EMAD: 基于证据的多模态诊断框架用于阿尔茨海默病
EMAD: Evidence-Centric Grounded Multimodal Diagnosis for Alzheimer's Disease
AI总结：
EMAD通过多模态证据接地机制，生成结构化诊断报告，提升阿尔茨海默病诊断的透明度和临床一致性。
摘要：
深度学习模型在医学影像分析中通常作为黑箱，很少与临床指南一致或明确将决策与支持证据联系起来。这在阿尔茨海默病（AD）中尤其关键，因为预测应基于解剖和临床发现。我们提出了EMAD，一种视觉-语言框架，能够生成结构化的AD诊断报告，其中每个声明都明确基于多模态证据。EMAD采用分层的句子-证据-解剖（SEA）接地机制：（i）句子到证据接地将生成的句子与临床证据短语联系起来，（ii）证据到解剖接地在3D脑MRI上局部化相应的结构。为了减少密集标注需求，我们提出GTX-Distill，它将接地行为从一个在有限监督下训练的教师模型转移到一个在模型生成报告上操作的学生模型。我们进一步引入可执行规则GRPO，一种带有可验证奖励的强化微调方案，强制临床一致性、协议遵守和推理诊断一致性。在AD-MultiSense数据集上，EMAD实现了最先进的诊断准确度，并生成比现有方法更透明、解剖上更忠实的报告。我们将发布代码和接地标注以支持未来在可信医学视觉-语言模型中的研究。
英文摘要：
Deep learning models for medical image analysis often act as black boxes, seldom aligning with clinical guidelines or explicitly linking decisions to supporting evidence. This is especially critical in Alzheimer's disease (AD), where predictions should be grounded in both anatomical and clinical findings. We present EMAD, a vision-language framework that generates structured AD diagnostic reports in which each claim is explicitly grounded in multimodal evidence. EMAD uses a hierarchical Sentence-Evidence-Anatomy (SEA) grounding mechanism: (i) sentence-to-evidence grounding links generated sentences to clinical evidence phrases, and (ii) evidence-to-anatomy grounding localizes corresponding structures on 3D brain MRI. To reduce dense annotation requirements, we propose GTX-Distill, which transfers grounding behavior from a teacher trained with limited supervision to a student operating on model-generated reports. We further introduce Executable-Rule GRPO, a reinforcement fine-tuning scheme with verifiable rewards that enforces clinical consistency, protocol adherence, and reasoning-diagnosis coherence. On the AD-MultiSense dataset, EMAD achieves state-of-the-art diagnostic accuracy and produces more transparent, anatomically faithful reports than existing methods. We will release code and grounding annotations to support future research in trustworthy medical vision-language models.
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。
