Infection-Reasoner: 一种用于伤口感染分类的紧凑视觉-语言模型，结合证据支撑的临床推理
Infection-Reasoner: A Compact Vision-Language Model for Wound Infection Classification with Evidence-Grounded Clinical Reasoning
AI总结：
本文提出Infection-Reasoner，一种紧凑的视觉-语言模型，通过两阶段训练提升伤口感染分类和推理生成的准确性与解释性，实验结果显示其在分类和推理质量上优于现有方法。
摘要：
评估慢性伤口感染的图像存在挑战，因为视觉表现在不同伤口病因、解剖位置和成像条件下变化较大。先前基于图像的深度学习方法主要集中在分类上，但缺乏可解释性，尽管需要证据支撑的解释以支持临床决策。我们提出了Infection-Reasoner，一种具有4B参数的推理视觉-语言模型，用于慢性伤口感染分类和推理生成。为解决专家标注的伤口图像和推理注释稀缺的问题，Infection-Reasoner采用两阶段训练流程：（1）推理蒸馏，其中GPT-5.1为未标注的伤口图像生成推理过程以初始化特定伤口的推理；（2）在小规模标注感染数据集上使用群体相对策略优化进行强化学习训练以优化分类推理。在测试的异质伤口数据集上，Infection-Reasoner实现了86.8%的准确率、86.4%的灵敏度和87.1%的特异度，优于多个强大的基线方法，包括GPT-5.1。推理质量通过多模态大语言模型（MLLM）评委和伤口专家评审进一步评估。四个MLLM评委的视觉支持一致性分数在0.722到0.903之间，而专家评审将61.8%的推理评为正确，32.4%评为部分正确。
英文摘要：
Assessing chronic wound infection from photographs is challenging because visual appearance varies across wound etiologies, anatomical locations, and imaging conditions. Prior image-based deep learning methods have mainly focused on classification with limited interpretability, despite the need for evidence-grounded explanations to support point-of-care decision making. We present Infection-Reasoner, a compact 4B-parameter reasoning vision-language model for chronic wound infection classification and rationale generation. To address the scarcity of expert-labeled wound images with reasoning annotations, Infection-Reasoner is trained using a two-stage pipeline: (1) reasoning distillation, in which GPT-5.1 generates chain-of-thought rationales for unlabeled wound images to initialize wound-specific reasoning in a smaller student model (Qwen3-VL-4B-Thinking), and (2) reinforcement learning post-training with Group Relative Policy Optimization on a small labeled infection dataset to refine classification reasoning. On a held-out heterogeneous wound dataset, Infection-Reasoner achieved 86.8\% accuracy, 86.4\% sensitivity, and 87.1\% specificity, outperforming several strong baselines, including GPT-5.1. Rationale quality was further evaluated using both multimodal large language model (MLLM) judges and wound expert review. Across four MLLM judges, visual-support agreement scores ranged from 0.722 to 0.903, while expert review rated 61.8\% of rationales as Correct and 32.4\% as Partially Correct.
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。
