Automated Prediction of Postoperative Pancreatic Fistula Using Preoperative Computed Tomography
This tool offers improved preoperative decision-making for surgeons performing pancreatic resections, potentially reducing patient morbidity and healthcare costs.
This paper developed an automated deep learning pipeline for predicting postoperative pancreatic fistula (POPF) using preoperative CT scans. The pipeline, from pancreatic segmentation to classification, was evaluated using various 3D CNN architectures, demonstrating promising predictive performance for POPF risk estimation.
Postoperative pancreatic fistula (POPF) is a serious complication after pancreatic resection, increasing morbidity, hospital stay, and healthcare costs. We present an automatic, end-to-end deep learning pipeline-from pancreatic segmentation to classification-for preoperative POPF risk estimation and stratification using preoperative CT scans. A data set with auto-segmented pancreas volumes and surgical outcomes was used to evaluate multiple architectures, including a custom lightweight 3D CNN baseline (CNN3D), R(2+1)D ResNet-18, and ResNet-MC3-18 models. Evaluation across multiple 3D architectures demonstrated promising predictive performance. This approach offers a clinically valuable tool and a methodological benchmark for pancreas-specific CT classification, supporting improved preoperative decision-making in pancreatic surgery.