Automatic Detection of Pancreatic Lesions and Main Pancreatic Duct Dilatation on Portal Venous CT Scans Using Deep Learning.

OBJECTIVES: This study proposes and evaluates a deep learning method to detect pancreatic neoplasms and to identify main pancreatic duct (MPD) dilatation on portal venous computed tomography scans. MATERIALS AND METHODS: A total of 2890 portal venous computed tomography scans from 9 institutions were acquired, among which 2185 had a pancreatic neoplasm and 705 were healthy controls. Each scan was reviewed by one in a group of 9 radiologists. Physicians contoured the pancreas, pancreatic lesions if present, and the MPD if visible. They also assessed tumor type and MPD dilatation. Data were split into a training and independent testing set of 2134 and 756 cases, respectively.A method to detect pancreatic lesions and MPD dilatation was built in 3 steps. First, a segmentation network was trained in a 5-fold cross-validation manner. Second, outputs of this network were postprocessed to extract imaging features: a normalized lesion risk, the predicted lesion diameter, and the MPD diameter in the head, body, and tail of the pancreas. Third, 2 logistic regression models were calibrated to predict lesion presence and MPD dilatation, respectively. Performance was assessed on the independent test cohort using receiver operating characteristic analysis. The method was also evaluated on subgroups defined based on lesion types and characteristics. RESULTS: The area under the curve of the model detecting lesion presence in a patient was 0.98 (95% confidence interval [CI], 0.97-0.99). A sensitivity of 0.94 (469 of 493; 95% CI, 0.92-0.97) was reported. Similar values were obtained in patients with small (less than 2 cm) and isodense lesions with a sensitivity of 0.94 (115 of 123; 95% CI, 0.87-0.98) and 0.95 (53 of 56, 95% CI, 0.87-1.0), respectively. The model sensitivity was also comparable across lesion types with values of 0.94 (95% CI, 0.91-0.97), 1.0 (95% CI, 0.98-1.0), 0.96 (95% CI, 0.97-1.0) for pancreatic ductal adenocarcinoma, neuroendocrine tumor, and intraductal papillary neoplasm, respectively. Regarding MPD dilatation detection, the model had an area under the curve of 0.97 (95% CI, 0.96-0.98). CONCLUSIONS: The proposed approach showed high quantitative performance to identify patients with pancreatic neoplasms and to detect MPD dilatation on an independent test cohort. Performance was robust across subgroups of patients with different lesion characteristics and types. Results confirmed the interest to combine a direct lesion detection approach with secondary features such as the MPD diameter, thus indicating a promising avenue for the detection of pancreatic cancer at early stages.

Patients with inflammatory bowel disease have higher abdominal adiposity and less skeletal mass than healthy controls.

BACKGROUND: Abdominal fat type and distribution have been associated with complicated Crohn's disease and adverse postoperative outcomes. Few studies have assessed the abdominal distribution of fat and lean stores in patients with inflammatory bowel disease (IBD) and compared this with healthy controls. This retrospective study aimed to compare the abdominal body composition in IBD patients who failed medical treatment and who underwent computed tomography (CT) imaging prior to gastrointestinal surgery with healthy controls. Associations between preoperative abdominal body composition and postoperative outcomes within a year of surgery were explored. METHODS: Abdominal body composition was evaluated in 22 presurgical patients with medically refractory IBD (18 with Crohn's disease) and 22 healthy controls, using routinely acquired CT. Total fat, subcutaneous fat, visceral fat, and skeletal muscle cross-sectional area were measured. RESULTS: An independent disease effect was observed, explaining a fat deposition excess of 38 cm2 and a skeletal muscle deficit of 15 cm2 in IBD. Abdominal skeletal muscle correlated with visceral fat for the control (rho=0.51, P=0.015), but not for the IBD group (rho=-0.13, P=0.553). A positive correlation observed between subcutaneous fat with skeletal muscle in the controls (rho=0.47, P=0.026) was inverted in the IBD group (rho=-0.43, P=0.045). Preoperative abdominal body composition was not predictive of postoperative outcomes. CONCLUSIONS: A higher degree of abdominal adiposity, a lower skeletal mass and a larger body size for the same anthropometry can be expected in IBD patients. Preoperative abdominal body composition is not associated with surgical outcomes.