用规则验证的多模态模型提升阿尔茨海默病诊断透明度
AD-Reasoning: Multimodal Guideline-Guided Reasoning for Alzheimer's Disease Diagnosis
- 融合脑影像与六类临床数据，用规则校验推理过程
- 在1万+病例数据集上诊断准确率达当前最优
- 输出结构化理由，适合临床医生和研究者使用
阿尔茨海默病（AD）诊断需整合神经影像与异构临床证据，并遵循既定指南进行推理，但现有多模态模型普遍缺乏可解释性且对指南遵循度弱。我们提出AD-Reasoning，一种将结构化MRI与六类临床模态结合、并引入基于规则的验证器的多模态框架，生成符合美国国家老龄化研究所-阿尔茨海默病协会（NIA-AA）标准的结构化诊断。该框架采用模态专用编码器、双向交叉注意力融合机制，并通过可验证奖励进行强化微调，以确保输出格式规范、指南依据覆盖完整及推理-决策一致性。我们还发布了AD-MultiSense数据集，包含10,378次就诊记录，其问答对与推理理由均经指南验证，源自ADNI/AIBL数据库。在该数据集上，AD-Reasoning达到最先进的诊断准确率，并生成比现有基线更透明的结构化推理过程。
原文摘要 · Abstract (English)
Alzheimer's disease (AD) diagnosis requires integrating neuroimaging with heterogeneous clinical evidence and reasoning under established criteria, yet most multimodal models remain opaque and weakly guideline-aligned. We present AD-Reasoning, a multimodal framework that couples structural MRI with six clinical modalities and a rule-based verifier to generate structured, NIA-AA-consistent diagnoses. AD-Reasoning combines modality-specific encoders, bidirectional cross-attention fusion, and reinforcement fine-tuning with verifiable rewards that enforce output format, guideline evidence coverage, and reasoning--decision consistency. We also release AD-MultiSense, a 10,378-visit multimodal QA dataset with guideline-validated rationales built from ADNI/AIBL. On AD-MultiSense, AD-Reasoning achieves state-of-the-art diagnostic accuracy and produces structured rationales that improve transparency over recent baselines, while providing transparent rationales.
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。