3D Venous Anatomy Analysis for Pancreatic Surgery Using Large Vision-Language Model

The portal-mesenteric venous system surrounding the pancreas exhibits significant anatomical complexity and variability. Precise segmentation and assessment of these venous structures are crucial for preoperative planning in pancreatic surgery to reduce the risk of intraoperative hemorrhage and postoperative complications. To address this, we present the Venous Anatomy Analyzer for Pancreatic Surgery (VA²PS), a novel framework that integrates 3D vein segmentation and Large Vision-Language Model (VLM), to provide surgeons with intuitive visualization and accurate analysis of the portalmesenteric venous system and pancreas. VA²PS first performs precise 3D segmentation of the venous system and pancreas from CT scans. Subsequently, it bridges the dimensional gap between segmentation result and VLM input by rendering these 3D structures into optimized 2D views. Finally, conditioned on the visual input and surgical instructions, VA² PS utilizes a VLM reasoning over a built-in repository of clinical knowledge to identify venous anatomical subtypes and generates surgical planning recommendations. Objective and subjective evaluations demonstrate that VA² PS provides accurate and efficient preoperative assessments for surgeons, holding the potential to improve surgical outcomes. Code and data are available at https://github.com/zengyue1376/VA2PS.