AD-Reasoning: Multimodal Guideline-Guided Reasoning for Alzheimer's Disease Diagnosis

Qiuhui Chen; Yushan Deng; Xuancheng Yao; Yi Hong

cs.CVMar 25, 2026

AD-Reasoning: Multimodal Guideline-Guided Reasoning for Alzheimer's Disease Diagnosis

Authors: Qiuhui Chen, Yushan Deng, Xuancheng Yao, Yi Hong

Organizations: School of Information Science and Engineering, East China University of Science and Technology, Shanghai, China · School of Computer Science, Shanghai Jiao Tong University, Shanghai, China

Abstract

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.

Figures & tables

Fig. 1: AD-Reasoning framework. Pretraining aligns sMRI and clinical data representations via encoders, SFT tunes LLMs using diagnostic rationales and RFT optimizes with GRPO for NIA-AA compliant structured outputs.

Fig. 2: Our AD-MultiSense dataset Construction pipeline: disease-level reports are generated via evidence-augmented reasoning under clinical guidelines with self-refinement for diagnostic validity.

	Method	BLEU	METEOR	ROUGE	BERT	ACC (%)	AUC (%)	SEN (%)	SPE (%)
CN vs. CI	LLaVA-1.5-7B	0.0112	0.1456	0.1023	0.7924	73.85	68.92	60.14	80.37
	LLaVA-Med	0.0144	0.1618	0.1168	0.8016	76.21	71.43	62.75	83.42
	Med-PaLM-M	0.0218	0.2031	0.1331	0.8181	79.92	75.76	66.63	85.85
	M3d-LaMed	0.0341	0.1756	0.1435	0.8128	82.37	78.95	69.84	86.21
	AD-Reasoning w/o PT	0.1873	0.2792	0.2424	0.8636	87.25	83.12	71.28	91.37
	AD-Reasoning w/o RFT	0.2015	0.2982	0.2617	0.8725	90.46	87.63	80.75	94.28

TABLE I: Comparison of AD-Reasoning and baselines in terms of reasoning and diagnostic performance for Alzheimer’s disease.

Table 4

Fig. 3: Inference example of AD-reasoning.

Alzheimer's Disease Classification

Alzheimer’s disease classification uses clinical, behavioral, and brain-imaging data to distinguish disease stages and predict progression.

See all 92 papers

EMAD: Evidence-Centric Grounded Multimodal Diagnosis for Alzheimer's Disease
Feb 22, 2026Qiuhui Chen, Xuancheng Yao, Zhenglei Zhou +2Medical VLMs Explainable Medical Image Analysis
East China University of Science and Technology · Shanghai Jiao Tong University · Tencent
AD-CARE: A Guideline-grounded, Modality-agnostic LLM Agent for Real-world Alzheimer's Disease Diagnosis with Multi-cohort Assessment, Fairness Analysis, and Reader Study
Mar 26, 2026Wenlong Hou, Sheng Bi, Guangqian Yang +16Alzheimer's Disease Classification Clinical Decision Support
Department of Biomedical Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, China. · Department of Radiology and Nuclear Medicine, Xuanwu Hospital, Capital Medical University, Beijing, China. · Amazon, USA. +10
A Multimodal Explainable Deep Learning Framework for Alzheimer's Disease Diagnosis using 3D Magnetic Resonance Imaging and Clinical Data
Sep 11, 2026Yusuf Brima, Marcellin Atemkeng, Lakshmana Rao Namamula +13D Medical Imaging Multimodal Classification
Computer Vision, Institute of Cognitive Science, Osnabrück University, Germany. · Department of Mathematics, Rhodes University, South Africa. · National Institute for Theoretical and Computational Sciences (NITheCS), Stellenbosch, 7600, South Africa. +2

Feb 22, 2026J/K move · Enter open · S save

EMAD: Evidence-Centric Grounded Multimodal Diagnosis for Alzheimer's Disease

Qiuhui Chen, Xuancheng Yao, Zhenglei Zhou, Xinyue Hu+1

East China University of Science and Technology · Shanghai Jiao Tong University · Tencent

Medical VLMs Explainable Medical Image Analysis Medical Report Generation Medical Image Grounding Alzheimer's Disease Classification

Open paper AskPDF arXiv

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.

Abstract

Alzheimer's Disease Classification

Explore similar work

EMAD: Evidence-Centric Grounded Multimodal Diagnosis for Alzheimer's Disease

AD-CARE: A Guideline-grounded, Modality-agnostic LLM Agent for Real-world Alzheimer's Disease Diagnosis with Multi-cohort Assessment, Fairness Analysis, and Reader Study

A Multimodal Explainable Deep Learning Framework for Alzheimer's Disease Diagnosis using 3D Magnetic Resonance Imaging and Clinical Data