提出新模型SurGo-R1，让AI理解手术阶段并准确定位安全操作区。
SurGo-R1: Benchmarking and Modeling Contextual Reasoning for Operative Zone in Surgical Video
- 分两步推理：先判断手术阶段，再基于阶段生成安全区坐标
- 在未见手术中达到76.6%阶段准确率、32.7 mIoU、54.8%硬性准确率
- 专为手术场景设计，适合外科AI辅助系统开发者使用
微创手术显著改善患者预后，但关键阶段的安全操作区识别仍具挑战，需医生在高认知负荷下融合视觉线索、手术阶段与解剖背景。现有AI系统仅提供二值化安全验证或静态检测，忽视术中推理的阶段依赖性。我们构建了ResGo基准，包含腹腔镜图像帧的“可操作区”边界框及临床医生撰写的推理说明，涵盖阶段、暴露质量、下一步操作与风险提示。引入新评估指标，将错误阶段下的正确定位视为失败，揭示多数视觉语言模型在此任务上表现不佳。随后提出SurGo-R1，通过强化学习人类反馈（RLHF）优化，采用多轮“阶段-然后-操作区”架构：模型先识别手术阶段，再生成推理并输出对应坐标。在未见过的手术中，SurGo-R1实现76.6%阶段准确率、32.7 mIoU和54.8%硬性准确率，较主流通用视觉语言模型提升6.6倍。代码、模型与基准数据将公开于https://github.com/jinlab-imvr/SurGo-R1。
原文摘要 · Abstract (English)
Minimally invasive surgery has dramatically improved patient operative outcomes, yet identifying safe operative zones remains challenging in critical phases, requiring surgeons to integrate visual cues, procedural phase, and anatomical context under high cognitive load. Existing AI systems offer binary safety verification or static detection, ignoring the phase-dependent nature of intraoperative reasoning. We introduce ResGo, a benchmark of laparoscopic frames annotated with Go Zone bounding boxes and clinician-authored rationales covering phase, exposure quality reasoning, next action and risk reminder. We introduce evaluation metrics that treat correct grounding under incorrect phase as failures, revealing that most vision-language models cannot handle such tasks and perform poorly. We then present SurGo-R1, a model optimized via RLHF with a multi-turn phase-then-go architecture where the model first identifies the surgical phase, then generates reasoning and Go Zone coordinates conditioned on that context. On unseen procedures, SurGo-R1 achieves 76.6% phase accuracy, 32.7 mIoU, and 54.8% hardcore accuracy, a 6.6$\times$ improvement over the mainstream generalist VLMs. Code, model and benchmark will be available at https://github.com/jinlab-imvr/SurGo-R1
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。