MedHorizon：迈向真实场景下的长上下文医学视频理解
MedHorizon: Towards Long-context Medical Video Understanding in the Wild
AI总结：
MedHorizon提出一个真实场景下的长上下文医学视频理解基准，通过稀疏证据和多跳临床推理评估，揭示当前系统在完整流程理解上的不足。
摘要：
医学多模态大语言模型（MLLMs）在图像理解和短视频分析方面有所进展，但实际临床审查往往需要完整流程视频理解。与一般长视频不同，医学程序包含高度冗余的解剖视图，而关键证据在时间上稀疏、空间上微妙且依赖上下文。现有基准通常假设证据已通过图像、短片段或预分割视频局部化，导致检索前推理问题未被充分测试。我们引入MedHorizon，一个真实场景下的长上下文医学视频理解基准。MedHorizon保存了759小时的完整临床流程视频，并提供1253个证据基础的多选问题，共同评估稀疏证据理解和多跳临床推理。其证据极其稀疏，平均仅0.166%的证据帧，要求模型在嘈杂的流程流中搜索后进行解释和聚合发现。我们评估了代表性的一般领域、医学领域和长视频MLLMs。最佳模型仅达到41.1%的准确率，表明当前系统仍远未达到稳健的完整流程理解。进一步分析得出四个关键发现：性能不随更多帧可靠增长，证据检索和临床解释仍是主要瓶颈；这些瓶颈根植于弱的流程推理和注意力漂移，以及通用采样方法只能部分平衡局部细节与全局覆盖。MedHorizon为能够检索稀疏证据并推理完整临床流程的MLLMs提供了严谨的测试平台。
英文摘要：
Medical multimodal large language models (MLLMs) have advanced image understanding and short-video analysis, but real clinical review often requires full-procedure video understanding. Unlike general long videos, medical procedures contain highly redundant anatomical views, while decisive evidence is temporally sparse, spatially subtle, and context dependent. Existing benchmarks often assume this evidence has already been localized through images, short clips, or pre-segmented videos, leaving the retrieval-before-reasoning problem under-tested. We introduce MedHorizon, an in-the-wild benchmark for long-context medical video understanding. MedHorizon preserves 759 hours of full-length clinical procedures and provides 1,253 evidence-grounded multiple-choice questionsthat jointly evaluate sparse evidence understanding and multi-hop clinical reasoning. Its evidence is extremely sparse, with only 0.166% evidence frames on average, requiring models to search noisy procedural streams before interpreting and aggregating findings. We evaluate representative general-domain, medical-domain, and long-video MLLMs. The best model reaches only 41.1% accuracy, showing that current systems remain far from robust full-procedure understanding. Further analysis yields four key findings: performance does not scale reliably with more frames, evidence retrieval and clinical interpretation remain primary bottlenecks; these bottlenecks are rooted in weak procedural reasoning and attention drift under redundancy, and generic sampling methods only partially balances local detail with global coverage. MedHorizon provides a rigorous testbed for MLLMs that retrieve sparse evidence and reason over complete clinical workflows.
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。
