Abstract
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.
Abstract (translated)
将临床诊断推理与人工智能相结合仍然是医学影像领域的一个核心挑战。我们引入了MedCLM，这是一个自动管道系统，它通过将病变框链接到器官分割和结构化理由来将检测数据集转换为具有链式思维（CoT）推理的大规模医疗视觉问答（VQA）数据。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的问答对。 为了有效利用此类数据，我们提出了一种集成CoT-课程策略，包括一个使用明确病变框进行视觉定位的简单阶段、一个鼓励隐式定位的中等难度阶段以及一个用于弱监督推理的困难阶段。实验结果表明，MedCLM在多个医疗VQA基准测试上达到了最先进的性能水平，并提供了一个可扩展的框架来开发与临床实践相一致的医学视觉语言模型。
URL
https://arxiv.org/abs/2510.04477
