ChestX-Reasoner：通过逐步验证推进具备推理能力的放射学基础模型
ChestX-Reasoner: Advancing Radiology Foundation Models with Reasoning through Step-by-Step Verification
AI总结：
本研究提出放射诊断多模态大模型ChestX-Reasoner，基于临床报告构建推理链数据集，采用两阶段训练框架对齐临床推理标准，配套推出基准与评估指标，在诊断准确率和推理能力上均优于现有模型，且资源全开源。
摘要：
推理增强型大语言模型（LLM）与多模态大语言模型（MLLM）的最新进展已显著提升了复杂任务的性能，但医学AI模型往往忽视了临床实践中固有的结构化推理过程。本研究提出ChestX-Reasoner，这是一款放射诊断多模态大语言模型，旨在利用直接从临床报告中挖掘的过程监督，复刻放射科医生遵循的逐步推理逻辑。我们通过从常规放射学报告中提取并优化推理链，构建了一个大规模数据集。我们的两阶段训练框架结合了监督微调与过程奖励引导的强化学习，使模型推理更贴合临床标准。我们推出了RadRBench-CXR这一综合性基准，包含5.9万个视觉问答样本及30.1万条经临床验证的推理步骤，并提出了RadRScore指标，用于评估推理的事实性、完整性与有效性。ChestX-Reasoner在诊断准确率与推理能力上均优于现有医学领域及通用领域的多模态大语言模型：与最优医学MLLM、最优通用MLLM及自身基座模型相比，其推理能力分别提升16%、5.9%和18%，结果准确率分别提升3.3%、24%和27%。所有资源均已开源，以推动医学推理多模态大语言模型的后续研究。
英文摘要：
Recent advances in reasoning-enhanced large language models (LLMs) and multimodal LLMs (MLLMs) have significantly improved performance in complex tasks, yet medical AI models often overlook the structured reasoning processes inherent in clinical practice. In this work, we present ChestX-Reasoner, a radiology diagnosis MLLM designed to leverage process supervision mined directly from clinical reports, reflecting the step-by-step reasoning followed by radiologists. We construct a large dataset by extracting and refining reasoning chains from routine radiology reports. Our two-stage training framework combines supervised fine-tuning and reinforcement learning guided by process rewards to better align model reasoning with clinical standards. We introduce RadRBench-CXR, a comprehensive benchmark featuring 59K visual question answering samples with 301K clinically validated reasoning steps, and propose RadRScore, a metric evaluating reasoning factuality, completeness, and effectiveness. ChestX-Reasoner outperforms existing medical and general-domain MLLMs in both diagnostic accuracy and reasoning ability, achieving 16%, 5.9%, and 18% improvements in reasoning ability compared to the best medical MLLM, the best general MLLM, and its base model, respectively, as well as 3.3%, 24%, and 27% improvements in outcome accuracy. All resources are open-sourced to facilitate further research in medical reasoning MLLMs.
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。
