SurgCoT：通过链式推理基准提升手术视频中的时空推理
SurgCoT: Advancing Spatiotemporal Reasoning in Surgical Videos through a Chain-of-Thought Benchmark
AI总结：
SurgCoT通过统一的链式推理框架评估多模态大语言模型在7个外科领域35种手术中的时空推理能力，揭示了商业模型在手术推理中的优势及现有模型的不足。
摘要：
在手术视频上进行细粒度时空推理至关重要，但多模态大语言模型（MLLMs）在此领域的能力仍待探索。为此，我们引入SurgCoT，一个统一的基准，用于评估MLLMs在7个外科专科和35种多样化手术中的链式推理（CoT）能力。SurgCoT通过结构化的CoT框架和密集标注协议（问题-选项-知识-线索-答案）评估五个核心推理维度：因果动作顺序、线索-动作对齐、可达性映射、微过渡定位和异常起始跟踪，其中知识字段提供必要的背景上下文，线索字段提供确定的时空证据。对10个领先MLLMs的评估显示：1）商业模型优于开源和医学专用变体；2）手术CoT推理存在显著差距；3）SurgCoT实现了有效的评估并增强了逐步时空推理。SurgCoT提供了一个可重复的测试平台，以缩小MLLM能力与临床推理需求之间的差距。代码：https://github.com/CVI-SZU/SurgCoT。
英文摘要：
Fine-grained spatiotemporal reasoning on surgical videos is critical, yet the capabilities of Multi-modal Large Language Models (MLLMs) in this domain remain largely unexplored. To bridge this gap, we introduce SurgCoT, a unified benchmark for evaluating chain-of-thought (CoT) reasoning in MLLMs across 7 surgical specialties and 35 diverse procedures. SurgCoT assesses five core reasoning dimensions: Causal Action Ordering, Cue-Action Alignment, Affordance Mapping, Micro-Transition Localization, and Anomaly Onset Tracking, through a structured CoT framework with an intensive annotation protocol (Question-Option-Knowledge-Clue-Answer), where the Knowledge field provides essential background context and Clue provides definitive spatiotemporal evidence. Evaluation of 10 leading MLLMs shows: 1) commercial models outperform open-source and medical-specialized variants; 2) significant gaps exist in surgical CoT reasoning; 3) SurgCoT enables effective evaluation and enhances progressive spatiotemporal reasoning. SurgCoT provides a reproducible testbed to narrow the gap between MLLM capabilities and clinical reasoning demands. Code: https://github.com/CVI-SZU/SurgCoT.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
