separate pathways based on the risk of malignant transformation. Cysts with pancreatic cancer or high-grade dysplasia, such as cystic degeneration of pancreatic adenocarcinoma, an IPMN with high-grade dysplasia or associated invasive adenocarcinoma, should be surgically resected . Patients harboring an IPMN or MCN with low grade dysplasia are recommended for surveillance. Patients with a pancreatic cyst with no malignant potential, such as a pseudocyst or a serous cystadenoma (SCA), require no follow-up and these patients can be discharged.”
Performance of explainable artificial intelligence in guiding the management of patients with a pancreatic cyst.
Lavista Ferres JM, Oviedo F, Robinson C, Chu L, Kawamoto S, Afghani E, He J, Klein AP, Goggins M, Wolfgang CL, Javed AA, Dodhia R, Papadopolous N, Kinzler K, Hruban RH, Weeks WB, Fishman EK, Lennon AM.
Pancreatology. 2024 Sep 2:S1424-3903(24)00730-0. doi: 10.1016/j.pan.2024.09.001. Epub ahead of print. PMID: 39261223. - “Correctly preoperatively classifying patients into these three different management pathways is challenging, with large surgical series finding that 25 % of cyst patients who undergo surgical resection have cysts with no malignant potential , while up to 73 % of patients with IPMNs who undergo surgical resection have low-grade dysplasia and in hindsight did not require surgery.”
Performance of explainable artificial intelligence in guiding the management of patients with a pancreatic cyst.
Lavista Ferres JM, Oviedo F, Robinson C, Chu L, Kawamoto S, Afghani E, He J, Klein AP, Goggins M, Wolfgang CL, Javed AA, Dodhia R, Papadopolous N, Kinzler K, Hruban RH, Weeks WB, Fishman EK, Lennon AM.
Pancreatology. 2024 Sep 2:S1424-3903(24)00730-0. doi: 10.1016/j.pan.2024.09.001. Epub ahead of print. PMID: 39261223. - “Artificial intelligence (AI) models are uniquely equipped to handle a large number of diverse and complex features, potentially aiding physicians and patients in making informed decisions. One early example of this is Multivariate Organization of Combinatorial Alterations (MOCA) model, which used combinatorial feature transformations and random sampling with iterative optimization to engineer a subset of composite markers with high predictive power. This machine learning model was applied to 862 patients with pancreatic cysts who underwent surgical resection, and was found to be more accurate than conventional clinical and imaging criteria alone for classifying patients into the three management groups of surgery, surveillance, or discharge.”
Performance of explainable artificial intelligence in guiding the management of patients with a pancreatic cyst.
Lavista Ferres JM, Oviedo F, Robinson C, Chu L, Kawamoto S, Afghani E, He J, Klein AP, Goggins M, Wolfgang CL, Javed AA, Dodhia R, Papadopolous N, Kinzler K, Hruban RH, Weeks WB, Fishman EK, Lennon AM.
Pancreatology. 2024 Sep 2:S1424-3903(24)00730-0. doi: 10.1016/j.pan.2024.09.001. Epub ahead of print. PMID: 39261223. 
Performance of explainable artificial intelligence in guiding the management of patients with a pancreatic cyst.
Lavista Ferres JM, Oviedo F, Robinson C, Chu L, Kawamoto S, Afghani E, He J, Klein AP, Goggins M, Wolfgang CL, Javed AA, Dodhia R, Papadopolous N, Kinzler K, Hruban RH, Weeks WB, Fishman EK, Lennon AM.
Pancreatology. 2024 Sep 2:S1424-3903(24)00730-0. doi: 10.1016/j.pan.2024.09.001. Epub ahead of print. PMID: 39261223.
Performance of explainable artificial intelligence in guiding the management of patients with a pancreatic cyst.
Lavista Ferres JM, Oviedo F, Robinson C, Chu L, Kawamoto S, Afghani E, He J, Klein AP, Goggins M, Wolfgang CL, Javed AA, Dodhia R, Papadopolous N, Kinzler K, Hruban RH, Weeks WB, Fishman EK, Lennon AM.
Pancreatology. 2024 Sep 2:S1424-3903(24)00730-0. doi: 10.1016/j.pan.2024.09.001. Epub ahead of print. PMID: 39261223.
Performance of explainable artificial intelligence in guiding the management of patients with a pancreatic cyst.
Lavista Ferres JM, Oviedo F, Robinson C, Chu L, Kawamoto S, Afghani E, He J, Klein AP, Goggins M, Wolfgang CL, Javed AA, Dodhia R, Papadopolous N, Kinzler K, Hruban RH, Weeks WB, Fishman EK, Lennon AM.
Pancreatology. 2024 Sep 2:S1424-3903(24)00730-0. doi: 10.1016/j.pan.2024.09.001. Epub ahead of print. PMID: 39261223.- “The results are even more striking when compared with clinical care. In this test cohort of patients, all of whom underwent surgical resection, use of the EBM with CFMM model decreases the number of unnecessary surgeries by 59 % (n=92), increases the number of correct surgeries by 7.5 % (n=11), better identifies patients who truly require monitoring by 122 % (n=76), and increases the number of patients correctly classified as being safe to discharge by 138 % (n=18) compared to clinical care. Overall, in this cohort of patients the use of the EBM with CFMM could have changed the management of at least 25 % of patients.”
Performance of explainable artificial intelligence in guiding the management of patients with a pancreatic cyst.
Lavista Ferres JM, Oviedo F, Robinson C, Chu L, Kawamoto S, Afghani E, He J, Klein AP, Goggins M, Wolfgang CL, Javed AA, Dodhia R, Papadopolous N, Kinzler K, Hruban RH, Weeks WB, Fishman EK, Lennon AM.
Pancreatology. 2024 Sep 2:S1424-3903(24)00730-0. doi: 10.1016/j.pan.2024.09.001. Epub ahead of print. PMID: 39261223. - “This study shows the potential of an AI model to incorporate multiple features and its ability to generate a correct management plan which can help guide care for patients and their physicians. In this study, the performance of the EBM model was superior to clinical management in correctly identifying which patients required surveillance or should be referred for surgery. The impact of the CFMM can be seen when we look at the global feature importance score, where 6 of the top 9 features used by the model are CFMMs. Overall, the use of EBM with CFMM model couldhave changed the management of at least 25 % (n=105) of the patients compared with clinical management.”
Performance of explainable artificial intelligence in guiding the management of patients with a pancreatic cyst.
Lavista Ferres JM, Oviedo F, Robinson C, Chu L, Kawamoto S, Afghani E, He J, Klein AP, Goggins M, Wolfgang CL, Javed AA, Dodhia R, Papadopolous N, Kinzler K, Hruban RH, Weeks WB, Fishman EK, Lennon AM.
Pancreatology. 2024 Sep 2:S1424-3903(24)00730-0. doi: 10.1016/j.pan.2024.09.001. Epub ahead of print. PMID: 39261223. - “The EBM model has a number of features which are very attractive for use in clinical care. First, it has an explainable aspect which provides a transparent understanding of the features that are used to generate the prediction. In contrast with other machine learning models, such as deep neural networks, the feature contributions used to generate predictions of the EBM model are easy to quantify and isolate. This transparency allows health care providers to understand how features were used in the model and confirm that they make clinical and biological sense. Furthermore, instead of providing a positive or negative output, the EBM model outputs a calibrated probability vector for each predicted outcome for an individual patient. Both feature explanations and calibrated probabilities affords clinicians and patients a richer perspective of model operation and uncertainty when determining clinical management.”
Performance of explainable artificial intelligence in guiding the management of patients with a pancreatic cyst.
Lavista Ferres JM, Oviedo F, Robinson C, Chu L, Kawamoto S, Afghani E, He J, Klein AP, Goggins M, Wolfgang CL, Javed AA, Dodhia R, Papadopolous N, Kinzler K, Hruban RH, Weeks WB, Fishman EK, Lennon AM.
Pancreatology. 2024 Sep 2:S1424-3903(24)00730-0. doi: 10.1016/j.pan.2024.09.001. Epub ahead of print. PMID: 39261223. - “Future work should validate the model in a prospective cohort of patients including patients who undergo surgical resection and those undergoing surveillance. Finally, the feature contributions and explanations are predictive but not necessarily casual, in the sense that observed trends could be affected by interaction with unknown confounders or variables not captured as clinical features. As models are retrained in larger datasets is important to verify that overall feature importance is comparable across models, and prospectively evaluate explanations and the high uncertainty/error-prone probability thresholds with clinical judgement.”
Performance of explainable artificial intelligence in guiding the management of patients with a pancreatic cyst.
Lavista Ferres JM, Oviedo F, Robinson C, Chu L, Kawamoto S, Afghani E, He J, Klein AP, Goggins M, Wolfgang CL, Javed AA, Dodhia R, Papadopolous N, Kinzler K, Hruban RH, Weeks WB, Fishman EK, Lennon AM.
Pancreatology. 2024 Sep 2:S1424-3903(24)00730-0. doi: 10.1016/j.pan.2024.09.001. Epub ahead of print. PMID: 39261223. - “In conclusion, we have developed and evaluated two AI models for patients with pancreatic cysts, using clinical features alone or combined with CFMM, which demonstrate greater accuracy for identifying the correct management recommendation of discharge, monitoring or surgery compared with either clinical management or prior AI models. These models allow health care providers and patients to understand the probability of a management recommendation and interpret the impact of features used to make predictions.”
Performance of explainable artificial intelligence in guiding the management of patients with a pancreatic cyst.
Lavista Ferres JM, Oviedo F, Robinson C, Chu L, Kawamoto S, Afghani E, He J, Klein AP, Goggins M, Wolfgang CL, Javed AA, Dodhia R, Papadopolous N, Kinzler K, Hruban RH, Weeks WB, Fishman EK, Lennon AM.
Pancreatology. 2024 Sep 2:S1424-3903(24)00730-0. doi: 10.1016/j.pan.2024.09.001. Epub ahead of print. PMID: 39261223.
- “Diagnosing liver lesions is crucial for treatment choices and patient outcomes. This study develops an automatic diagnosis system for liver lesions using multiphase enhanced computed tomography (CT). A total of 4039 patients from six data centers are enrolled to develop Liver Lesion Network (LiLNet). LiLNet identifies focal liver lesions, including hepatocellular carcinoma (HCC), intrahepatic cholangiocarcinoma (ICC), metastatic tumors (MET), focal nodular hyperplasia (FNH), hemangioma (HEM), and cysts (CYST). Validated in four external centers and clinically verified in two hospitals, LiLNet achieves an accuracy (ACC) of 94.7% and an area under the curve (AUC) of 97.2% for benign and malignant tumors. For HCC, ICC, and MET, the ACC is 88.7% with an AUC of 95.6%. For FNH, HEM, and CYST, the ACC is 88.6% with an AUC of 95.9%. LiLNet can aid in clinical diagnosis, especially in regions with a shortage of radiologists.”
Focal liver lesion diagnosis with deep learning and multistage CT imaging
Yi Wei et al.
Nature Communications | ( 2024) 15:7040 - “In this study, we demonstrate the performance of our AI system, LiLNet, in distinguishing six common types of focal liver lesions. We develop the model using data from six centers and assess its generalization through extensive testing on a test set and four externalvalidation centers. We compare LiLNet’s performance with radiologists’ interpretations of contrast-enhanced CT images in a reader study. To address real-world clinical implementation, we deploy LiLNet in two hospitals, integrating it into routine workflows across outpatient, emergency, and inpatient settings. This integration evaluates the system’s performance in various clinical environments, ensuring its robustness and reliability in practical use.”
Focal liver lesion diagnosis with deep learning and multistage CT imaging
Yi Wei et al.
Nature Communications | ( 2024) 15:7040 - “We used a test set of 6743 images from 221 patients at West China Hospital of Sichuan University to compare the diagnostic ability of LiLNet with that of radiologists. The evaluation involved three radiologists with varying levels of experience. Radiologists independently labeled the 221 patients based on multiphase contrast-enhanced CT images. LiLNet demonstrated a diagnostic accuracy of 91.0% for distinguishing between benign and malignant tumors, 82.9% for distinguishing between malignant tumors, and 92.3% for distinguishing between benign tumors. Compared to junior-level radiologists, LiLNet achieved 4.6% greater accuracy for benign and malignant diagnosis, 4.1% greater accuracy for middle-level radiologists, and 2.3% greater accuracy for senior level radiologists. The diagnostic accuracy of radiologists for diagnosing malignant tumors was similar. Notably, compared with radiologists, LiLNet achieved a substantial 18% improvement in diagnostic accuracy. Additionally, in diagnosing benign tumors, LiLNet outperformed junior-level practitioners by 20%, middle-level practitioners by 10%, and senior-level practitioners by 6.7%.”
Focal liver lesion diagnosis with deep learning and multistage CT imaging
Yi Wei et al.
Nature Communications | ( 2024) 15:7040 
Focal liver lesion diagnosis with deep learning and multistage CT imaging
Yi Wei et al.
Nature Communications | ( 2024) 15:7040- “We utilized patients’ name-ID as the unique identifier to prevent duplicate IDs. Duplicate samples with the same name-ID were systematically removed, and patients were randomly assigned to either the training set or testing set to prevent data overlap. As shown in Fig. 1a, the training set comprised images from 1580 patients from West ChinaHospital of SichuanUniversity and Sanya People’sHospital. The testing cohort consisted of 1308 patients from West China Hospital of Sichuan University, while external validation cohorts included 1151 patients from Henan Provincial People’s Hospital, The First Affiliated Hospital of Chengdu Medical College, Leshan People’s Hospital, and Guizhou Provincial People’s Hospital.”
Focal liver lesion diagnosis with deep learning and multistage CT imaging
Yi Wei et al.
Nature Communications | ( 2024) 15:7040 - “Between June 2012 and December 2022, a total of 4039 patients’ multiphase (arterial phase and portal venous phase) contrastenhanced CT images from six hospitals were included under the following inclusion criteria: Patients (1) were eighteen years or older; (2) did not have a history of hepatectomy, transarterial chemotherapy (TACE), or radiofrequency ablation (RFA) before CT imaging; (3) had pathologically confirmed malignant tumors; and (4) had benign tumors confirmed either by consensus among three radiologists or by follow-up of at least six months using two imaging modalities. The method used for retrospective data collection and basic patientinformation including sex and age are depicted in Fig. 1a and Table 1, respectively. Furthermore, clinical testing was conducted on two real world clinical evaluation queues (Fig. 1b): West China Tianfu Center and Sanya People’s Hospital. At Tianfu Center, we examined 184 cases, while at Sanya People’s Hospital, 235 cases were assessed. Gender andAge assignment was based on government-issued IDs.”
Focal liver lesion diagnosis with deep learning and multistage CT imaging
Yi Wei et al.
Nature Communications | ( 2024) 15:7040
- Background To develop and compare machine learning models based on triphasic contrast-enhanced CT (CECT) for distinguishing between benign and malignant renal tumors.
Materials and Methods In total, 427 patients were enrolled from two medical centers: Center 1 (serving as the training set) and Center 2 (serving as the external validation set). First, 1781 radiomic features were individually extracted from corticomedullary phase (CP), nephrographic phase (NP), and excretory phase (EP) CECT images, after which 10 features were selected by the minimum redundancy maximum relevance method. Second, random forest (RF) models were constructed from single-phase features (CP, NP, and EP) as well as from the combination of features from all three phases (TP). Third,the RF models were assessed in the training and external validation sets. Finally, the internal prediction mechanisms of the models were explained by the SHapley Additive exPlanations (SHAP) approach.
Interpretable multiphasic CT‑based radiomic analysis for preoperatively differentiating benign and malignant solid renal tumors: a multicenter study
Yaohai Wu et al.
Abdominal Radiology (2024) 49:3096–3106 - Results A total of 266 patients with renal tumors from Center 1 and 161 patients from Center 2 were included. In the training set, the AUCs of the RF models constructed from the CP, NP, EP, and TP features were 0.886, 0.912, 0.930, and 0.944, respectively. In the external validation set, the models achieved AUCs of 0.860, 0.821, 0.921, and 0.908, respectively. The “original_shape_Flatness” feature played the most important role in the prediction outcome for the RF model based on EP features according to the SHAP method.
Conclusions The four RF models efficiently differentiated benign from malignant solid renal tumors, with the EP feature based RF model displaying the best performance.
Interpretable multiphasic CT‑based radiomic analysis for preoperatively differentiating benign and malignant solid renal tumors: a multicenter study
Yaohai Wu et al.
Abdominal Radiology (2024) 49:3096–3106 - “In summary, all four RF models efficiently differentiated benign from malignant solid renal tumors, and the RF model based on EP features displayed the best performance. The feature “original_shape_Flatness” played the greatest role in predicting the outcome of RF model based on EP image features.”
Interpretable multiphasic CT‑based radiomic analysis for preoperatively differentiating benign and malignant solid renal tumors: a multicenter study
Yaohai Wu et al.
Abdominal Radiology (2024) 49:3096–3106
- Introduction: In health care, artificial intelligence (AI)–powered clinical documentation tools aim to reduce physician burnout, optimize workflows, and refine the accuracy of clinician documentation. Some of these AI tools can generate a preliminary clinical note by listening to the interaction between a clinician and a patient, then synthesizing the conversation into a draft clinical note. We evaluated clinicians’ experiences with clinical documentation before and after implementing an AI-powered clinical documentation tool. Discussion:Approximately half of clinicians using the AI-powered clinical documentation tool based on interest reported a positive outcome, potentially reducing burnout. However, a significant subset did not find time-saving benefits or improved EHR experience. Study limitations include potential selection bias and recall bias in both groups. Further research is needed to identify opportunities for improvement and understand the impact on different clinician subsets and health systems.
- Objective: To evaluate the accuracy and quality of AI-generated chest radiograph interpretations in the emergency department setting.
Design, setting, and participants: This was a retrospective diagnostic study of 500 randomly sampled emergency department encounters at a tertiary care institution including chest radiographs interpreted by both a teleradiology service and on-site attending radiologist from January 2022 to January 2023. An AI interpretation was generated for each radiograph. The 3 radiograph interpretations were each rated in duplicate by 6 emergency department physicians using a 5-point Likert scale.
Main outcomes and measures: The primary outcome was any difference in Likert scores between radiologist, AI, and teleradiology reports, using a cumulative link mixed model. Secondary analyses compared the probability of each report type containing no clinically significant discrepancy with further stratification by finding presence, using a logistic mixed-effects model. Physician comments on discrepancies were recorded.
Generative Artificial Intelligence for Chest Radiograph Interpretation in the Emergency Department.
Huang J, Neill L, Wittbrodt M, et al..
JAMA Netw Open. 2023 Oct 2;6(10):e2336100. - Results: A total of 500 ED studies were included from 500 unique patients with a mean (SD) age of 53.3 (21.6) years; 282 patients (56.4%) were female. There was a significant association of report type with ratings, with post hoc tests revealing significantly greater scores for AI (mean [SE] score, 3.22 [0.34]; P < .001) and radiologist (mean [SE] score, 3.34 [0.34]; P < .001) reports compared with teleradiology (mean [SE] score, 2.74 [0.34]) reports. AI and radiologist reports were not significantly different. On secondary analysis, there was no difference in the probability of no clinically significant discrepancy between the 3 report types. Further stratification of reports by presence of cardiomegaly, pulmonary edema, pleural effusion, infiltrate, pneumothorax, and support devices also yielded no difference in the probability of containing no clinically significant discrepancy between the report types.
Conclusions and relevance: In a representative sample of emergency department chest radiographs, results suggest that the generative AI model produced reports of similar clinical accuracy and textual quality to radiologist reports while providing higher textual quality than teleradiologist reports. Implementation of the model in the clinical workflow could enable timely alerts to life-threatening pathology while aiding imaging interpretation and documentation.
Generative Artificial Intelligence for Chest Radiograph Interpretation in the Emergency Department.
Huang J, Neill L, Wittbrodt M, et al..
JAMA Netw Open. 2023 Oct 2;6(10):e2336100. - Key Points
Question How do emergency department physicians rate artificial intelligence (AI)–generated chest radiograph reports for quality and accuracy, compared with in-house radiologist and teleradiology reports?
Findings In this diagnostic study of the developed generative AI model on a representative sample of 500 emergency department chest radiographs from 500 unique patients, the AI model produced reports of similar clinical accuracy and textual quality to radiology reports while providing higher textual quality than teleradiology reports.
Meaning Results suggest that use of the generative AI tool may facilitate timely interpretation of chest radiography by emergency department physicians.
Generative Artificial Intelligence for Chest Radiograph Interpretation in the Emergency Department.
Huang J, Neill L, Wittbrodt M, et al..
JAMA Netw Open. 2023 Oct 2;6(10):e2336100. - “In this diagnostic study accounting for both clinical accuracy and textual quality, results suggest that our AI tool produced reports similar in performance to a radiologist and better than a teleradiology service in a representative sample of ED chest radiographs. AI report ratings were comparable with those of on-site radiologists across all evaluated pathology categories. Model integration in clinical workflows could enable timely alerts to life-threatening pathology while aiding physician imaging interpretation and speeding up documentation. Further efforts to prospectively evaluate clinical impact and generalizability are needed.”
Generative Artificial Intelligence for Chest Radiograph Interpretation in the Emergency Department.
Huang J, Neill L, Wittbrodt M, et al..
JAMA Netw Open. 2023 Oct 2;6(10):e2336100. - Huang et al. developed a multimodal generative AI model and evaluated its ability to produce full radiology reportsfor chest radiographs in the emergency department (ED) setting. An encoder-decoder model was trained on 900,000 chest radiographs and generated a report when given an input chest radiograph and its most recent prior radiograph. A retrospective analysis was performed on 500 unique ED encounters with chest radiographs interpreted by three reader categories: a teleradiology service (all with U.S. residency and board experience), 12 ED radiologists (mean, 14.6 ± 12.5 [SD] years of post residency clinical practice experience), and the AI model. Six ED physicians (10.6 ± 6.4 years of postresidency clinical practice experience) rated the AI, radiologist, and teleradiology reports in a blinded fashion using a 5-point Likert scale.
Beyond the AJR: Early Applications of Generative Artificial Intelligence for Radiology Report Interpretation.
Doo FX, Parekh VS.
AJR Am J Roentgenol. 2024 Aug;223(2):e2330696. - “The results indicated that the AI-generated reports and radiologist reports were of similar quality and accuracy (on a Likert scale, AI reports: 3.22 ± 0.34 [SD], radiologist reports: 3.34 ± 0.34, both of which scored significantly higher than teleradiology reports: 2.74 ± 0.34) (p < .001). There was no significant difference in the probability of reports containing clinically significant discrepancies among the three report types, even when stratified by specific findings. This study suggests that generative AI models can produce chest radiograph reports with clinical accuracy and textual quality comparable with those produced by radiologists, showing the potential of AI to enhance radiology services in EDs, especially in settings in which access to radiology services is limited.”
Beyond the AJR: Early Applications of Generative Artificial Intelligence for Radiology Report Interpretation.
Doo FX, Parekh VS.
AJR Am J Roentgenol. 2024 Aug;223(2):e2330696. - “This study represents a step toward clinical application of generative AI. A key strength is the evaluation of an AI model’s capability to generate full radiology reports, compared with prior narrow AI applications. However, one important factor affecting the generalizability of this Huang et al. study is that clinical quality was scored by referring ED physicians, rather than expert radiologists. A recent study on GPT-4 (OpenAI)-generated radiology report impressions has shown that radiologists overall graded AI impressions to be less coherent, less comprehensive, more factually inconsistent, and more medically harmful, whereas referring providers favored GPT-4 impressions for coherence and diminished harmfulness.”
Beyond the AJR: Early Applications of Generative Artificial Intelligence for Radiology Report Interpretation.
Doo FX, Parekh VS.
AJR Am J Roentgenol. 2024 Aug;223(2):e2330696. - “The debate about AI potentially replacing human radiologists has since shifted toward recognizing AI’s role as a supportive, rather than a substitutive, tool . Even when using AI as an adjunct, radiologists may not necessarily save time, especially if needing to study and correct errors . Although generative AI introduces additional ways that AI can augment radiologist workflow, this study also shows the need to further refine the technology to understand its limitations as an adjunct to human expertise and to apply it to more diverse care settings and patient populations . Also, we must carefully consider factors such as patient privacy, consistency of generated outputs, and the potential impact on clinical workflows .”
Beyond the AJR: Early Applications of Generative Artificial Intelligence for Radiology Report Interpretation.
Doo FX, Parekh VS.
AJR Am J Roentgenol. 2024 Aug;223(2):e2330696. - Takeaway Point
“A generative AI model for chest radiograph interpretations was comparable to radiologists and superior to teleradiology services in the ED setting, when judged by ED physicians, highlighting its potential as a supportive tool in emergency radiology.”
Beyond the AJR: Early Applications of Generative Artificial Intelligence for Radiology Report Interpretation.
Doo FX, Parekh VS.
AJR Am J Roentgenol. 2024 Aug;223(2):e2330696. - “Although there has been progress in addressing sources of algorithmic bias in health care, that progress will be negated if the rapidly evolving AI landscape does not have the safeguards in place to prevent bias in clinical algorithms—there is an opportunity to seize the heightened awareness and growing consensus around the need to pursue these protections. Successfully protecting patients from AI algorithmic bias will require shared responsibility across multiple partners, transparency from AI developers, and deliberate action from health care facilities throughout the AI life cycle. Only then will health care pioneers be positioned to successfully ensure that AI is used in a fair and equitable manner that maximizes patient benefit and advances health equity.”
Addressing AI Algorithmic Bias in Health Care.
Ratwani RM, Sutton K, Galarraga JE.
JAMA. Published online September 04, 2024. doi:10.1001/jama.2024.13486 - “As artificial intelligence (AI) algorithms become an increasingly integral part of health care, ranging from diagnostic decisions and treatment plans to population health management, it is vital that rigorous processes to mitigate algorithmic bias are established. Addressing bias is not only about ensuring fair and just opportunities for optimal health outcomes but also about promoting universal safeguards for patient safety. Biased AI algorithms can result in certain patient populations not receiving appropriate care, potentially leading to significant harm. Previously, an AI algorithm developed to proactively support patients by predicting additional complex care needs yielded biased results along racial lines. The algorithm used health care costs as its target variable, underrepresenting Black patients due to systemic barriers in access to care despite their having a significant burden of illness. The algorithm may have reduced the number of Black patients identified for extra care by more than one-half.”
Addressing AI Algorithmic Bias in Health Care.
Ratwani RM, Sutton K, Galarraga JE.
JAMA. Published online September 04, 2024. doi:10.1001/jama.2024.13486 - ”In the future many of us will find that our professional success depends on our ability to elicit the best possible output from large language models (LLMs) like ChatGPT—and to learn and grow along with them. To excel in this new era of AI-human collaboration, most people will need one or more of what we call “fusion skills”—intelligent interrogation, judgment integration, and reciprocal apprenticing.”
Embracing Gen AI at Work
H. James Wilson and Paul R. Daugherty
Harvard Business Review (September-October 2024) - Intelligent interrogation involves prompting LLMs (or in lay terms, giving them instructions) in ways that will produce measurably better reasoning and outcomes. Put simply, it’s the skill of thinking with AI. Judgment integration is about bringing in your human discernment when a gen AI model is uncertain about what to do or lacks the necessary business or ethical context in its reasoning. The idea is to make the results of human-machine interactions more trustworthy.
Judgment integration requires sensing where, when, and how to step in, and its effectiveness is measured by the reliability, accuracy, and explainability of the AI’s output.
With reciprocal apprenticing, you help AI learn about your business tasks and needs by incorporating rich data and organizational knowledge into the prompts you give it, thereby training it to be your cocreator. It’s the skill of tailoring gen AI to your company’s specific business context so that it can achieve the outcomes you want. As you do that, you yourself learn how to train the AI to tackle more-sophisticated challenges. Once a capability that only data scientists and analytics experts building data models needed, reciprocal apprenticing has become increasingly crucial in nontechnical roles. - “The AI revolution isn’t coming; it’s already here, with leading companies using the technology to reimagine processes across industries, functions, and jobs. Gen AI has dramatically raised the bar, requiring us to think with AI, ensure that we trust it, and continually tailor it—and ourselves—to perform better. Though gen AI is part of the extended movement to create more-symbiotic relationships between humans and machines, it’s also unique in the annals of technology. No other major innovation in history has taken off so fast. Knowledge work is set to be transformed more quickly and powerfully than many of us can even imagine. Get ready. The future of business will be driven not by gen AI alone but by the people who know how to use it most effectively.”
Embracing Gen AI at Work
H. James Wilson and Paul R. Daugherty
Harvard Business Review (September-October 2024) - “In this retrospective study, we examined a cohort of 101 patients with stage II-III pancreatic cancer who underwent SBRT with sequential chemotherapy at a single institution (Stanford Health Care) between 1999- 2020. From their pre-SBRT contrast-enhanced CT images with segmented tumors, delineating regions-of-interest, we extracted 900 radiomic (quantitative pixel-level imaging characteristic) features. In the first phase, we identified radiomic features that predicted rapid tumor progression within three months following SBRT.”
Utility of radiomic features in predicting clinical outcomes in stage II-III pancreatic cancer.
Haruka Itakura,et al
American Society of Clinical Oncology Sept 2024 (abstract) - Background: We identified computed tomography (CT)-derived radiomic features predictive of tumor progression within three months, then examined their ability to prognosticate overall survival (OS) along with clinical features in pancreatic cancer. We evaluated these features in patients with unresected pancreatic cancer who underwent stereotactic body radiation therapy (SBRT) in sequence with chemotherapy, but not surgery.
Conclusions: CT-derived radiomic features predict rapid tumor progression following SBRT, confer nearly a twofold increase in mortality risk, and, along with patient age, enhance the identification of patients with stage II-IIIpancreatic cancer with poor OS.
Utility of radiomic features in predicting clinical outcomes in stage II-III pancreatic cancer.
Haruka Itakura,et al
American Society of Clinical Oncology Sept 2024 (abstract)
Kidney
- “Hereditary renal mass syndromes, although rare, account for at least 3–5% of kidney cancers and significantly impact affected families. Von Hippel–Lindau syndrome, tuberous sclerosis complex, Birt–Hogg–Dube syndrome, hereditary paraganglioma/pheochromocytoma (PGL/mm PCC) syndrome/succinate dehydrogenase deficiency, hereditary leiomyomatosis and renal cell cancer (HLRCC)/fumarate hydratase deficiency, PTEN hamartoma syndrome, BRCA1-associated protein 1 (BAP1) tumor disposition syndrome, hereditary papillary renal cell carcinoma, and familial clear cell renal cell cancer with chromosome 3 translocation.”
Hereditary renal mass syndromes: a pictorial review
Acacia H. Yoon1 · Justin R. Tse2
Abdominal Radiology 2024 https://doi.org/10.1007/s00261-024-04534-y 
Hereditary renal mass syndromes: a pictorial review
Acacia H. Yoon1 · Justin R. Tse2
Abdominal Radiology 2024 https://doi.org/10.1007/s00261-024-04534-y- “Birt–Hogg–Dubé syndrome (BHD) is caused by an inactivating germline mutation in the folliculin tumor suppressor gene (FLCN) . Patients have a 19–35% likelihood of developing RCC with a median age of diagnosis at 48 . The majority of these RCCs are chromophobe RCC or hybrid oncocytic tumors (i.e. mixed oncocytoma and chromophobe RCC), latter of which is characteristic of BHD . These masses have moderate enhancement relative to renal cortex and T2 iso- or hyperintensity, without microscopic fat. Other RCC subtypes are possible.
Hereditary renal mass syndromes: a pictorial review
Acacia H. Yoon1 · Justin R. Tse2
Abdominal Radiology 2024 https://doi.org/10.1007/s00261-024-04534-y - TSC affects approximately 1/10,000 people and most (75–80%) develop angiomyolipomas (AMLs), which can include the epithelioid subtype. The RCC risk is similar to that of the general population but occurs earlier at a mean age of 28 . TSC-associated RCCs are histologically unique, diverse, and clinically indolent; clear cell histology is less common. Approximately 5% of TSC patients also have polycystic kidney disease, i.e. continuous gene syndrome, which occurs because the responsible genes are adjacent. These patients have worse prognosiswith earlier progression to renal failure.
Hereditary renal mass syndromes: a pictorial review
Acacia H. Yoon1 · Justin R. Tse2
Abdominal Radiology 2024 https://doi.org/10.1007/s00261-024-04534-y - “Hereditary papillary RCC is caused by activating germline mutations in the Mesenchymal Epithelial Transition (MET) gene, which encodes a tyrosine kinase receptor. This rare syndrome is reported in fewer than 60 reported families and causes a higher risk of papillary RCCs, occurring at a mean age of 42. Patients present with multifocal and/or bilateral papillary RCCs , which are usually solid renal masses with hypovascular enhancement, T2-hypointense signal, and variable intrinsic T1-hyperintense signal, or less commonly, cystic renal mass with variable intrinsic T1-hyperintense signal . Patients can develop numerous microscopic precursor lesions such as adenomas and papillary lesions. There are no known extra-renal manifestations.”
Hereditary renal mass syndromes: a pictorial review
Acacia H. Yoon1 · Justin R. Tse2
Abdominal Radiology 2024 https://doi.org/10.1007/s00261-024-04534-y - “Hereditary renal cancer syndromes present a significant risk for RCC and extra-renal manifestations. Early diagnosis, imaging surveillance, and timely interventions can improve outcomes. MRI is preferred for surveillance over CT as patients are expected to undergo repeated imaging at an early age. Once diagnosed with RCC, standard treatment consists of observation if small or NSS versus thermal ablation. Two exceptions are RCCs from HLRCC and PGL/ PCC, which require wide resection margins due aggressive biology. Understanding the genetic and clinical aspects of these syndromes is essential for radiologists to ensure comprehensive patient care.”
Hereditary renal mass syndromes: a pictorial review
Acacia H. Yoon1 · Justin R. Tse2
Abdominal Radiology 2024 https://doi.org/10.1007/s00261-024-04534-y
- “Non-traumatic acute renal artery emergencies encompass a spectrum of etiologies, including renal artery stenosis, arteriovenous malformations, aneurysms and pseudoaneurysms, dissections, thrombosis, and vasculitis. Prompt and accurate diagnosis in the emergency setting is crucial due to the potential for significant morbidity and mortality. Computed tomography (CT) and CT angiography (CTA) are the mainstay imaging modalities, offering rapid acquisition and high diagnostic accuracy. The integration of 3D postprocessing techniques, such as 3D cinematic rendering (CR), improves the diagnostic workflow by providing photorealistic and anatomically accurate visualizations. This pictorial essay illustrates the diagnostic utility of CT and CTA, supplemented by 3D CR, through a series of 10 cases of non-traumatic renal artery emergencies. The added value of 3D CR in improving diagnostic confidence, surgical planning, and understanding of complex vascular anatomy is emphasized.”
Flank pain, hypertension, and hematuria: CT and 3D cinematic rendering in the evaluation of renal artery emergencies-a pictorial essay.
Yasrab M, Fishman EK, Chu LC.
Emerg Radiol. 2024 Aug 24. doi: 10.1007/s10140-024-02279-1. Epub ahead of print. - “Irrespective of the specific etiology, computed tomography (CT) based imaging has become the mainstay diagnostic modality of choice when evaluating suspected renal vessel disease or injury owing to its rapid acquisition, low cost, and high diagnostic accuracy for vascular processes and pathologies. Initial assessment via contrast-enhanced ultrasonography(US) and color doppler US may be performed to reveal flow anomalies, but barring unstable patients requiring immediate intervention or resuscitation, CT and CT angiography (CTA) studies are obtained for a thorough assessment of the vasculature and associated structures. With the advent of 3D postprocessing, including the novel 3D cinematic rendering (CR) technique that improves upon traditional volumetric rendering (VR) by employing a global illumination model, life-like and anatomically accurate reconstructions of the volumetric dataset can be rapidly acquired.”
Flank pain, hypertension, and hematuria: CT and 3D cinematic rendering in the evaluation of renal artery emergencies-a pictorial essay.
Yasrab M, Fishman EK, Chu LC.
Emerg Radiol. 2024 Aug 24. doi: 10.1007/s10140-024-02279-1. Epub ahead of print. - “Renal AVMs are abnormal communications between the arteries and veins, which may be a result of a simple, direct fistula or a complex network of tortuous vessels forming a nidus. Acquired AVMs are more common than congenital, and although they are a rare entity (prevalence < 0.04%) that can remain asymptomatic, they most commonly present with hematuria that may be associated with flank pain or hypertension in the acute setting. Life-threatening hemorrhage triggered by rupture of anomalous vessels or high-output failure in larger shunts are possible complications Hyperenhancing foci seen on arterial phase with early venous return, tortuous vessels, and enlarged feeding arteries should raise concern for an AVM. 3D CR effectively captures the complex vascular anatomy with a more intuitive perspective that helps guide interventional management.”
Flank pain, hypertension, and hematuria: CT and 3D cinematic rendering in the evaluation of renal artery emergencies-a pictorial essay.
Yasrab M, Fishman EK, Chu LC.
Emerg Radiol. 2024 Aug 24. doi: 10.1007/s10140-024-02279-1. Epub ahead of print. - “FMD is an idiopathic, noninflammatory medium-vessel vascular pathology underpinned by focal fibroplasia, which most commonly affects the renal and then carotid arteries. It is predominantly seen in females. CTA has been shown to have nearly 100% sensitivity and over 90% specificity for detecting RAS, and while atherosclerotic RAS is unilateral with stenosis towards the origin or bifurcation of the artery in most patients, bilateral and multifocal involvement is often seen in FMD, especially in acutely symptomatic patients. The classic description of FMD is the ‘string of beads’ appearance on imaging due to alternating regions of focal dilatations and stenoses. The diseased vessel walls also predispose themselves to other sequelae of FMD such as dissections, aneurysms, and thrombosis as seen in our cases.”
Flank pain, hypertension, and hematuria: CT and 3D cinematic rendering in the evaluation of renal artery emergencies-a pictorial essay.
Yasrab M, Fishman EK, Chu LC.
Emerg Radiol. 2024 Aug 24. doi: 10.1007/s10140-024-02279-1. Epub ahead of print. - Acute occlusion of the renal artery or its branches requires prompt diagnosis and treatment to prevent severe loss of renal function. In-situ renal artery thrombosis and thromboembolic phenomena (originating from the heart or aorta) are major causes, with increased risk in the context of comorbid conditions that predispose to hypercoagulability. Pathologic vascular processes like dissections and aneurysms can also be complicated by thrombosis . Most symptomatic patients present with acute abdominal or flank pain that may be associated with hypertension, nausea, hematuria, or overt renal failure in severe cases .
Flank pain, hypertension, and hematuria: CT and 3D cinematic rendering in the evaluation of renal artery emergencies-a pictorial essay.
Yasrab M, Fishman EK, Chu LC.
Emerg Radiol. 2024 Aug 24. doi: 10.1007/s10140-024-02279-1. Epub ahead of print. - “Unlike small-vessel vasculitides (ANCA-associated vasculitides) where kidney pathology primarily manifests as glomerulonephritis, direct renal artery disease can be seen in medium- and large-vessel vasculitides. Vasculitides often have bilateral involvement and are the most common vascular cause of spontaneous renal hemorrhage (excluding neoplasms), particularly polyarteritis nodosa (PAN). PAN is a necrotizing medium-vessel vasculitis, a prominent feature of which is involvement of the renal arteries and branches in up to 90% of patients. It is associated with hepatitis B and is more common in men.”
Flank pain, hypertension, and hematuria: CT and 3D cinematic rendering in the evaluation of renal artery emergencies-a pictorial essay.
Yasrab M, Fishman EK, Chu LC.
Emerg Radiol. 2024 Aug 24. doi: 10.1007/s10140-024-02279-1. Epub ahead of print. - “Characteristic CTA findings include multiple, bilateral microaneurysms and hypoenhancing regions of infarction due to occluded vessels. 3D CR is particularly helpful in careful evaluation of the microaneurysms and differentiation from calculi as they are often internally calcified by visualizing the arterial map. Largevessel vasculitis such as Takayasu arteritis may also involve the renal arteries and result in renovascular hypertension, with CT findings showing mural thickening and involvement of major vessels confirming diagnosis.”
Flank pain, hypertension, and hematuria: CT and 3D cinematic rendering in the evaluation of renal artery emergencies-a pictorial essay.
Yasrab M, Fishman EK, Chu LC.
Emerg Radiol. 2024 Aug 24. doi: 10.1007/s10140-024-02279-1. Epub ahead of print.
- Background To develop and compare machine learning models based on triphasic contrast-enhanced CT (CECT) for distinguishing between benign and malignant renal tumors.
Materials and Methods In total, 427 patients were enrolled from two medical centers: Center 1 (serving as the training set) and Center 2 (serving as the external validation set). First, 1781 radiomic features were individually extracted from corticomedullary phase (CP), nephrographic phase (NP), and excretory phase (EP) CECT images, after which 10 features were selected by the minimum redundancy maximum relevance method. Second, random forest (RF) models were constructed from single-phase features (CP, NP, and EP) as well as from the combination of features from all three phases (TP). Third,the RF models were assessed in the training and external validation sets. Finally, the internal prediction mechanisms of the models were explained by the SHapley Additive exPlanations (SHAP) approach.
Interpretable multiphasic CT‑based radiomic analysis for preoperatively differentiating benign and malignant solid renal tumors: a multicenter study
Yaohai Wu et al.
Abdominal Radiology (2024) 49:3096–3106 - Results A total of 266 patients with renal tumors from Center 1 and 161 patients from Center 2 were included. In the training set, the AUCs of the RF models constructed from the CP, NP, EP, and TP features were 0.886, 0.912, 0.930, and 0.944, respectively. In the external validation set, the models achieved AUCs of 0.860, 0.821, 0.921, and 0.908, respectively. The “original_shape_Flatness” feature played the most important role in the prediction outcome for the RF model based on EP features according to the SHAP method.
Conclusions The four RF models efficiently differentiated benign from malignant solid renal tumors, with the EP feature based RF model displaying the best performance.
Interpretable multiphasic CT‑based radiomic analysis for preoperatively differentiating benign and malignant solid renal tumors: a multicenter study
Yaohai Wu et al.
Abdominal Radiology (2024) 49:3096–3106 - “In summary, all four RF models efficiently differentiated benign from malignant solid renal tumors, and the RF model based on EP features displayed the best performance. The feature “original_shape_Flatness” played the greatest role in predicting the outcome of RF model based on EP image features.”
Interpretable multiphasic CT‑based radiomic analysis for preoperatively differentiating benign and malignant solid renal tumors: a multicenter study
Yaohai Wu et al.
Abdominal Radiology (2024) 49:3096–3106
Liver
- “Hydatid disease is a parasitic infection caused by the echinococcus tapeworm that is most classically endemic to South America, Africa, and Asia. Domestic diagnoses of hydatid disease are predominantly attributable to persons infected in endemic regions outside the United States. While hydatid disease can involve multiple organs, hepatic involvement is most common. Cinematic rendering enables detailed characterization of cyst architecture, facilitating visualization of daughter cysts, membranes, septations, and hydatid sand. While percutaneous treatment options have been demonstrated to be safe and efficacious alternatives, radical surgery with pre- and postoperative administration of albendazole remains the best treatment option due to low recurrence and complication rates.”
Cinematic Rendering of Hepatic Hydatid Disease.
Ahmed TM, Fishman EK.
Radiology. 2024 Sep;312(3):e240527. doi: 10.1148/radiol.240527. PMID: 39287529.
- “Diagnosing liver lesions is crucial for treatment choices and patient outcomes. This study develops an automatic diagnosis system for liver lesions using multiphase enhanced computed tomography (CT). A total of 4039 patients from six data centers are enrolled to develop Liver Lesion Network (LiLNet). LiLNet identifies focal liver lesions, including hepatocellular carcinoma (HCC), intrahepatic cholangiocarcinoma (ICC), metastatic tumors (MET), focal nodular hyperplasia (FNH), hemangioma (HEM), and cysts (CYST). Validated in four external centers and clinically verified in two hospitals, LiLNet achieves an accuracy (ACC) of 94.7% and an area under the curve (AUC) of 97.2% for benign and malignant tumors. For HCC, ICC, and MET, the ACC is 88.7% with an AUC of 95.6%. For FNH, HEM, and CYST, the ACC is 88.6% with an AUC of 95.9%. LiLNet can aid in clinical diagnosis, especially in regions with a shortage of radiologists.”
Focal liver lesion diagnosis with deep learning and multistage CT imaging
Yi Wei et al.
Nature Communications | ( 2024) 15:7040 - “In this study, we demonstrate the performance of our AI system, LiLNet, in distinguishing six common types of focal liver lesions. We develop the model using data from six centers and assess its generalization through extensive testing on a test set and four externalvalidation centers. We compare LiLNet’s performance with radiologists’ interpretations of contrast-enhanced CT images in a reader study. To address real-world clinical implementation, we deploy LiLNet in two hospitals, integrating it into routine workflows across outpatient, emergency, and inpatient settings. This integration evaluates the system’s performance in various clinical environments, ensuring its robustness and reliability in practical use.”
Focal liver lesion diagnosis with deep learning and multistage CT imaging
Yi Wei et al.
Nature Communications | ( 2024) 15:7040 - “We used a test set of 6743 images from 221 patients at West China Hospital of Sichuan University to compare the diagnostic ability of LiLNet with that of radiologists. The evaluation involved three radiologists with varying levels of experience. Radiologists independently labeled the 221 patients based on multiphase contrast-enhanced CT images. LiLNet demonstrated a diagnostic accuracy of 91.0% for distinguishing between benign and malignant tumors, 82.9% for distinguishing between malignant tumors, and 92.3% for distinguishing between benign tumors. Compared to junior-level radiologists, LiLNet achieved 4.6% greater accuracy for benign and malignant diagnosis, 4.1% greater accuracy for middle-level radiologists, and 2.3% greater accuracy for senior level radiologists. The diagnostic accuracy of radiologists for diagnosing malignant tumors was similar. Notably, compared with radiologists, LiLNet achieved a substantial 18% improvement in diagnostic accuracy. Additionally, in diagnosing benign tumors, LiLNet outperformed junior-level practitioners by 20%, middle-level practitioners by 10%, and senior-level practitioners by 6.7%.”
Focal liver lesion diagnosis with deep learning and multistage CT imaging
Yi Wei et al.
Nature Communications | ( 2024) 15:7040
Focal liver lesion diagnosis with deep learning and multistage CT imaging
Yi Wei et al.
Nature Communications | ( 2024) 15:7040- “We utilized patients’ name-ID as the unique identifier to prevent duplicate IDs. Duplicate samples with the same name-ID were systematically removed, and patients were randomly assigned to either the training set or testing set to prevent data overlap. As shown in Fig. 1a, the training set comprised images from 1580 patients from West ChinaHospital of SichuanUniversity and Sanya People’sHospital. The testing cohort consisted of 1308 patients from West China Hospital of Sichuan University, while external validation cohorts included 1151 patients from Henan Provincial People’s Hospital, The First Affiliated Hospital of Chengdu Medical College, Leshan People’s Hospital, and Guizhou Provincial People’s Hospital.”
Focal liver lesion diagnosis with deep learning and multistage CT imaging
Yi Wei et al.
Nature Communications | ( 2024) 15:7040 - “Between June 2012 and December 2022, a total of 4039 patients’ multiphase (arterial phase and portal venous phase) contrastenhanced CT images from six hospitals were included under the following inclusion criteria: Patients (1) were eighteen years or older; (2) did not have a history of hepatectomy, transarterial chemotherapy (TACE), or radiofrequency ablation (RFA) before CT imaging; (3) had pathologically confirmed malignant tumors; and (4) had benign tumors confirmed either by consensus among three radiologists or by follow-up of at least six months using two imaging modalities. The method used for retrospective data collection and basic patientinformation including sex and age are depicted in Fig. 1a and Table 1, respectively. Furthermore, clinical testing was conducted on two real world clinical evaluation queues (Fig. 1b): West China Tianfu Center and Sanya People’s Hospital. At Tianfu Center, we examined 184 cases, while at Sanya People’s Hospital, 235 cases were assessed. Gender andAge assignment was based on government-issued IDs.”
Focal liver lesion diagnosis with deep learning and multistage CT imaging
Yi Wei et al.
Nature Communications | ( 2024) 15:7040
Neuroradiology
- Summary
The performance of an artificial intelligence clinical decision support solution for intracranial hemorrhage detection was low in a low prevalence environment; falsely flagged studies led to increased radiologist interpretation time, potentially reducing system efficiency.
Key Points
■ An artificial intelligence (AI) clinical decision support solution for intracranial hemorrhage detection yielded a positive predictive value of 21.1% in a low prevalence (2.70%) environment.
■ Falsely flagged studies by the AI solution led to lengthened radiologist read times and system inefficiencies (median read time increased 1 minute 14 seconds [P < .001] for examinations with false-positive findings and 1 minute 5 seconds [P = .04] for examinations with false-negative findings).
■ Factoring in prevalence of a condition in varying clinical settings and the impact that falsely flagged studies will have on system efficiency may aid institutional decision-making for use of an AI solution and help set clearer expectations for end users.
Deep Learning to Detect Intracranial Hemorrhage in a National Teleradiology Program and the Impact on Interpretation Time
Andrew James Del Gaizo, et al.
Radiology: Artificial Intelligence 2024; 6(5):e240067 - The diagnostic performance of an artificial intelligence (AI) clinical decision support solution for acute intracranial hemorrhage (ICH) detection was assessed in a large teleradiology practice. The impact on radiologist read times and system efficiency was also quantified. A total of 61 704 consecutive noncontrast head CT examinations were retrospectively evaluated. System performance was calculated along with mean and median read times for CT studies obtained before (baseline, pre-AI period; August 2021 to May 2022) and after (post-AI period; January 2023 to February 2024) AI implementation. The AI solution had a sensitivity of 75.6%, specificity of 92.1%, accuracy of 91.7%, prevalence of 2.70%, and positive predictive value of 21.1%. Of the 56 745 post-AI CT scans with no bleed identified by a radiologist, examinations falsely flagged as suspected ICH by the AI solution (n = 4464) took an average of 9 minutes 40 seconds (median, 8 minutes 7 seconds) to interpret as compared with 8 minutes 25 seconds (median, 6 minutes 48 seconds) for unremarkable CT scans before AI (n = 49 007) (P < .001) and 8 minutes 38 seconds (median, 6 minutes 53 seconds) after AI when ICH was not suspected by the AI solution (n = 52 281) (P < .001).
Deep Learning to Detect Intracranial Hemorrhage in a National Teleradiology Program and the Impact on Interpretation Time
Andrew James Del Gaizo, et al.
Radiology: Artificial Intelligence 2024; 6(5):e240067 - The AI solution had a sensitivity of 75.6%, specificity of 92.1%, accuracy of 91.7%, prevalence of 2.70%, and positive predictive value of 21.1%. Of the 56 745 post-AI CT scans with no bleed identified by a radiologist, examinations falsely flagged as suspected ICH by the AI solution (n = 4464) took an average of 9 minutes 40 seconds (median, 8 minutes 7 seconds) to interpret as compared with 8 minutes 25 seconds (median, 6 minutes 48 seconds) for unremarkable CT scans before AI (n = 49 007) (P < .001) and 8 minutes 38 seconds (median, 6 minutes 53 seconds) after AI when ICH was not suspected by the AI solution (n = 52 281) (P < .001). CT scans with no bleed identified by the AI but reported as positive for ICH by the radiologist (n = 384) took an average of 14 minutes 23 seconds (median, 13 minutes 35 seconds) to interpret as compared with 13 minutes 34 seconds (median, 12 minutes 30 seconds) for CT scans correctly reported as a bleed by the AI (n = 1192) (P = .04). With lengthened read times for falsely flagged examinations, system inefficiencies may outweigh the potential benefits of using the tool in a high volume, low prevalence environment.
Deep Learning to Detect Intracranial Hemorrhage in a National Teleradiology Program and the Impact on Interpretation Time
Andrew James Del Gaizo, et al.
Radiology: Artificial Intelligence 2024; 6(5):e240067 - “CT scans with no bleed identified by the AI but reported as positive for ICH by the radiologist (n = 384) took an average of 14 minutes 23 seconds (median, 13 minutes 35 seconds) to interpret as compared with 13 minutes 34 seconds (median, 12 minutes 30 seconds) for CT scans correctly reported as a bleed by the AI (n = 1192) (P = .04). With lengthened read times for falsely flagged examinations, system inefficiencies may outweigh the potential benefits of using the tool in a high volume, low prevalence environment.”
Deep Learning to Detect Intracranial Hemorrhage in a National Teleradiology Program and the Impact on Interpretation Time
Andrew James Del Gaizo, et al.
Radiology: Artificial Intelligence 2024; 6(5):e240067 - “In conclusion, use of an AI tool for ICH detection in our teleradiology practice yielded reduced sensitivity and specificity compared with the published literature. However, a low prevalence of ICH in our patients contributed to a substantially lower positive predictive value. Noncontrast head CT examinations falsely flagged by an AI solution lengthened mean and median read times. In aggregate, this led to system inefficiencies that reduced the potential benefit of using the AI tool in our environment. A broader understanding of an AI solution’s impact on system efficiency may aid institutional decision-making and help set clearer expectations for end users.”
Deep Learning to Detect Intracranial Hemorrhage in a National Teleradiology Program and the Impact on Interpretation Time
Andrew James Del Gaizo, et al.
Radiology: Artificial Intelligence 2024; 6(5):e240067 - “The experience reported by Del Gaizo et al has important implications and lessons for anyone planning to introduce AI solutions into clinical radiology practice or undertake similar research. Prospective users should assess whether their patient population is a close enough match to the population on which an AI program was developed for it to be used: They should assess the potential impact of prevalence on accuracy and predictive value. For a given combination of sensitivity and specificity, lower prevalence will result in lower estimates of PPV. Other important issues to assess are the impact on radiologists’ interpretation times and, for many clinical scenarios, impact on time to therapy. Conservatively, radiology practices introducing AI applications into their clinical operations should always undertake an assessment after implementation to determine how well the program is functioning in their respective unique environments.”
Challenges of Implementing Artificial Intelligence–enabled Programs in the Clinical Practice of Radiology
James H. Thrall
Radiology: Artificial Intelligence 2024; 6(5):e240411 - “A striking finding in the study reported by Del Gaizo et al was a positive predictive value (PPV) of only 21.1%. PPV is a function of sensitivity, specificity, and prevalence: It is the probability that a patient with a positive (abnormal) test result actually has the disease. The authors observe that the low prevalence of 2.7% in their study is the likely reason for the low PPV. Of note, McLouth et al reported a prevalence of ICH of 31% (255 of 814), indicating a different patient population than the current study. The corresponding PPV in the McLouth et al study was 91.4%. McLouth et al modeled different levels of prevalence, holding sensitivity and specificity constant, which showed PPV ranged from 80.2% at 10% prevalence to 97.3% at 50% prevalence.”
Challenges of Implementing Artificial Intelligence–enabled Programs in the Clinical Practice of Radiology
James H. Thrall
Radiology: Artificial Intelligence 2024; 6(5):e240411
Pancreas
- “SCAs are benign cystic neoplasms characterized by glycogen-rich epithelial cells forming multiple small thin walled cysts that contain serous fluid. They usually occur sporadically but have an increased incidence in von Hippel–Lindau syndrome (VHL). While frequently found incidentally and usually asymptomatic, larger lesions (>4 cm) can cause non- specific symptoms [5, 6], including abdominal pain, palpable abdominal mass, and rarely jaundice. Most lesions (60%) occur in the pancreatic body and tail, with the remaining 40% seen in the pancreatic head and uncinate process. SCAs show a predilection for middle-aged and older women and are less commonly seen in males.”
Imaging of pancreatic serous cystadenoma and common imitators
Camila Lopes Vendrami · Nancy A. Hammond · David J. Escobar et al.
Abdominal Radiology (2024) 49:3666–3685 - “The solid variant is an extremely rare type of SCAs and is also known as solid serous adenoma. This variant has variable definitions in the literature with some authors basing their definition on a microscopic appearance, while others use a solid radiologic appearance for diagnosis. Solid variant SCAs are formed by cells that resemble those from other forms of SCA but do not contain cystic spaces in histopathology. This is in distinction to other variants of SCAs that can have a solid appearance on imaging but demonstrate cystic spaces on histopathology. On imaging, the solid variant is difficult to distinguish from other solid pancreatic lesions such as pancreatic neuroendocrine tumors or other solid lesions such as metastatic renal cell carcinoma.”
Imaging of pancreatic serous cystadenoma and common imitators
Camila Lopes Vendrami · Nancy A. Hammond · David J. Escobar et al.
Abdominal Radiology (2024) 49:3666–3685 - “VHL-associated serous cystic neoplasm (WHO classification) present with lesions that are indiscernible at histology from sporadically occurring serous cystic tumors. VHL is a multi-tumor inherited autosomal dominant disease. VHL is caused by mutations in the VHL tumor suppressor gene and is characterized by the presence of hemangioblastoma of the central nervous system and retina, adrenal pheochromocytoma, renal cell carcinoma (RCC), pancreatic neuroendocrine tumors and cysts, cystadenomas, and mixed tumors, and other organ involvement . In VHL disease, almost 7.6% of patients may have pancreatic manifestations alone, while 11.5% of patients show combined lesions.”
Imaging of pancreatic serous cystadenoma and common imitators
Camila Lopes Vendrami · Nancy A. Hammond · David J. Escobar et al.
Abdominal Radiology (2024) 49:3666–3685 - “Chu et al. demonstrated equivalent performance between their radiomics-based model and an experienced radiologist in the accurate classification of several pancreatic cystic lesions (SCAs, MCNs, SPNs, and NETs) with an AUC of 0.94 for the AI-based approach and 0.895 for the radiologist. The documented imaging features were size and location of pancreatic cysts and presence of calcifications or pancreatic duct dilatation (>3 mm in diameter). A total of 488 radiomics features from the segmented three-dimensional (3D) volume of the cystic lesion were extracted based on venous phase images. Although more validation is still needed, the ability of AI to accurately characterize pancreatic cystic lesions can potentially improve the selection of patients with high-risk lesions who would benefit from surgical intervention, while separating out those who can be managed more conservatively.”
Imaging of pancreatic serous cystadenoma and common imitators
Camila Lopes Vendrami · Nancy A. Hammond · David J. Escobar et al.
Abdominal Radiology (2024) 49:3666–3685 - “Cystic PNETs can occur due to large solid tumors that have undergone cystic degeneration or more recently, a smaller cystic subtype of PNET has been identified. This subtype occurs mostly in the pancreatic body and tail, demonstrates less aggressive behavior (lower ki-67 index), are nonfunctioning, and are associated with a lower rate of metastases. The most suggestive radiologic feature of cystic PNETs is the hypervascular peripheral wall . Additionally, clinical history of endocrinopathy, and associated lymphadenopathy and liver metastases are helpful characteristics to differentiate PNETs from SCAs.”
Imaging of pancreatic serous cystadenoma and common imitators
Camila Lopes Vendrami · Nancy A. Hammond · David J. Escobar et al.
Abdominal Radiology (2024) 49:3666–3685 - “Pancreatic serous cystadenoma are mostly benign tumors that can be managed conservatively with surveillance unless they demonstrate aggressive behavior or unspecific features that prevent proper pre-operative diagnosis. In blinded studies, radiologists could diagnose SCAs relatively well (23–82% of cases). SCAs classically appear as multiple small cysts leading to a multilobulated external contour that does not usually occur in other cystic lesions, known as microcystic pattern, and that may allow differentiation from other types of pancreatic tumors possible. However, SCAs may also depict a wide range of imaging appearances ranging from a unilocular cystic lesion to a solid hypervascular mass that may overlap with other pancreatic neoplasms. Cyst fluid analysis with immunohistochemistry and molecular characterization may assist in the preoperative risk stratification. Newer imaging techniques may also playa role in the discrimination of SCAs and their mimickers.”
Imaging of pancreatic serous cystadenoma and common imitators
Camila Lopes Vendrami · Nancy A. Hammond · David J. Escobar et al.
Abdominal Radiology (2024) 49:3666–3685
- IMPORTANCE Pancreatic ductal adenocarcinoma (PDAC) is a deadly disease with increasing incidence. The majority of PDACs are incurable at presentation, but population-based screening is not recommended. Surveillance of high-risk individuals for PDAC may lead to early detection, but the survival benefit is unproven.
OBJECTIVE To compare the survival of patients with surveillance-detected PDAC with US national data.
DESIGN, SETTING, AND PARTICIPANTS This comparative cohort studywas conducted in multiple US academic medical centers participating in the Cancer of the Pancreas Screening program, which screens high-risk individuals with a familial or genetic predisposition for PDAC. The comparison cohort comprised patients with PDAC matched for age, sex, and year of diagnosis from the Surveillance, Epidemiology, and End Results (SEER) program. The Cancer of the Pancreas Screening program originated in 1998, and data collection was done through 2021. The data analysis was performed from April 29, 2022, through April 10, 2023.
Pancreatic Cancer Surveillance and Survival of High-Risk Individuals.
Blackford AL, Canto MI, Dbouk M, Hruban RH, Katona BW, Chak A, Brand RE, Syngal S, Farrell J, Kastrinos F, Stoffel EM, Rustgi A, Klein AP, Kamel I, Fishman EK, He J, Burkhart R, Shin EJ, Lennon AM, Goggins M.
JAMA Oncol. 2024 Aug 1;10(8):1087-1096. - RESULTS A total of 26 high-risk individuals (mean [SD] age at diagnosis, 65.8 [9.5] years; 15m female [57.7%]) with PDAC were compared with 1504 SEER control patients with PDAC (mean [SD] age at diagnosis, 66.8 [7.9] years; 771 female [51.3%]). The median primary tumor diameter of the 26 high-risk individuals was smaller than in the control patients (2.5 [range, 0.6-5.0] vs 3.6 [range, 0.2-8.0] cm, respectively; P < .001). The high-risk individuals weremore likely to be diagnosed with a lower stage (stage I, 10 [38.5%]; stage II, 8 [30.8%]) than matched control patients (stage I, 155 [10.3%]; stage II, 377 [25.1%]; P < .001). The PDAC mortality rate at 5 years was lower for high-risk individuals than control patients (43%vs 86%; hazard ratio, 3.58; 95%CI, 2.01-6.39; P < .001), and high-risk individuals lived longer than matched control patients (median OS, 61.7 [range, 1.9-147.3] vs 8.0 [range, 1.0-131.0] months; 5-year OS rate, 50% [95%CI, 32%-80%] vs 9% [95%CI, 7%-11%]).
CONCLUSIONS AND RELEVANCE These findings suggest that surveillance of high-risk individuals may lead to detection of smaller, lower-stage PDACs and improved survival.
Pancreatic Cancer Surveillance and Survival of High-Risk Individuals.
Blackford AL, Canto MI, Dbouk M, Hruban RH, Katona BW, Chak A, Brand RE, Syngal S, Farrell J, Kastrinos F, Stoffel EM, Rustgi A, Klein AP, Kamel I, Fishman EK, He J, Burkhart R, Shin EJ, Lennon AM, Goggins M.
JAMA Oncol. 2024 Aug 1;10(8):1087-1096. - Key Points
Question What is the association of selective pancreatic cancer surveillance with survival?
Findings In this cohort study comparing 26 individuals with a genetic or familial predisposition undergoing pancreatic cancer surveillance and 1504 matched control patients, surveillance led toa significantly higher proportion of stage I cancers (31% vs 10%),longer 5-year survival rate (50% vs 9%), and lower pancreatic cancer–specific mortality rate (43%vs 86%).
Meaning These findings suggest that selective surveillance of individuals at high risk for pancreatic cancer may improve clinical outcomes. - Study Eligibility
The high-risk individuals were enrolled based on eitherfamily history criteria, which included individualswhohad at east 1 first-degree relative with PDAC and who were part of akindred with at least 1 pair of affected first-degree relatives(familial pancreatic cancer kindred), or germline gene status criteria (carriers of a germline deleterious variant in a gene associated with hereditary pancreatic cancer [ATM, BRCA1,BRCA2, CDKN2A, PALB2, or STK11]). 
- Screening of average-risk individuals for PDAC is not recommended by the US Preventive Services Task Force.4 Because PDAC is a rare, albeit deadly disease, a randomized clinical trial comparing surveillance vs no surveillance in high-risk individuals is not feasible. Selective surveillance of high-risk individuals has been 1 proposed alternative to population based screening in the past 2 decades. Using EUS, MRI, and/or CT, 25 surveillance studies involving more than 3000 high-risk individuals showed that early detection of asymptomatic PDAC is feasible. In a 2019 clinical practice update, the American Gastroenterological Association endorsed selective surveillance in high-risk individuals. In a 2022 clinical guideline, the American Society for Gastrointestinal Endoscopy recommended selective surveillance of high-risk individuals based on scientific review and a Grading of Recommendations Assessment, Development, and Evaluation methodology.
- “Survival after a PDAC diagnosis among high-risk individuals undergoing surveillance in the CAPS program is higher thanreported in other established programs. Although PDAC surveillance programs have shown a greater proportion of stage I cancers (33%-40% of cases) and improved resectability (60%-83%) for all patients with screen-detected PDAC compared with patients with PDAC diagnosed in the general population or outside of surveillance, the reported survival benefit is highly variable, with median survival ranging from18 months in the other studies to 61.7 months in our study.”
Pancreatic Cancer Surveillance and Survival of High-Risk Individuals.
Blackford AL, Canto MI, Dbouk M, Hruban RH, Katona BW, Chak A, Brand RE, Syngal S, Farrell J, Kastrinos F, Stoffel EM, Rustgi A, Klein AP, Kamel I, Fishman EK, He J, Burkhart R, Shin EJ, Lennon AM, Goggins M.
JAMA Oncol. 2024 Aug 1;10(8):1087-1096. - “The findings of our cohort study show that high-risk individuals who underwent annual or semiannual surveillance EUS and MRI and who were diagnosed with PDAC had a greater likelihood of having smaller, lower-stage tumors; lower PDAC-specific mortality; and better OS (5-year rate, 50%) compared with a national cohort (5-year rate, 9%) matched for age, sex, race, and year of diagnosis and with similar tumor location and type of surgery. The adjusted HRs showed a 4-fold higher chance of being alive for screened high-risk individuals.”
Pancreatic Cancer Surveillance and Survival of High-Risk Individuals.
Blackford AL, Canto MI, Dbouk M, Hruban RH, Katona BW, Chak A, Brand RE, Syngal S, Farrell J, Kastrinos F, Stoffel EM, Rustgi A, Klein AP, Kamel I, Fishman EK, He J, Burkhart R, Shin EJ, Lennon AM, Goggins M.
JAMA Oncol. 2024 Aug 1;10(8):1087-1096. - “However, screening for a low prevalence disease may lead to false-positive results. The diagnostic yield (finding PDAC or high-grade dysplasia at resection) of surveillance-detected lesions is low(29% of those undergoing surgical resection, or 8.6% of high-risk individuals), despite expert multidisciplinary recommendation and shared decision-making. False-negative test results are also still a problem, and radiologists frequently (50%-62%) miss pancreatic cancers presenting with atypical or subtle signs on CT or MRI, which may lead to delayed diagnosis and advanced disease. In a retrospective review of prior negative MRI findings for carriers of germline CDKN2A pathogenic variants who developed PDAC, mild pancreatic ductal dilatation was an unrecognized subtle abnormality.None the less, nearly one-half of high-risk individuals who developed neoplastic progression while under surveillance had no prior pancreatic lesions detected by imaging studies.”
Pancreatic Cancer Surveillance and Survival of High-Risk Individuals.
Blackford AL, Canto MI, Dbouk M, Hruban RH, Katona BW, Chak A, Brand RE, Syngal S, Farrell J, Kastrinos F, Stoffel EM, Rustgi A, Klein AP, Kamel I, Fishman EK, He J, Burkhart R, Shin EJ, Lennon AM, Goggins M.
JAMA Oncol. 2024 Aug 1;10(8):1087-1096. - Conclusions
In this comparative cohort study, surveillance of high-risk individuals for PDAC using EUS and MRI within established programs at academic centers was observed to lead to the detection of smaller pancreatic cancers, a greater number of patients with stage I disease, lower mortality, and a much higher likelihood of long-term survival than unscreened patients in the general population diagnosed with PDAC. These findings suggest that selective surveillance of individuals at high risk for pancreatic cancer may improve clinical outcomes.
- Background: This study aimed to investigate the effects of changes in clinicopathological factors during preoperative chemotherapy for pancreatic cancer, including skeletal muscle volume, on recurrence and prognosis after pancreatectomy.
Methods: Data from 41 patients who underwent resection for pancreatic cancer after preoperative chemotherapy from 2012 to 2021 were retrospectively reviewed. Skeletal muscle volume was substituted for the psoas muscle area (PMA) at the level of the third lumbar vertebra. We investigated the relationship of clinicopathological factors during preoperative chemotherapy with disease-free survival (DFS) and overall survival (OS). The association between clinicopathological factors and a decrease in PMA was investigated.
Changes in Skeletal Muscle Volume During Preoperative Chemotherapy Affect the Outcome of Pancreatic Cancer
Michinori Matsumoto et al.
The American Surgeon™ 2024, (in press) - Results: In the multivariate analyses for DFS and OS, the factors associated with recurrence were as follows: decrease in PMA (P = 0.003) and the absence of adjuvant therapy (P = 0.03), and the factors associated with poor prognosis were as follows: decrease in PMA (P = 0.04) and the absence of adjuvant therapy (P = 0.008), and the resectability of borderline resectable and unresectable-locally advanced tumors (P = 0.033). All patients with partial response according to the Response Evaluation Criteria in Solid Tumors (version 1.1) had no decrease in PMA (P = 0.01). The proportion of patients with Evans classification ≥ II was significantly higher in the group without a decrease in PMA (P = 0.02). The proportion of patients with an average relative dose intensity of adjuvant therapy ≥0.6 was significantly higher in the group without a decrease in PMA (P = 0.02).
Conclusion: Changes in preoperative skeletal muscle volume during preoperative chemotherapy for pancreatic cancer is a potential predictor of recurrence and prognosis after pancreatectomy.
Changes in Skeletal Muscle Volume During Preoperative Chemotherapy Affect the Outcome of Pancreatic Cancer
Michinori Matsumoto et al.
The American Surgeon™ 2024, (in press) - Key Takeaway
· We evaluated the effects of the changes in inflammatory and nutritional markers, including psoas muscle volume, during preoperative chemotherapy for pancreatic cancer on recurrence and prognosis.
· Changes in preoperative skeletal muscle volume during preoperative chemotherapy for pancreatic cancer are a potential predictor of recurrence and prognosis after pancreatectomy.
· No decrease in psoas muscle volume was significantly associated with partial response according to the RECIST (version 1.1) and average relative dose intensity ≥0.6 for adjuvant therapy. - “According to data from the National Cancer Institute’s SEER program, at diagnosis, 12% of patients with PDA have stage I disease (confinement of the disease within the pancreas); 52% have stage IV (metastatic) disease. Patients with stage I (including stages IA [T1N0M0, tumor size ≤ 2 cm] and IB [T2N0M0, tumor size > 2 cm and ≤ 4 cm]) disease have a 5-year survival rate of around 44%, in contrast to the 3% 5-year survival rate for patients with stage IV metastatic disease. For patients with stage IA pancreatic cancer, 5-year survival rates exceed 80%.”
Imaging for Early Detection of Pancreatic Ductal Adenocarcinoma: Updates and Challenges in the Implementation of Screening and Surveillance Programs
Chenchan Huang et al.
AJR 2024; 223:e2431151 - “In the general U.S. population, lifetime risk of PDA is about 1.7% , and the incidence of PDA in Americans over 50 years old is 0.037% per year. CA 19–9 and CEA are the two most commonly used tumor markers in PDA management, but they lack the sensitivity and specificity needed for early detection. Though there are candidates showing promise , no blood-based biomarkers for early detection of PDA are recommended for use in clinical practice . Therefore, the U.S. Preventive Services Task Force opposes general population screening for PDA . Other challenges in the pursuit of early detection include the complexity of identifying high-risk groups suitable for screening and the limitations of standard-of-care imaging to detect very early PDA.”
Imaging for Early Detection of Pancreatic Ductal Adenocarcinoma: Updates and Challenges in the Implementation of Screening and Surveillance Programs
Chenchan Huang et al.
AJR 2024; 223:e2431151 - “Three groups are recognized as having elevated risk of PDA: high-risk individuals (HRIs) defined by specific criteria, patients with mucinous cystic neoplasms (MCNs), and patients over 50 years old with new-onset diabetes (NOD). Screening protocols are available for the first two groups (although without set guidelines); ongoing randomized controlled trials are being conducted to ascertain approaches for the third group. Imaging findings for patients undergoing surveillance are the same in all three groups; they include a solid mass, secondary signs of obstruction such as pancreatic duct dilatation or parenchymal atrophy in the absence of a history of pancreatitis, or a precursor cystic lesion with one or more worrisome features or high-risk stigmata.”
Imaging for Early Detection of Pancreatic Ductal Adenocarcinoma: Updates and Challenges in the Implementation of Screening and Surveillance Programs
Chenchan Huang et al.
AJR 2024; 223:e2431151 - “Lifetime risk of PDA exceeding 5% has been used to identify individuals at high risk . Multiple guidelines recommend that this population, which makes up 10–15% of persons diagnosed with PDA, undergo screening. HRIs include patientsnwho test positive for a pathogenic germline variant (PGV) and cases of familial PDA . PGVs include genes such as BRCA1; BRCA2; ATM; PALB2; mismatch repair genes MLH1, MSH2, MSH6, and PMS2 (Lynch syndrome); CDKN2A (familial atypical multiple mole melanoma syndromes); STK11 (Peutz-Jeghers syndrome); and PRSS1 (hereditary pancreatitis), with the last four having the highest relative risks for PDA.”
Imaging for Early Detection of Pancreatic Ductal Adenocarcinoma: Updates and Challenges in the Implementation of Screening and Surveillance Programs
Chenchan Huang et al.
AJR 2024; 223:e2431151 - “Familial PDA is the presence of two or more relatives with PDA, including at least one first- or second-degree relative, in the absence of a known PGV; risk escalates as the number of affected first-degree relatives increases (Table 1). Known PGVs explain only 10–20% of cases of familial PDA. Other likely causative factors include shared epigenetic mechanisms, genetic elements, or environmental influences contributing to the inheritance pattern . About 50% of patients with PDA and PGVs do not have a history of familial PDA, suggesting incomplete penetrance of some of the relevant PGVs.”
Imaging for Early Detection of Pancreatic Ductal Adenocarcinoma: Updates and Challenges in the Implementation of Screening and Surveillance Programs
Chenchan Huang et al.
AJR 2024; 223:e2431151 
Imaging for Early Detection of Pancreatic Ductal Adenocarcinoma: Updates and Challenges in the Implementation of Screening and Surveillance Programs
Chenchan Huang et al.
AJR 2024; 223:e2431151
Imaging for Early Detection of Pancreatic Ductal Adenocarcinoma: Updates and Challenges in the Implementation of Screening and Surveillance Programs
Chenchan Huang et al.
AJR 2024; 223:e2431151
Imaging for Early Detection of Pancreatic Ductal Adenocarcinoma: Updates and Challenges in the Implementation of Screening and Surveillance Programs
Chenchan Huang et al.
AJR 2024; 223:e2431151- “Identifying PDA early can be complicated by inherent tumor characteristics or concurrent pathologies that might distract the radiologist’s attention from subtle pancreatic lesions. The biologic understanding of the chronologic order of early PDA imaging findings is still evolving. Retrospective studies of serial prediagnostic CT examinations have shed light on some of the key imaging findings suggestive of early pancreatic cancer. Application of artificial intelligence (AI) to standard-of-care imaging may address current limitations and diagnostic errors that delay identification of PDA. Emerging research highlights AI’s considerable capability in detection of visually occult PDA at least 1 year before clinical diagnosis in addition to fully automated detection [79] and segmentation of small PDAs on standard portal venous phase imaging. Although these studies offer valuable insights and generate considerable hope, the clinical adoption of AI-facilitated early detection of PDA hinges on prospective validation within high-risk groups, especially alongside emerging fluid-based biomarkers of early detection.”
Imaging for Early Detection of Pancreatic Ductal Adenocarcinoma: Updates and Challenges in the Implementation of Screening and Surveillance Programs
Chenchan Huang et al.
AJR 2024; 223:e2431151 - “PDAs up to 20 mm can be isoenhancing and may not produce secondary signs such as pancreatic duct dilatation or cutoff that would be seen with larger tumors, so they go undetected. An isoenhancing mass is a lesion with an attenuation difference of less than 15 HU compared with normal pancreas in all phases. MRI and PET/CT may be useful for detecting these lesions, with MRI reported to have higher diagnostic accuracy than CT for tumors smaller than 2 cm (82% vs 69%). Tumor location such as the uncinate process and pancreatic tail is rarely associated with secondary signs. Systematic examination of parenchymal morphology, such as ensuring the absence of a rounded nodular border in the normal uncinate process and scrutinizing adjacent vessels for abnormal soft-tissue involvement, is recommended.”
Imaging for Early Detection of Pancreatic Ductal Adenocarcinoma: Updates and Challenges in the Implementation of Screening and Surveillance Programs
Chenchan Huang et al.
AJR 2024; 223:e2431151 - Indirect Features of PDA
“Among individuals with PDA, subtle indirect findings hinting at early PDA can manifest on CT during the preclinical phase (i.e., 3–36 months before clinical diagnosis). Focal parenchymal atrophy, also described as the K sign and defined as parenchymal narrowing compared with upstream and downstream parenchyma, has been identified as one of the earliest findings. It has been observed a mean of 1.8–4.6 years before PDA diagnosis [75, 76]. Focal parenchymal atrophy is distinct from the late sign of pancreatic tail atrophy and has been observed on 37.9– 58.5% of prediagnostic CT scans, but it is rarely seen in control patients (0.16%) . The etiology of focal parenchymal atrophy is not well understood, but one hypothesis is that it occurs when precursor pancreatic intraepithelial neoplasia lesions obstruct peripheral branch ducts, destroying acinar cells, which are replaced by fat or fibrosis. This sign often disappears as the pancreatic mass enlarges. The fibrosis may manifest as focal faint parenchymal enhancement, which one study found on 26.2% of prediagnostic CT scans obtained 3.3 years before diagnosis.”
Imaging for Early Detection of Pancreatic Ductal Adenocarcinoma: Updates and Challenges in the Implementation of Screening and Surveillance Programs
Chenchan Huang et al.
AJR 2024; 223:e2431151 - ”Localized steatosis can occur 1.6 years before diagnosis of PDA and has been seen on 19.5% of prediagnostic CT scans . Because diffuse pancreatic steatosis is more common on prediagnostic CT of patients with PDA than on that of control patients after accounting for BMI and DM (adjusted OR, 2.7; 95% CI, 1.06–6.85), it has been proposed as an independent risk factor for future PDA. However, more studies are necessary to validate this finding.”
Imaging for Early Detection of Pancreatic Ductal Adenocarcinoma: Updates and Challenges in the Implementation of Screening and Surveillance Programs
Chenchan Huang et al.
AJR 2024; 223:e2431151 - “Main-duct abnormality, such as cutoff or dilatation without a discrete mass, may be present up to 1.1 years before diagnosis of PDA . However, these observations frequently escape notice in clinical settings, resulting in diagnostic delays. Considerable variation exists among different observers when assessing these findings. Furthermore, these findings lack specificity for early PDA, as they are also seen in control individuals . Most importantly, the pancreas retains a morphologically normal appearance on prediagnostic CT scans for many patients. This poses a significant challenge, given that cancer progression from subclinical status inimaging to stage IV can be swift.
Imaging for Early Detection of Pancreatic Ductal Adenocarcinoma: Updates and Challenges in the Implementation of Screening and Surveillance Programs
Chenchan Huang et al.
AJR 2024; 223:e2431151 - “For patients diagnosed with PDA, survival is impeded by late stage diagnosis. However, the lack of reliable biomarkers and the rarity of the disease make screening the general population impractical. HRIs and persons with precursor cystic lesions are reasonable focus points for surveillance guidelines, yet collectively they represent the minority of cases. The ongoing EDI explores the ENDPAC model’s effectiveness in detecting early PDA in patients over 50 years old with NOD. The ENDPAC model shows promise, but its performance awaits assessment. Although highrisk surveillance programs offer improved outcomes, they raise concerns of unnecessary surgeries. PCL surveillance shares these drawbacks; hence, there is a pressing need for better risk stratification and an accurate noninvasive biomarkers.”
Imaging for Early Detection of Pancreatic Ductal Adenocarcinoma: Updates and Challenges in the Implementation of Screening and Surveillance Programs
Chenchan Huang et al.
AJR 2024; 223:e2431151
- “The overall risk of malignancy in pancreatic cysts may be as low as 0.5 to 1.5%, and the annual risk of progression is 0.5%.7,15 Conversely, studies estimate that 15% of all pancreatic adenocarcinomas originate from mucinous cysts, and these cysts are the sole recognizable precursors of malignant transformation that can be identified on cross-sectional imaging.16-18 Thus, identification of cysts at risk for progression provides an opportunity for prevention or early detection of cancer. Although surgical resection is the only curative treatment option, it carries a risk of major complications, despite technical advances.”
Pancreatic Cysts
Tamas A. Gonda, Djuna L. Cahen, and James J. Farrell
N Engl J Med 2024;391:832-43. - “There are more than 20 types of epithelial and nonepithelial pancreatic cysts, but the majority belong to the six most common histologic categories. The two most prevalent benign lesions, pseudocysts and serous cystadenomas, account for 15 to 25% of all pancreatic cysts. The two types of mucinous cysts, intraductal papillary mucinous neoplasms (IPMNs) and mucinous cystic neoplasms (MCNs), are the predominant premalignant cystic lesions and account for approximately50% of cysts that are found incidentally on imaging for other indications. Solid pseudopapillary neoplasms and cystic pancreatic neuroendocrine tumors are two less common malignant cystic neoplasms.”
Pancreatic Cysts
Tamas A. Gonda, Djuna L. Cahen, and James J. Farrell
N Engl J Med 2024;391:832-43.
Pancreatic Cysts
Tamas A. Gonda, Djuna L. Cahen, and James J. Farrell
N Engl J Med 2024;391:832-43.- Pancreas Cysts: Key Points
• Pancreatic cysts are common and are being discovered at an increasing rate on cross-sectional imaging, but only a minority progress to cancer.
• The most important goal is to identify the small percentage of cystic lesions associated with a substantialrisk of cancer, and this should be done through a multidisciplinary evaluation based on an algorithmic approach.
• In many cases, imaging, symptom assessment, and laboratory tests can help distinguish benign cysts from those associated with a low, intermediate, or high risk of malignant transformation.
• Endoscopic ultrasonography should be considered for equivocal findings or intermediate-risk cysts.
• Endoscopic ultrasonography and fluid aspiration for cytologic and molecular analysis may help in risk stratification for patients with intermediate-risk cysts.
• Surgical evaluation is warranted for high-risk cysts and for intermediate-risk cysts with multiple risk features, whereas surveillance is used for low-risk cysts - “Serous cystadenomas are benign, slow-growing lesions that predominantly affect women innthe fifth to seventh decades of life.25 These cystsncommonly have a microcystic (honeycomb) appearancenbut may be manifested as solid, macrocysticnor unilocular lesions. A central scar on computed tomography (CT) or magnetic resonance imaging (MRI) is a pathognomonic feature, but it is observed in only 30% of cases. In the absence of typical morphologic features, further evaluation may be necessary to confirm the diagnosis. Although most cases are asymptomatic,large serous cystadenomas can cause abdominal pain, pancreatitis, and biliary obstruction.”
Pancreatic Cysts
Tamas A. Gonda, Djuna L. Cahen, and James J. Farrell
N Engl J Med 2024;391:832-43. - “MCNs are the less common type of mucinous cysts. They characteristically contain ovarian like stroma and almost exclusively affect women in the fourth to sixth decades of life. MCNs are single, thick-walled, mostly unilocular cysts that are generally situated in the distal pancreas. In contrast to intraductal papillary neoplasms, which are much more common, MCNs have no communication with the pancreatic ducts. Although rare, the presence of peripheral (eggshell) calcifications is a diagnostic hallmark. The risk of advanced neoplasia (high-grade dysplasia or cancer) in patients with MCNs was previously reported to be as high as 30 to 40%, but when the presence of pathognomonic ovariantype stroma is confirmed, only 5 to 15% of MCNs contain invasive cancer.”
Pancreatic Cysts
Tamas A. Gonda, Djuna L. Cahen, and James J. Farrell
N Engl J Med 2024;391:832-43. - “IPMNs are the most common type of mucinous cystic lesions, with an equal sex distribution and a peak incidence between the fifth and seventh decades of life. These neoplasms, which arise from the ductal cells, are often multifocal and located throughout the pancreas. IPMNs are classified according to ductal involvement as main-duct, branch-duct, or mixedtype IPMNs. Main-duct IPMNs, which are less common than the branch-duct and mixed-duct types, are characterized by diffuse or segmental dilatation of the main duct (often due to excessive intraductal mucin production) in the absence of a cystic lesion.”
Pancreatic Cysts
Tamas A. Gonda, Djuna L. Cahen, and James J. Farrell
N Engl J Med 2024;391:832-43.
Pancreatic Cysts
Tamas A. Gonda, Djuna L. Cahen, and James J. Farrell
N Engl J Med 2024;391:832-43.- “The risk of malignant transformation depends on the histologic and anatomical subtypes and ranges from 1 to 38% for branchduct IPMNs and 33 to 85% for main-duct or mixed-type IPMNs. These estimates are mostly from surgical series, and more recent data suggest the risk may be lower. The probable field defect responsible for the multifocality also provides a small concomitant risk of pancreatic cancer, separate from the cyst of interest.”
Pancreatic Cysts
Tamas A. Gonda, Djuna L. Cahen, and James J. Farrell
N Engl J Med 2024;391:832-43. - “Solid pseudopapillary neoplasms most often develop in women in their second or third decade of life. These lesions, which can be located throughout the pancreas, have a well demarcated, heterogeneous appearance, with both solid and cystic components and, in some cases, irregular calcifications. The majority of solid pseudopapillary neoplasms are associated with a low risk of metastasis, and 10 to 15% are classified on histologic evaluation as solid pseudopapillary carcinoma.”
Pancreatic Cysts
Tamas A. Gonda, Djuna L. Cahen, and James J. Farrell
N Engl J Med 2024;391:832-43. - “Cystic pancreatic endocrine neoplasms arise from the pancreatic endocrine cells and are essentially a cystic degeneration of pancreatic neuroendocrine tumors, often with thick, enhancing walls on radiologic imaging Although most of these neoplasms are sporadic and nonfunctioning, up to 10% arise in patients with multiple endocrine neoplasia type 1. More than 80% of cystic pancreatic endocrine neoplasms express somatostatin receptors, which can be detected by means of positron-emission tomography with octreotide or dotatate tracers. Features associated with a poor prognosis, which are similar to those for solid pancreatic endocrine tumors, include a high histologic grade, a diameter of 2 cm or more, symptoms, a Ki-67 proliferation index of 3% or higher, and lymphovascular invasion.”
Pancreatic Cysts
Tamas A. Gonda, Djuna L. Cahen, and James J. Farrell
N Engl J Med 2024;391:832-43. - “A subsequent evaluation of symptoms can aid in risk stratification, although a minority of cysts are symptomatic. Jaundice that is caused by biliary obstruction is considered a high-risk feature. Pancreatitis (due to obstruction of the pancreatic duct by the cyst or produced mucin) and abdominal pain are considered intermediate- risk factors when they are related to the cyst, which is often difficult to confirm. With respect to laboratory testing, an elevation in levels of the serum marker CA 19-9 has been associated with an increased risk of malignant transformation. Similarly, new-onset diabetes is associated with an increased risk of advanced neoplasia. Therefore, an elevation in CA 19-9 and newly abnormal levels of glycated hemoglobin are both associated with an intermediate risk.”
Pancreatic Cysts
Tamas A. Gonda, Djuna L. Cahen, and James J. Farrell
N Engl J Med 2024;391:832-43. - “DNA can be isolated from cyst fluid, and the detection of mutations associated with specific neoplasms can be helpful, particularly when other findings are inconclusive and the amount of fluid obtained is small (≤0.5 ml). The presence of a VHL mutation is nearly 100% specific for serous cystadenoma but is identified in only 25 to 50% of cases.The KRAS mutation,which is considered a founder mutation, is more than 95% specific for either type of mucinous cyst, with a sensitivity of 60 to 70%. Mutations in GNAS are specific for IPMNs (but not MCNs). and are detected in 30 to 60% of cases. The absence of a VHL mutation combined with the presence of a KRAS or GNAS mutation is nearly 100% specific for mucinous cysts, with an accuracy of 97%. Detection of a CT NB1 mutation has high specificity for solid pseudopapillary tumors, and the presence of a MEN1 mutation has high specificity for cystic pancreatic endocrine neoplasms.”
Pancreatic Cysts
Tamas A. Gonda, Djuna L. Cahen, and James J. Farrell
N Engl J Med 2024;391:832-43. - “ For most low-risk cysts, surveillance is recommended, with its intensity depending on thebaseline risk. Follow-up every 6 months is advised in the first year, with yearly follow-up thereafter, but the interval can be lengthened with continued stability of the lesion. Surveillance is typically performed with cross-sectional imaging (preferably MRI with magnetic resonance cholangiopancreatography or, if that is unfeasible, with contrast-enhanced CT) or, for larger cysts and cysts with worrisome features, MRI and endoscopic ultrasonography on analternating schedule or combined.”
Pancreatic Cysts
Tamas A. Gonda, Djuna L. Cahen, and James J. Farrell
N Engl J Med 2024;391:832-43. - “Cyst stability is typically defined as less than a 20% increase in the greatest diameter or growth of less than 2.5 mm per year. Faster growth or the development of new intermediate-risk or highrisk features should warrant reconsideration of endoscopic ultrasonography, with or without guided fine-needle aspiration or biopsy, or surgical resection. Current data do not unequivocally support discontinuing surveillance. However, for low-risk lesions that have remained stable for years, the risk of progression is minimal, and cessation of surveillance becomes a reasonable option. Also, a patient’s health status needs to be reevaluated regularly, since a change in health status may warrant adjustment of surveillance goals.”
Pancreatic Cysts
Tamas A. Gonda, Djuna L. Cahen, and James J. Farrell
N Engl J Med 2024;391:832-43. - “Current data do not unequivocally support discontinuing surveillance. However, for low-risk lesions that have remained stable for years, the risk of progression is minimal, and cessation of surveillance becomes a reasonable option. Also, a patient’s health status needs to be reevaluated regularly, since a change in health status may warrant adjustment of surveillance goals.”
Pancreatic Cysts
Tamas A. Gonda, Djuna L. Cahen, and James J. Farrell
N Engl J Med 2024;391:832-43. - “Pancreatic cysts are strikingly common, mostly incidental findings. Although the majority of these cysts are associated with a very low risk of malignant transformation, a minority may offer an opportunity to recognize and eliminate highrisk precursors of pancreatic cancer. Several guidelines provide recommendations for evaluation, treatment, and surveillance, but they are based on expert opinion rather than solid evidence. Fortunately, an initiative to develop a unified global guideline in the next 1 to 2 years is widely endorsed.”
Pancreatic Cysts
Tamas A. Gonda, Djuna L. Cahen, and James J. Farrell
N Engl J Med 2024;391:832-43. - “An important goal in the management of pancreatic cysts is to reduce the surveillance burden for low-risk lesions while improving the recognition of malignant and premalignant cysts. To accomplish this, prospective studies are needed to determine the true predictive value of known risk factors for cancer. Also, advances in our understanding of the molecular evolution of cystic precursors will lead to the identification of increasingly sensitive biomarkers derived from either cyst fluid, pancreatic juice, or blood. The integration of radiomics (machine learning and artificial intelligence) and advances in endoscopic imaging, such as needle-based, intracystic confocal microscopy, may enhance the sensitivity of risk stratification. Although surgery has become much safer, alternative and less invasive techniques are needed, especially for prophylactic interventions.”
Pancreatic Cysts
Tamas A. Gonda, Djuna L. Cahen, and James J. Farrell
N Engl J Med 2024;391:832-43. - “The current approach to management relies on identifying the cyst type and conducting a multimodal assessment of the risk of cancer, an assessment that is mostly noninvasive, with selective use of endoscopic ultrasonography and tissue sampling. The best personalized approach will be provided by models that combine risk factors, clinical variables, imaging characteristics, and molecular markers. Treatment and surveillance decisions should follow an algorithmic framework that is overseen by a multidisciplinary team and that incorporates shared decision making with the patient.”
Pancreatic Cysts
Tamas A. Gonda, Djuna L. Cahen, and James J. Farrell
N Engl J Med 2024;391:832-43.
- Background: We identified computed tomography (CT)-derived radiomic features predictive of tumor progression within three months, then examined their ability to prognosticate overall survival (OS) along with clinical features in pancreatic cancer. We evaluated these features in patients with unresected pancreatic cancer who underwent stereotactic body radiation therapy (SBRT) in sequence with chemotherapy, but not surgery.
Conclusions: CT-derived radiomic features predict rapid tumor progression following SBRT, confer nearly a twofold increase in mortality risk, and, along with patient age, enhance the identification of patients with stage II-IIIpancreatic cancer with poor OS.
Utility of radiomic features in predicting clinical outcomes in stage II-III pancreatic cancer.
Haruka Itakura,et al
American Society of Clinical Oncology Sept 2024 (abstract) - “In this retrospective study, we examined a cohort of 101 patients with stage II-III pancreatic cancer who underwent SBRT with sequential chemotherapy at a single institution (Stanford Health Care) between 1999- 2020. From their pre-SBRT contrast-enhanced CT images with segmented tumors, delineating regions-of-interest, we extracted 900 radiomic (quantitative pixel-level imaging characteristic) features. In the first phase, we identified radiomic features that predicted rapid tumor progression within three months following SBRT.”
Utility of radiomic features in predicting clinical outcomes in stage II-III pancreatic cancer.
Haruka Itakura,et al
American Society of Clinical Oncology Sept 2024 (abstract) - Background: When determining the initial chemotherapy regimen for advanced or metastatic pancreatic cancer, various factors must be evaluated. The decision between FOLFIRINOX and Gemcitabine/Nab-paclitaxel (GnP) is challenging, as patient survival hinges on the efficacy and toxicity profiles of these treatments, alongside individual patient characteristics and vulnerabilities. This study aims to guide the selection of an appropriate first-line chemotherapy regimen for advanced or metastatic pancreatic cancer by leveraging machine learning (ML) methods to predict survival outcomes. Conclusions: We developed the ML models that can compute the probability of OS based on the routinely collected data from patients with advanced or metastatic pancreatic cancer. To the best of our knowledge, this is the first ML solution aimed at aiding clinicians in the selection of the first-line chemotherapy regimen for pancreatic cancer.
Predicting chemotherapy response in patients with advanced or metastatic pancreatic cancer using machine learning.
Moonho Kim, Gyucheol Choi, Jamin Koo
American Society of Clinical Oncology. Sept 2024 - Results: The median age of the patients was 66 years, with 62.3% being male. The MLnmodels achieved the ROC-AUC of 0.81 when predicting OS after 12 months following the initial administration of FOLFIRINOX (n=61) or GnP (n=47). Five (peritoneal metastases, other metastases, bilirubin level, white blood cell counts, and retroperitoneal lymph node metastases) or four (age, tumor location, sex, and metastatic status) covariates were used to achieve the predictive accuracy for the two regimens, respectively. The median OS of the high versus low risk groups of FOLFIRINOX predicted by the ML models were significantly different (7 vs 18 months, P, 0.01), recording the hazard ratio (HR) of 2.79 (95% CI, 1.47-5.26). Similarly, the median OS of the high and low risk groups of GnP were significantly different (8 vs 16 months,P , 0.001, HR 3.50, 95% CI, 1.60-7.66).
Predicting chemotherapy response in patients with advanced or metastatic pancreatic cancer using machine learning.
Moonho Kim, Gyucheol Choi, Jamin Koo
American Society of Clinical Oncology. Sept 2024
- “Among the 5579 patients with localized pNETs ≤2 cm during 2015 and 2020, 2027 underwent observation (36.3%) whereas 3552 underwent resection (63.7%). On multivariable analysis female sex, further distance traveled, tumor size 1.01cm-2 cm, and pancreas body/tail tumors were associated with surgery whereas increasing age, later year of diagnosis, and treatment at an academic program were associated with observation.”
Trends in the Use of Observation for Small Nonfunctional Pancreatic Neuroendocrine Tumors.
Ruff SM, Dillhoff M, Tsai S, Pawlik TM, Sukrithan V, Konda B, Cloyd JM.
JAMA Surg. 2024 Aug 21: - “These findings highlight a growing nationwide trend in the initial nonoperative management of small NF-pNETs. As most patients with small NF-pNETs still undergo resection despite its associated morbidity and unclear survival advantage, research should focus on whether barriers exist to adopting active surveillance in specific patient populations. Further research on the long-term efficacy of active surveillance, cost effectiveness strategies, and further refining patient-related risk factors other than tumor size will ultimately guide the evidence based and personalized management of small NF-pNETs.”
Trends in the Use of Observation for Small Nonfunctional Pancreatic Neuroendocrine Tumors.
Ruff SM, Dillhoff M, Tsai S, Pawlik TM, Sukrithan V, Konda B, Cloyd JM.
JAMA Surg. 2024 Aug 21: - Background. PanNETs are a rare group of pancreatic tumors that display heterogeneous histopathological and clinical behavior. Nodal disease has been established as one of the strongest predictors of patient outcomes in PanNETs. Lack of accurate preoperative assessment of nodal disease is a major limitation in the management of these patients, in particular those with small (< 2 cm) low-grade tumors. The aim of the study was to evaluate the ability of radiomic features (RF) to preoperatively predict the presence of nodal disease in pancreatic neuroendocrine tumors (PanNETs).
Preoperative Prediction of Lymph Node Metastases in Nonfunctional Pancreatic Neuroendocrine Tumors Using a Combined CT Radiomics-Clinical Model.
Ahmed TM, Zhu Z, Yasrab M, Blanco A, Kawamoto S, He J, Fishman EK, Chu L, Javed AA
Ann Surg Oncol. 2024 Aug 23. doi: 10.1245/s10434-024-16064-4. Epub ahead of print - Results. Of the 320 patients included in the study, 92 (28.8%) had nodal disease based on histopathological assessment of the surgical specimen. A radiomic signature based on ten selected RF was developed. Clinicopathological characteristics predictive of nodal disease included tumor grade and size. Upon internal validation the combined radiomics and clinical feature model demonstrated adequate performance (AUC 0.80) in identifying nodal disease. The modelmaccurately identified nodal disease in 85% of patients with small tumors (< 2 cm).
Conclusions. Non-invasive preoperative assessment of nodal disease using RF and clinicopathological characteristics is feasible.
Preoperative Prediction of Lymph Node Metastases in Nonfunctional Pancreatic Neuroendocrine Tumors Using a Combined CT Radiomics-Clinical Model.
Ahmed TM, Zhu Z, Yasrab M, Blanco A, Kawamoto S, He J, Fishman EK, Chu L, Javed AA
Ann Surg Oncol. 2024 Aug 23. doi: 10.1245/s10434-024-16064-4. Epub ahead of print - ”In conclusion, this study presents a novel tool on the basis of RFs and clinical factors for accurate prediction of nodal disease in NF-PanNETs. Furthermore, we demonstrated that addition of RFs to clinical factors can make this model more robust and accurate. Further validation of this model is required to assess its performance in external cohorts. If validated, this tool could allow for non-invasive serial assessment of nodal disease in patients with well differentiated nonfunctioning PanNETs to tailor management plans and provide precise therapy on the basis of each patient’s disease biology.”
Preoperative Prediction of Lymph Node Metastases in Nonfunctional Pancreatic Neuroendocrine Tumors Using a Combined CT Radiomics-Clinical Model.
Ahmed TM, Zhu Z, Yasrab M, Blanco A, Kawamoto S, He J, Fishman EK, Chu L, Javed AA
Ann Surg Oncol. 2024 Aug 23. doi: 10.1245/s10434-024-16064-4. Epub ahead of print - Purpose: The purpose of this study was to develop a radiomics-based algorithm to identify small pancreatic neuroendocrine tumors(PanNETs) on CT and evaluate its robustness across manual and automated segmentations, exploring the feasibility of automated screening.
Conclusion: Radiomics features identify small PanNETs, with stable performance when extracted using automated segmentations. These models demonstrate high sensitivity, complementing the high specificity of radiologists, and could serve as opportunistic screeners.
Radiomics machine learning algorithm facilitates detection of small pancreatic neuroendocrine tumors on CT.
Lopez-Ramirez F, Soleimani S, Azadi JR, Sheth S, Kawamoto S, Javed AA, Tixier F, Hruban RH, Fishman EK, Chu LC.
Diagn Interv Imaging. 2024 Sep 14:S2211-5684(24)00172-4. doi: 10.1016/j.diii.2024.08.003. Epub ahead of print. PMID: 39278763 . - Results:A total of 135 patients with 142 PanNETs,and135 healthy controls were included.There were 168 women and 102 men,with a mean age of 55.4 +/-11.6(standard deviation) years(range:20−85years). Median PanNET size was 1.3cm (Q1,1.0;Q3,1.5;range:0.5−1.9).The arterial phase Light GBM model achieved the best performance in the test set,with 90% sensitivity (95% confidence interval[CI]:80−98),76% specificity (95%CI:62−88)and an AUC of 0.87 (95% CI:0.79−0.94).Using features from the automated segmentations,this model achieved an AUC of 0.86(95%CI:0.79−0.93). In comparison, the radiologists achieved a mean 50% sensitivity and 100% specificity using arterial phase CT images.
Radiomics machine learning algorithm facilitates detection of small pancreatic neuroendocrine tumors on CT.
Lopez-Ramirez F, Soleimani S, Azadi JR, Sheth S, Kawamoto S, Javed AA, Tixier F, Hruban RH, Fishman EK, Chu LC.
Diagn Interv Imaging. 2024 Sep 14:S2211-5684(24)00172-4. doi: 10.1016/j.diii.2024.08.003. Epub ahead of print.
Radiomics machine learning algorithm facilitates detection of small pancreatic neuroendocrine tumors on CT.
Lopez-Ramirez F, Soleimani S, Azadi JR, Sheth S, Kawamoto S, Javed AA, Tixier F, Hruban RH, Fishman EK, Chu LC.
Diagn Interv Imaging. 2024 Sep 14:S2211-5684(24)00172-4. doi: 10.1016/j.diii.2024.08.003. Epub ahead of print.
Radiomics machine learning algorithm facilitates detection of small pancreatic neuroendocrine tumors on CT.
Lopez-Ramirez F, Soleimani S, Azadi JR, Sheth S, Kawamoto S, Javed AA, Tixier F, Hruban RH, Fishman EK, Chu LC.
Diagn Interv Imaging. 2024 Sep 14:S2211-5684(24)00172-4. doi: 10.1016/j.diii.2024.08.003. Epub ahead of print.
Radiomics machine learning algorithm facilitates detection of small pancreatic neuroendocrine tumors on CT.
Lopez-Ramirez F, Soleimani S, Azadi JR, Sheth S, Kawamoto S, Javed AA, Tixier F, Hruban RH, Fishman EK, Chu LC.
Diagn Interv Imaging. 2024 Sep 14:S2211-5684(24)00172-4. doi: 10.1016/j.diii.2024.08.003. Epub ahead of print.- “In conclusion, this study demonstrates the feasibility of radiomics-based tools, with features extracted from manual and automatic pancreas segmentations, to detect small PanNETs with higher sensitivity than two experienced radiologists.These preliminary results suggest that radiomics could potentially serve as a second reader or opportunist screener for detection of low-stage disease and ultimately impact clinical care.”
Radiomics machine learning algorithm facilitates detection of small pancreatic neuroendocrine tumors on CT.
Lopez-Ramirez F, Soleimani S, Azadi JR, Sheth S, Kawamoto S, Javed AA, Tixier F, Hruban RH, Fishman EK, Chu LC.
Diagn Interv Imaging. 2024 Sep 14:S2211-5684(24)00172-4. doi: 10.1016/j.diii.2024.08.003. Epub ahead of print.
- “Between June 2012 and December 2022, a total of 4039 patients’ multiphase (arterial phase and portal venous phase) contrastenhanced CT images from six hospitals were included under the following inclusion criteria: Patients (1) were eighteen years or older; (2) did not have a history of hepatectomy, transarterial chemotherapy (TACE), or radiofrequency ablation (RFA) before CT imaging; (3) had pathologically confirmed malignant tumors; and (4) had benign tumors confirmed either by consensus among three radiologists or by follow-up of at least six months using two imaging modalities. The method used for retrospective data collection and basic patientinformation including sex and age are depicted in Fig. 1a and Table 1, respectively. Furthermore, clinical testing was conducted on two real world clinical evaluation queues (Fig. 1b): West China Tianfu Center and Sanya People’s Hospital. At Tianfu Center, we examined 184 cases, while at Sanya People’s Hospital, 235 cases were assessed. Gender andAge assignment was based on government-issued IDs.”
Focal liver lesion diagnosis with deep learning and multistage CT imaging
Yi Wei et al.
Nature Communications | ( 2024) 15:7040 - Background/objectives: Pancreatic cyst management can be distilled into three separate pathways -- discharge, monitoring or surgery based on the risk of malignant transformation. This study compares the performance of artificial intelligence (AI) models to clinical care for this task.
Methods: Two explainable boosting machine (EBM) models were developed and evaluated using clinical features only, or clinical features and cyst fluid molecular markers (CFMM) using a publicly available dataset, consisting of 850 cases (median age 64; 65 % female) with independent training (429 cases) and holdout test cohorts (421 cases). There were 137 cysts with no malignant potential, 114 malignant cysts, and 599 IPMNs and MCNs.
Performance of explainable artificial intelligence in guiding the management of patients with a pancreatic cyst.
Lavista Ferres JM, Oviedo F, Robinson C, Chu L, Kawamoto S, Afghani E, He J, Klein AP, Goggins M, Wolfgang CL, Javed AA, Dodhia R, Papadopolous N, Kinzler K, Hruban RH, Weeks WB, Fishman EK, Lennon AM.
Pancreatology. 2024 Sep 2:S1424-3903(24)00730-0. doi: 10.1016/j.pan.2024.09.001. Epub ahead of print. PMID: 39261223. - Results: The EBM and EBM with CFMM models had higher accuracy for identifying patients requiring monitoring (0.88 and 0.82) and surgery (0.66 and 0.82) respectively compared with current clinical care (0.62 and 0.58). For discharge, the EBM with CFMM model had a higher accuracy (0.91) than either the EBM model (0.84) or current clinical care (0.86). In the cohort of patients who underwent surgical resection, use of the EBM-CFMM model would have decreased the number of unnecessary surgeries by 59 % (n=92), increased correct surgeries by 7.5 % (n=11), identified patients who require monitoring by 122 % (n=76), and increased the number of patients correctly classified for discharge by 138 % (n=18) compared to clinical care.
Conclusions: EBM models had greater sensitivity and specificity for identifying the correct management compared with either clinical management or previous AI models. The model predictions are demonstrated to be interpretable by clinicians.
Performance of explainable artificial intelligence in guiding the management of patients with a pancreatic cyst.
Lavista Ferres JM, Oviedo F, Robinson C, Chu L, Kawamoto S, Afghani E, He J, Klein AP, Goggins M, Wolfgang CL, Javed AA, Dodhia R, Papadopolous N, Kinzler K, Hruban RH, Weeks WB, Fishman EK, Lennon AM.
Pancreatology. 2024 Sep 2:S1424-3903(24)00730-0. doi: 10.1016/j.pan.2024.09.001. Epub ahead of print. PMID: 39261223. - “Conclusions: EBM models had greater sensitivity and specificity for identifying the correct management compared with either clinical management or previous AI models. The model predictions are demonstrated to be interpretable by clinicians.”
Performance of explainable artificial intelligence in guiding the management of patients with a pancreatic cyst.
Lavista Ferres JM, Oviedo F, Robinson C, Chu L, Kawamoto S, Afghani E, He J, Klein AP, Goggins M, Wolfgang CL, Javed AA, Dodhia R, Papadopolous N, Kinzler K, Hruban RH, Weeks WB, Fishman EK, Lennon AM.
Pancreatology. 2024 Sep 2:S1424-3903(24)00730-0. doi: 10.1016/j.pan.2024.09.001. Epub ahead of print. PMID: 39261223. - “The management of patients with pancreatic cysts can be distilled into three separate pathways based on the risk of malignant transformation. Cysts with pancreatic cancer or high-grade dysplasia, such as cystic degeneration of pancreatic adenocarcinoma, an IPMN with high-grade dysplasia or associated invasive adenocarcinoma, should be surgically resected . Patients harboring an IPMN or MCN with low grade dysplasia are recommended for surveillance. Patients with a pancreatic cyst with no malignant potential, such as a pseudocyst or a serous cystadenoma (SCA), require no follow-up and these patients can be discharged.”
Performance of explainable artificial intelligence in guiding the management of patients with a pancreatic cyst.
Lavista Ferres JM, Oviedo F, Robinson C, Chu L, Kawamoto S, Afghani E, He J, Klein AP, Goggins M, Wolfgang CL, Javed AA, Dodhia R, Papadopolous N, Kinzler K, Hruban RH, Weeks WB, Fishman EK, Lennon AM.
Pancreatology. 2024 Sep 2:S1424-3903(24)00730-0. doi: 10.1016/j.pan.2024.09.001. Epub ahead of print. PMID: 39261223. - “Correctly preoperatively classifying patients into these three different management pathways is challenging, with large surgical series finding that 25 % of cyst patients who undergo surgical resection have cysts with no malignant potential , while up to 73 % of patients with IPMNs who undergo surgical resection have low-grade dysplasia and in hindsight did not require surgery.”
Performance of explainable artificial intelligence in guiding the management of patients with a pancreatic cyst.
Lavista Ferres JM, Oviedo F, Robinson C, Chu L, Kawamoto S, Afghani E, He J, Klein AP, Goggins M, Wolfgang CL, Javed AA, Dodhia R, Papadopolous N, Kinzler K, Hruban RH, Weeks WB, Fishman EK, Lennon AM.
Pancreatology. 2024 Sep 2:S1424-3903(24)00730-0. doi: 10.1016/j.pan.2024.09.001. Epub ahead of print. PMID: 39261223. - “Artificial intelligence (AI) models are uniquely equipped to handle a large number of diverse and complex features, potentially aiding physicians and patients in making informed decisions. One early example of this is Multivariate Organization of Combinatorial Alterations (MOCA) model, which used combinatorial feature transformations and random sampling with iterative optimization to engineer a subset of composite markers with high predictive power. This machine learning model was applied to 862 patients with pancreatic cysts who underwent surgical resection, and was found to be more accurate than conventional clinical and imaging criteria alone for classifying patients into the three management groups of surgery, surveillance, or discharge.”
Performance of explainable artificial intelligence in guiding the management of patients with a pancreatic cyst.
Lavista Ferres JM, Oviedo F, Robinson C, Chu L, Kawamoto S, Afghani E, He J, Klein AP, Goggins M, Wolfgang CL, Javed AA, Dodhia R, Papadopolous N, Kinzler K, Hruban RH, Weeks WB, Fishman EK, Lennon AM.
Pancreatology. 2024 Sep 2:S1424-3903(24)00730-0. doi: 10.1016/j.pan.2024.09.001. Epub ahead of print. PMID: 39261223.
Performance of explainable artificial intelligence in guiding the management of patients with a pancreatic cyst.
Lavista Ferres JM, Oviedo F, Robinson C, Chu L, Kawamoto S, Afghani E, He J, Klein AP, Goggins M, Wolfgang CL, Javed AA, Dodhia R, Papadopolous N, Kinzler K, Hruban RH, Weeks WB, Fishman EK, Lennon AM.
Pancreatology. 2024 Sep 2:S1424-3903(24)00730-0. doi: 10.1016/j.pan.2024.09.001. Epub ahead of print. PMID: 39261223.
Performance of explainable artificial intelligence in guiding the management of patients with a pancreatic cyst.
Lavista Ferres JM, Oviedo F, Robinson C, Chu L, Kawamoto S, Afghani E, He J, Klein AP, Goggins M, Wolfgang CL, Javed AA, Dodhia R, Papadopolous N, Kinzler K, Hruban RH, Weeks WB, Fishman EK, Lennon AM.
Pancreatology. 2024 Sep 2:S1424-3903(24)00730-0. doi: 10.1016/j.pan.2024.09.001. Epub ahead of print. PMID: 39261223.
Performance of explainable artificial intelligence in guiding the management of patients with a pancreatic cyst.
Lavista Ferres JM, Oviedo F, Robinson C, Chu L, Kawamoto S, Afghani E, He J, Klein AP, Goggins M, Wolfgang CL, Javed AA, Dodhia R, Papadopolous N, Kinzler K, Hruban RH, Weeks WB, Fishman EK, Lennon AM.
Pancreatology. 2024 Sep 2:S1424-3903(24)00730-0. doi: 10.1016/j.pan.2024.09.001. Epub ahead of print. PMID: 39261223.- “The results are even more striking when compared with clinical care. In this test cohort of patients, all of whom underwent surgical resection, use of the EBM with CFMM model decreases the number of unnecessary surgeries by 59 % (n=92), increases the number of correct surgeries by 7.5 % (n=11), better identifies patients who truly require monitoring by 122 % (n=76), and increases the number of patients correctly classified as being safe to discharge by 138 % (n=18) compared to clinical care. Overall, in this cohort of patients the use of the EBM with CFMM could have changed the management of at least 25 % of patients.”
Performance of explainable artificial intelligence in guiding the management of patients with a pancreatic cyst.
Lavista Ferres JM, Oviedo F, Robinson C, Chu L, Kawamoto S, Afghani E, He J, Klein AP, Goggins M, Wolfgang CL, Javed AA, Dodhia R, Papadopolous N, Kinzler K, Hruban RH, Weeks WB, Fishman EK, Lennon AM.
Pancreatology. 2024 Sep 2:S1424-3903(24)00730-0. doi: 10.1016/j.pan.2024.09.001. Epub ahead of print. PMID: 39261223. - “This study shows the potential of an AI model to incorporate multiple features and its ability to generate a correct management plan which can help guide care for patients and their physicians. In this study, the performance of the EBM model was superior to clinical management in correctly identifying which patients required surveillance or should be referred for surgery. The impact of the CFMM can be seen when we look at the global feature importance score, where 6 of the top 9 features used by the model are CFMMs. Overall, the use of EBM with CFMM model couldhave changed the management of at least 25 % (n=105) of the patients compared with clinical management.”
Performance of explainable artificial intelligence in guiding the management of patients with a pancreatic cyst.
Lavista Ferres JM, Oviedo F, Robinson C, Chu L, Kawamoto S, Afghani E, He J, Klein AP, Goggins M, Wolfgang CL, Javed AA, Dodhia R, Papadopolous N, Kinzler K, Hruban RH, Weeks WB, Fishman EK, Lennon AM.
Pancreatology. 2024 Sep 2:S1424-3903(24)00730-0. doi: 10.1016/j.pan.2024.09.001. Epub ahead of print. PMID: 39261223. - “The EBM model has a number of features which are very attractive for use in clinical care. First, it has an explainable aspect which provides a transparent understanding of the features that are used to generate the prediction. In contrast with other machine learning models, such as deep neural networks, the feature contributions used to generate predictions of the EBM model are easy to quantify and isolate. This transparency allows health care providers to understand how features were used in the model and confirm that they make clinical and biological sense. Furthermore, instead of providing a positive or negative output, the EBM model outputs a calibrated probability vector for each predicted outcome for an individual patient. Both feature explanations and calibrated probabilities affords clinicians and patients a richer perspective of model operation and uncertainty when determining clinical management.”
Performance of explainable artificial intelligence in guiding the management of patients with a pancreatic cyst.
Lavista Ferres JM, Oviedo F, Robinson C, Chu L, Kawamoto S, Afghani E, He J, Klein AP, Goggins M, Wolfgang CL, Javed AA, Dodhia R, Papadopolous N, Kinzler K, Hruban RH, Weeks WB, Fishman EK, Lennon AM.
Pancreatology. 2024 Sep 2:S1424-3903(24)00730-0. doi: 10.1016/j.pan.2024.09.001. Epub ahead of print. PMID: 39261223. - “Future work should validate the model in a prospective cohort of patients including patients who undergo surgical resection and those undergoing surveillance. Finally, the feature contributions and explanations are predictive but not necessarily casual, in the sense that observed trends could be affected by interaction with unknown confounders or variables not captured as clinical features. As models are retrained in larger datasets is important to verify that overall feature importance is comparable across models, and prospectively evaluate explanations and the high uncertainty/error-prone probability thresholds with clinical judgement.”
Performance of explainable artificial intelligence in guiding the management of patients with a pancreatic cyst.
Lavista Ferres JM, Oviedo F, Robinson C, Chu L, Kawamoto S, Afghani E, He J, Klein AP, Goggins M, Wolfgang CL, Javed AA, Dodhia R, Papadopolous N, Kinzler K, Hruban RH, Weeks WB, Fishman EK, Lennon AM.
Pancreatology. 2024 Sep 2:S1424-3903(24)00730-0. doi: 10.1016/j.pan.2024.09.001. Epub ahead of print. PMID: 39261223. - “In conclusion, we have developed and evaluated two AI models for patients with pancreatic cysts, using clinical features alone or combined with CFMM, which demonstrate greater accuracy for identifying the correct management recommendation of discharge, monitoring or surgery compared with either clinical management or prior AI models. These models allow health care providers and patients to understand the probability of a management recommendation and interpret the impact of features used to make predictions.”
Performance of explainable artificial intelligence in guiding the management of patients with a pancreatic cyst.
Lavista Ferres JM, Oviedo F, Robinson C, Chu L, Kawamoto S, Afghani E, He J, Klein AP, Goggins M, Wolfgang CL, Javed AA, Dodhia R, Papadopolous N, Kinzler K, Hruban RH, Weeks WB, Fishman EK, Lennon AM.
Pancreatology. 2024 Sep 2:S1424-3903(24)00730-0. doi: 10.1016/j.pan.2024.09.001. Epub ahead of print. PMID: 39261223.
Small Bowel
- “Intramural hemorrhage of the small bowel results from deposition of red blood cells predominantly in the submucosal layer. There are several causes of intramural hemorrhage, including but not limited to trauma, vasculitis, coagulopathy, ischemia, amyloidosis, and Dieulafoy lesions . Patients present in a variety of ways, depending on the cause of the hemorrhage, but abdominal pain and GI bleeding are common symptoms. Increased attenuation and thickening of the bowel wall, which can be diffuse or focal, are visualized on CT images. The high attenuation is helpful for differentiating hemorrhage from other inflammatory and infectious causes of bowel wall thickening. A large hematoma can lead to luminal narrowing and bowel obstruction.”
Diffusely Infiltrative Small Bowel Disease
Preet Dhillon et al.
RadioGraphics 2024; 44(9):e230148 - “ACE inhibitor–induced angioedema is reversible as soon as 36 hours after ACE inhibitor cessation. Imaging shows submucosal bowel wall edema, mesenteric vessel engorgement, and ascites. The jejunum, followed by the ileum and then the duodenum, is the most commonly involved segment of the small intestine. ACE inhibitor–induced angioedema is typically diagnosed clinically. Laboratory values are often within normal limits, and the combination of clinical presentation and imaging findings aids clinicians in making the diagnosis. ACE inhibitor–induced angioedema is an important entity to recognize to prevent unnecessary concern for ischemic bowel, as the interloop mesenteric edema in combination with ascites can mimic small vessel ischemia. The pertinent clinical history facilitates correct diagnosis and guides appropriate change in medical therapy to avoid future occurrences.”
Diffusely Infiltrative Small Bowel Disease
Preet Dhillon et al.
RadioGraphics 2024; 44(9):e230148 - “GVHD affecting the bowel occurs after bone marrow or stem cell transplant. Donor T lymphocytes, or T cells, cause an immune response against mismatched antigens on recipient epithelial cells, triggering cytotoxic T-cell infiltration of the mucosa and cytokine release, which results in immune- mediated damage of the GI tract, skin, liver, and lung mucosa. Clinically, GVHD can be subclassified as acute GVHD (10–40 days, usually <100 days, after transplant) or chronic GVHD (>100 days and <3 years after transplant) . The focus here is on the diffusely infiltrative acute phase.”
Diffusely Infiltrative Small Bowel Disease
Preet Dhillon et al.
RadioGraphics 2024; 44(9):e230148 - “The characteristic findings in acute GVHD are bowel wall thickening and mural stratification due to avidly enhancing mucosa and serosa, with hypoattenuating intramural bowel wall edema. Diffuse involvement of the entire GI tract may be seen. Additional imaging findings can be hepatomegaly, ascites, and ground-glass opacities in the visualized lung bases if the lungs are involved. Definitive diagnosis is made with skin or GI tract biopsy, as opportunistic infections can mimic acute GVHD. Patients are then treated with steroids and advanced immunosuppressive therapy.”
Diffusely Infiltrative Small Bowel Disease
Preet Dhillon et al.
RadioGraphics 2024; 44(9):e230148
Spleen
- “Sarcoidosis is a systemic inflammatory condition characterized by noncaseating granulomas. Its annual incidence ranges from 1 to 15 per 100,000 individuals and is more common in women. While pulmonary and mediastinal lymph node involvement is common, affecting 90% of patients, splenic involvement is reported in close to 24% of cases. Splenic sarcoidosis at CT scans reveals multiple solid hypodense nodules of varying sizes, typically hypoenhancing after contrast administration, often coexisting with hepatic nodules and abdominal lymphadenopathies . Traditionally, these splenic lesions exhibit characteristic MRI features based on disease activity. Inflammatory lesions show high signals on T2 and DWI sequences, whereas fibrous lesions present with low signals on both T1 and T2 sequences.”
Spleen anomalies and lesions in CT and MRI: essentials for radiologists and clinicians—a pictorial review
Andres Felipe Herrera‑Ortiz et al.
Abdominal Radiology 2024 (in press) https://doi.org/10.1007/s00261-024-04405-6 - Splenic metastases are rare and often associated with advanced stages of widespread metastatic disease in melanoma,breast, ovarian, lung, and colon cancers . Splenic metastases are generally multiple, although isolated metastasis has also been reported as an even rarer occurrence. At CT, splenic metastases commonly present as hypodense lesions; nevertheless, their appearance can vary based on the primary tumor, occasionally manifesting as cystic lesions with diverse enhancement patterns. At MRI, splenic metastases present low signal intensity on T1 and high signal intensity on T2 sequences, with a variable degree of contrast enhancement, making their diagnosis challenging.
Spleen anomalies and lesions in CT and MRI: essentials for radiologists and clinicians—a pictorial review
Andres Felipe Herrera‑Ortiz et al.
Abdominal Radiology 2024 (in press) https://doi.org/10.1007/s00261-024-04405-6 - Primary splenic angiosarcoma predominantly affects patients in the 6th–7th decade of life, with an annual incidence of one case per 4 million individuals. This aggressive neoplasm displays a predilection for males and has a poor prognosis, marked by a high mortality rate and significant risk of rupture in up to 30% of cases. At CT imaging, splenic angiosarcoma often presents as solitary or multiple poorly defined nodular masses distorting the normal anatomy of the spleen and producing enlargement. The contrast enhancement pattern on CT varies depending on the extent of necrosis within the lesion. Its enhancement is usually centripetal and heterogeneous, and 69–100% of the cases tend to present with metastases, most commonly disseminating to the liver, lungs, adrenals, bones, and lymphatics .
Spleen anomalies and lesions in CT and MRI: essentials for radiologists and clinicians—a pictorial review
Andres Felipe Herrera‑Ortiz et al.
Abdominal Radiology 2024 (in press) https://doi.org/10.1007/s00261-024-04405-6
Vascular
- “Non-traumatic acute renal artery emergencies encompass a spectrum of etiologies, including renal artery stenosis, arteriovenous malformations, aneurysms and pseudoaneurysms, dissections, thrombosis, and vasculitis. Prompt and accurate diagnosis in the emergency setting is crucial due to the potential for significant morbidity and mortality. Computed tomography (CT) and CT angiography (CTA) are the mainstay imaging modalities, offering rapid acquisition and high diagnostic accuracy. The integration of 3D postprocessing techniques, such as 3D cinematic rendering (CR), improves the diagnostic workflow by providing photorealistic and anatomically accurate visualizations. This pictorial essay illustrates the diagnostic utility of CT and CTA, supplemented by 3D CR, through a series of 10 cases of non-traumatic renal artery emergencies. The added value of 3D CR in improving diagnostic confidence, surgical planning, and understanding of complex vascular anatomy is emphasized.”
Flank pain, hypertension, and hematuria: CT and 3D cinematic rendering in the evaluation of renal artery emergencies-a pictorial essay.
Yasrab M, Fishman EK, Chu LC.
Emerg Radiol. 2024 Aug 24. doi: 10.1007/s10140-024-02279-1. Epub ahead of print. - “Irrespective of the specific etiology, computed tomography (CT) based imaging has become the mainstay diagnostic modality of choice when evaluating suspected renal vessel disease or injury owing to its rapid acquisition, low cost, and high diagnostic accuracy for vascular processes and pathologies. Initial assessment via contrast-enhanced ultrasonography(US) and color doppler US may be performed to reveal flow anomalies, but barring unstable patients requiring immediate intervention or resuscitation, CT and CT angiography (CTA) studies are obtained for a thorough assessment of the vasculature and associated structures. With the advent of 3D postprocessing, including the novel 3D cinematic rendering (CR) technique that improves upon traditional volumetric rendering (VR) by employing a global illumination model, life-like and anatomically accurate reconstructions of the volumetric dataset can be rapidly acquired.”
Flank pain, hypertension, and hematuria: CT and 3D cinematic rendering in the evaluation of renal artery emergencies-a pictorial essay.
Yasrab M, Fishman EK, Chu LC.
Emerg Radiol. 2024 Aug 24. doi: 10.1007/s10140-024-02279-1. Epub ahead of print. - “Renal AVMs are abnormal communications between the arteries and veins, which may be a result of a simple, direct fistula or a complex network of tortuous vessels forming a nidus. Acquired AVMs are more common than congenital, and although they are a rare entity (prevalence < 0.04%) that can remain asymptomatic, they most commonly present with hematuria that may be associated with flank pain or hypertension in the acute setting. Life-threatening hemorrhage triggered by rupture of anomalous vessels or high-output failure in larger shunts are possible complications Hyperenhancing foci seen on arterial phase with early venous return, tortuous vessels, and enlarged feeding arteries should raise concern for an AVM. 3D CR effectively captures the complex vascular anatomy with a more intuitive perspective that helps guide interventional management.”
Flank pain, hypertension, and hematuria: CT and 3D cinematic rendering in the evaluation of renal artery emergencies-a pictorial essay.
Yasrab M, Fishman EK, Chu LC.
Emerg Radiol. 2024 Aug 24. doi: 10.1007/s10140-024-02279-1. Epub ahead of print. - “FMD is an idiopathic, noninflammatory medium-vessel vascular pathology underpinned by focal fibroplasia, which most commonly affects the renal and then carotid arteries. It is predominantly seen in females. CTA has been shown to have nearly 100% sensitivity and over 90% specificity for detecting RAS, and while atherosclerotic RAS is unilateral with stenosis towards the origin or bifurcation of the artery in most patients, bilateral and multifocal involvement is often seen in FMD, especially in acutely symptomatic patients. The classic description of FMD is the ‘string of beads’ appearance on imaging due to alternating regions of focal dilatations and stenoses. The diseased vessel walls also predispose themselves to other sequelae of FMD such as dissections, aneurysms, and thrombosis as seen in our cases.”
Flank pain, hypertension, and hematuria: CT and 3D cinematic rendering in the evaluation of renal artery emergencies-a pictorial essay.
Yasrab M, Fishman EK, Chu LC.
Emerg Radiol. 2024 Aug 24. doi: 10.1007/s10140-024-02279-1. Epub ahead of print. - Acute occlusion of the renal artery or its branches requires prompt diagnosis and treatment to prevent severe loss of renal function. In-situ renal artery thrombosis and thromboembolic phenomena (originating from the heart or aorta) are major causes, with increased risk in the context of comorbid conditions that predispose to hypercoagulability. Pathologic vascular processes like dissections and aneurysms can also be complicated by thrombosis . Most symptomatic patients present with acute abdominal or flank pain that may be associated with hypertension, nausea, hematuria, or overt renal failure in severe cases .
Flank pain, hypertension, and hematuria: CT and 3D cinematic rendering in the evaluation of renal artery emergencies-a pictorial essay.
Yasrab M, Fishman EK, Chu LC.
Emerg Radiol. 2024 Aug 24. doi: 10.1007/s10140-024-02279-1. Epub ahead of print. - “Unlike small-vessel vasculitides (ANCA-associated vasculitides) where kidney pathology primarily manifests as glomerulonephritis, direct renal artery disease can be seen in medium- and large-vessel vasculitides. Vasculitides often have bilateral involvement and are the most common vascular cause of spontaneous renal hemorrhage (excluding neoplasms), particularly polyarteritis nodosa (PAN). PAN is a necrotizing medium-vessel vasculitis, a prominent feature of which is involvement of the renal arteries and branches in up to 90% of patients. It is associated with hepatitis B and is more common in men.”
Flank pain, hypertension, and hematuria: CT and 3D cinematic rendering in the evaluation of renal artery emergencies-a pictorial essay.
Yasrab M, Fishman EK, Chu LC.
Emerg Radiol. 2024 Aug 24. doi: 10.1007/s10140-024-02279-1. Epub ahead of print. - “Characteristic CTA findings include multiple, bilateral microaneurysms and hypoenhancing regions of infarction due to occluded vessels. 3D CR is particularly helpful in careful evaluation of the microaneurysms and differentiation from calculi as they are often internally calcified by visualizing the arterial map. Largevessel vasculitis such as Takayasu arteritis may also involve the renal arteries and result in renovascular hypertension, with CT findings showing mural thickening and involvement of major vessels confirming diagnosis.”
Flank pain, hypertension, and hematuria: CT and 3D cinematic rendering in the evaluation of renal artery emergencies-a pictorial essay.
Yasrab M, Fishman EK, Chu LC.
Emerg Radiol. 2024 Aug 24. doi: 10.1007/s10140-024-02279-1. Epub ahead of print.