MVMGNN;Multi-View Masked Graph Neural Network for Alzheimer's Disease Diagnosis using Structural MRI

2026-07-08

AI Summary

This study addresses the limitations of existing structural MRI–based brain network approaches, which typically rely on a single graph construction strategy and thus struggle to simultaneously model both spatial adjacency and morphological similarity among brain regions, hindering early diagnosis of Alzheimer’s disease (AD). To overcome this, the authors propose a Multi-View Masked Graph Neural Network (MVMGNN) that introduces a novel joint node-edge masking mechanism to adaptively select radiomic features and structural connections. Furthermore, a patient-level cross-view gated fusion strategy is designed to effectively integrate multi-view representations. Experiments on the ADNI dataset demonstrate that the proposed method significantly outperforms current models, achieving higher diagnostic accuracy while also identifying critical AD-related brain regions, thereby enhancing model interpretability.

Abstract

Alzheimer's disease (AD) is a common neurodegenerative disorder, and early diagnosis is of great significance for delaying disease progression and enabling timely intervention. Mild cognitive impairment (MCI), which represents an intermediate clinical stage between cognitively normal aging and AD. Structural magnetic resonance imaging (sMRI) provides detailed characterization of anatomical structures and plays an important role in AD-related brain analysis. However, existing sMRI-based brain network methods typically rely on a single graph construction strategy, limiting their ability to jointly capture spatial relationships and morphological similarities between brain regions. To address these issues, this paper proposes an sMRI-based multi-view masked graph neural network model (MVMGNN) for AD diagnosis. A joint node-edge masking mechanism is proposed to simultaneously select radiomics feature dimensions and structural connections, reducing redundancy during graph learning. Furthermore, a patient-level cross-view gated fusion mechanism is proposed to integrate multi-view representations. Experimental results on the ADNI dataset demonstrate that MVMGNN outperforms several competing approaches in AD classification. Interpretability analysis further demonstrates that MVMGNN is able to identify key brain regions associated with AD, providing useful insights into discriminative patterns in sMRI-based brain networks.Our implementation is publicly available at https://github.com/chenzhao2023/MVMGNN_AD

Problem

• Alzheimer's disease
• structural MRI
• brain network
• multi-view learning
• graph neural network

Innovation

• Multi-view Graph Neural Network
• Joint Node-Edge Masking
• Cross-view Gated Fusion
• sMRI-based Brain Network
• Alzheimer's Disease Diagnosis