构建医学视觉问答数据集，让AI像医生一样逐步推理诊断。
MedCLM: Learning to Localize and Reason via a CoT-Curriculum in Medical Vision-Language Models
- 用病变框与器官分割链接生成带思维链的问答数据。
- 在多个医疗VQA基准上达到顶尖水平，提升诊断可解释性。
- 适合研究医疗AI推理、临床辅助诊断的团队使用。
将临床诊断推理与人工智能结合仍是医学影像领域的核心挑战。我们提出MedCLM，一个自动化流程，通过将检测数据集转化为大规模医学视觉问答（VQA）数据，结合链式思维（Chain-of-Thought, CoT）推理，将病变框与器官分割及结构化理由相连接。这些上下文信号使医学视觉语言模型能够生成带有逐步推理过程的问题-答案对。为有效利用该数据，我们设计了集成式CoT-课程策略：易阶段使用显式病变框进行视觉定位；中阶段鼓励隐式定位；难阶段实现弱监督推理。实验表明，MedCLM在多个医学VQA基准上取得领先性能，为开发贴近临床需求的医学视觉语言模型提供可扩展框架。
原文摘要 · Abstract (English)
Bridging clinical diagnostic reasoning with AI remains a central challenge in medical imaging. We introduce MedCLM, an automated pipeline that converts detection datasets into large-scale medical visual question answering (VQA) data with Chain-of-Thought (CoT) reasoning by linking lesion boxes to organ segmentation and structured rationales. These contextual signals enable medical vision-language models to generate question-answer pairs with step-by-step reasoning. To utilize this data effectively, we propose an Integrated CoT-Curriculum Strategy composed of an Easy stage with explicit lesion boxes for visual grounding, a Medium stage that encourages implicit localization, and a Hard stage for weakly supervised reasoning. Experimental results demonstrate that MedCLM attains state-of-the-art performance on several medical VQA benchmarks, providing a scalable framework for developing clinically aligned medical vision-language models.
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。