Surgical safety improved by interpretable anatomy reasoning system
Structured Reasoning Agentic Framework for Interpretable Critical View of Safety Assessment
Computer Vision and Pattern Recognition
Summary
Surgical safety during gallbladder removal is hard because doctors need to understand complex anatomy to avoid injuries. The authors created ReasonCVS, a system that breaks down this task into checking specific anatomical parts and their relationships, making the decisions easier to understand. It uses advanced visual and language AI models to carefully assess the surgical area and explain its conclusions. This approach improves accuracy and helps surgeons better trust computer assistance during operations.
What this means in practice
- •For surgical device developers: Integrate interpretable anatomy verification to improve safety features in laparoscopic surgery support systems.
- •For medical imaging software teams: Enhance surgical scene analysis tools by adding explicit reasoning about anatomical relationships for clearer clinical explanations.
Authors
Qing Xu, Yuxiang Luo, Zhen Chen
Abstract
Surgical scene understanding is critical for computer-assisted intervention, yet laparoscopic cholecystectomy remains challenged by the complex anatomy of the hepatocystic triangle and the risk of bile duct injury. Existing methods for Critical View of Safety (CVS) assessment typically treat it as a holistic prediction task, mapping visual features directly to criterion-level labels. This black-box paradigm lacks explicit reasoning about anatomical relationships, limiting both interpretability and compositional generalization. To address this, we propose ReasonCVS, a structured reasoning agentic framework empowered by Vision-Language Models (VLMs) that decomposes CVS assessment into explicit, fine-grained anatomical verification. Specifically, we devise an Anatomical Scene Graph Abstraction (ASGA) that organizes anatomical entities and their spatial relationships into a structured representation. To operationalize this, we introduce a Rationale-Aware Reasoning Agent, powered by a Large Language Model (LLM) fine-tuned via rationale distillation. Functioning as a strict central decision-maker, it invokes VLM-driven Sub-criterion Verifier as a specialized perceptual tool to parse the graph and independently evaluate individual sub-criteria. Through calibrated soft reasoning, this agent synthesizes the tool-gathered distributed observations, yielding a final verdict alongside a traceable clinical rationale. Extensive experiments on the Endoscapes-CVS201 benchmark demonstrate that ReasonCVS achieves superior performance (68.1\% mAP) over state-of-the-art while providing interpretable, criterion-level explanations for reliable surgical assessment.