AD-Reasoning：多模态指南引导推理用于阿尔茨海默病诊断
AD-Reasoning: Multimodal Guideline-Guided Reasoning for Alzheimer's Disease Diagnosis
AI总结：
本文提出AD-Reasoning框架，结合结构MRI和六种临床模态，生成符合NIA-AA标准的诊断，通过强化学习提升透明度和指南一致性。
摘要：
阿尔茨海默病诊断需整合神经影像与异质临床证据，并在既定标准下进行推理，但大多数多模态模型仍不透明且指南对齐性差。本文提出AD-Reasoning框架，结合结构性MRI与六种临床模态及基于规则的验证器，生成结构化的、符合NIA-AA标准的诊断。AD-Reasoning结合模态特定编码器、双向交叉注意力融合和强化学习微调，使用可验证奖励以强制输出格式、指南证据覆盖度和推理-决策一致性。我们还发布了AD-MultiSense，一个包含10,378次访问的多模态问答数据集，其基于ADNI/AIBL构建的指南验证推理。在AD-MultiSense上，AD-Reasoning实现了最先进的诊断准确率，并生成结构化的推理，相较于近期基线提升了透明度。
英文摘要：
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.
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。
