MEDLAYXPLAIN: 医学视觉语言模型中的专家-外行差距基准测试
MEDLAYXPLAIN: Benchmarking the Expert-Lay Gap in Medical Vision-Language Models
AI总结：
提出首个大规模医学外行语言生成基准MedLayXPlain，包含12万+区域级样本和三层UMLS本体，通过HOVER管道构建外行描述，并引入轻量级评估器MedLayEval，揭示当前医学VLM在外行可读性与临床精度间的系统性差距。
摘要：
医学视觉语言模型（Med-VLM）在专家级任务上表现优异，但其生成患者可理解描述的能力尚未得到充分探索。随着《21世纪治愈法案》要求患者立即获取诊断影像结果，评估Med-VLM能否弥合专家-外行差距对于患者教育和共享决策既紧迫又具有临床意义。为此，我们引入MedLayXPlain，这是首个面向医学外行语言生成（MLLG）的大规模多模态基准和评估框架。MedLayXPlain-122K提供了来自12个公开数据集的8种影像模态的122,789个区域级样本，每个样本包含医学图像及其配对的专家和外行描述，这些描述锚定在三级统一医学语言系统（UMLS）本体层次结构中，涵盖7个语义组、43个语义类型和2,411个医学概念。外行描述通过分层本体验证精炼（HOVER）构建，这是一个三步流程，结合以患者为中心的词汇映射、基于LLM的约束重写和跨模型视觉验证，以在防止幻觉的同时强制语义等价。我们进一步引入MedLayEval，这是一个从27B验证器蒸馏得到的轻量级3B评估器，跨五个临床基础属性对外行-专家对齐进行评分，解决了标准NLG指标与临床判断之间相关性差的问题。在MedLayXPlain-122K上对33个VLM进行基准测试揭示了系统性的专家-外行差距：医学VLM在专家描述上表现强劲，但外行注册能力显著下降，而通用VLM生成更易理解的语言但缺乏临床精度，证实当前两种范式均不足以满足面向患者的沟通需求。
英文摘要：
Medical Vision-Language Models (Med-VLMs) achieve strong expert-level performance, yet their ability to generate patient-accessible descriptions remains underexplored. With the 21st Century Cures Act now mandating immediate patient access to diagnostic imaging results, evaluating whether Med-VLMs can bridge this Expert-Lay Gap is both urgent and clinically consequential for patient education and shared decision-making. To this end, we introduce MedLayXPlain, the first large-scale multimodal benchmark and evaluation framework for Medical Lay Language Generation (MLLG). MedLayXPlain-122K provides 122,789 region-grounded samples across 8 imaging modalities from 12 publicly available source datasets, each comprising a medical image with paired expert and lay captions anchored in a three-level Unified Medical Language System (UMLS) ontology hierarchy spanning 7 semantic groups, 43 semantic types, and 2,411 medical concepts. Lay captions are constructed via Hierarchical Ontology-Verified Refinement (HOVER), a three-step pipeline combining patient-centric vocabulary mapping, LLM-based constrained rewriting, and cross-model visual verification to enforce semantic equivalence while preventing hallucination. We further introduce MedLayEval, a lightweight 3B evaluator distilled from a 27B verifier that scores expert-lay alignment across five clinically grounded attributes, addressing the poor correlation between standard NLG metrics and clinical judgment. Benchmarking 33 VLMs on MedLayXPlain-122K reveals a systematic Expert-Lay Gap: medical VLMs achieve strong expert captioning but suffer significant lay-register degradation, while general-purpose VLMs produce more accessible language yet lack clinical precision, confirming that neither current paradigm adequately serves patient-facing communication.
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。
