Search

Purpose: The purpose of the 2023 SFR data challenge was to invite researchers to develop artificial intelligence (AI) models to identify the presence of a pancreatic mass and distinguish between benign and malignant pancreatic masses on abdominal computed tomography (CT) examinations., Materials and Methods: Anonymized abdominal CT examinations acquired during the portal venous phase were collected from 18 French centers. Abdominal CT examinations were divided into three groups including CT examinations with no lesion, CT examinations with benign pancreatic mass, or CT examinations with malignant pancreatic mass. Each team included at least one radiologist, one data scientist, and one engineer. Pancreatic lesions were annotated by expert radiologists. CT examinations were distributed in balanced batches via a Health Data Hosting certified platform. Data were distributed into four batches, two for training, one for internal evaluation, and one for the external evaluation. Training used 83 % of the data from 14 centers and external evaluation used data from the other four centers. The metric (i.e., final score) used to rank the participants was a weighted average of mean sensitivity, mean precision and mean area under the curve., Results: A total of 1037 abdominal CT examinations were divided into two training sets (including 500 and 232 CT examinations), an internal evaluation set (including 139 CT examinations), and an external evaluation set (including 166 CT examinations). The training sets were distributed on September 7 and October 13, 2023, and evaluation sets on October 15, 2023. Ten teams with a total of 93 members participated to the data challenge, with the best final score being 0.72., Conclusion: This SFR 2023 data challenge based on multicenter CT data suggests that the use of AI for pancreatic lesions detection is possible on real data, but the distinction between benign and malignant pancreatic lesions remains challenging., Competing Interests: Declaration of competing interest The authors declare that they have no competing interest in relation with this article., (Copyright © 2024 Société française de radiologie. Published by Elsevier Masson SAS. All rights reserved.)

Background and Aims: Changes in body composition have been described in patients with Crohn's disease, but their predictive performances on disease evolution remain undefined. The aims of our study were to assess, in patients with Crohn's disease requiring abdominal computed tomography, body composition by computed tomography, and to study the outcome according to various body composition parameters at the time of the computed tomography., Methods: Patients with Crohn's disease who underwent abdominal computed tomography for suspected complications were retrospectively included. The definition of adverse outcome included death or need for surgery within 6 months of the computed tomography. Skeletal muscle index and visceral and subcutaneous adiposity indexes were calculated from tissue surface areas measured at the third lumbar vertebra, divided by the height squared., Results: The prevalence of underweight was 26.8% and the prevalence of sarcopenia was 33.6%. After gender adjustment, skeletal muscle index tended to be reduced in patients with adverse outcome, compared with patients without surgery or death [p = 0.07]. Moreover, subcutaneous adiposity index and visceral adiposity index were significantly lower in patients with surgery or death [p = 0.009 and p < 0.001, respectively]. These differences were almost equivalent in both genders for the subcutaneous adiposity index but were clearly stronger in men for the visceral adiposity index., Conclusions: Subcutaneous and visceral adiposity indexes correlate inversely with adverse outcome in patients with Crohn's disease. Alteration of body composition assessed by computed tomography in these patients appears to be a marker of disease severity.

Purpose: Sleeve gastrectomy is a new bariatric surgical procedure with promising early results and low morbidity and mortality. We have evaluated the early imaging findings and value of upper GI study (UGI) and CT., Patients and Methods: Twenty five patients (mean age=38.9 years, mean BMI=51.5 kg/m2) following sleeve gastrectomy for morbid obesity underwent UGI at day 1. CT was immediately performed in patients with suspected leak or as a follow-up examinations in patients with suspected complication. The different imaging features observed were recorded., Results: UGI demonstrated 13 normal examinations (52%), an abnormal appearance in 11 cases (44%) with opacification of a lateral pouch, and one complication (leak confirmed on CT). Two patients underweent CT (day 3 and day 15) for suspected complication, with demonstration of leak in both cases., Conclusion: An abnormal appearance after sleeve gastrectomy is frequently observed on UGI. Routine UGI at day 1 is useful to detect large leaks. CT with oral contrast should be performed in all patients with imaging or clinical suspicion of leak.

We report the case of a 77-year-old woman presenting with a jejunal intussusception as the primary symtom of metastatic renal cell carcinoma. Both lesions were demonstrated by abdominal CT which detected also pancreatic metastasis. This case emphasizes the significance of CT to diagnose intussusception and to characterize its cause.

Introduction: Renal infarction is a rare and often difficult diagnosis. The objective of this study was to demonstrate that contrast-enhanced spiral CT in patients presenting features of renal colic, can establish the diagnosis by confirming the presence of infarction of the renal parenchyma., Material and Methods: Over a 10-month period, the authors proposed the following decision flow-chart for all patients admitted with clinical features of renal colic: plain abdominal x-ray and first-line renal ultrasound, which, in the absence of a diagnosis (stones or dilatation of cavities), were completed by unenhanced spiral CT scan. When these examinations were normal, contrast-enhanced spiral CT scan was then performed., Results: 300 patients were included in this study, and CT was performed in 40 cases. This management allowed the diagnosis of infarction of the renal parenchyma in three patients, who are described here. When unenhanced CT sections do not reveal any abnormality, contrast-enhanced sections are essential to visualize the infarcted zone, seen as a triangular low density lesion with clearly defined margins and a vascular topography., Conclusion: Contrast-enhanced spiral CT should now be considered to be the reference examination for the assessment of non-documented renal colic. This recent imaging modality should allow the diagnosis of a greater number of infarctions of the renal parenchyma, which formerly remained undiagnosed.