Interpretable Alzheimer's Diagnosis via Multimodal Fusion of Regional Brain Experts

TL;DR

This paper introduces MREF-AD, a Mixture-of-Experts model that adaptively fuses multimodal neuroimaging data for early Alzheimer's diagnosis, offering improved interpretability and competitive accuracy.

Contribution

The work presents a novel MoE framework that models brain regions as experts and learns subject-specific fusion weights, enhancing interpretability and performance in AD diagnosis.

Findings

MREF-AD outperforms classic and deep baselines in AD diagnosis.

The model provides interpretable insights at modality- and region-level.

Utilizes ADNI data for validation.

Abstract

Accurate and early diagnosis of Alzheimer's disease (AD) is critical for effective intervention and requires integrating complementary information from multimodal neuroimaging data. However, conventional fusion approaches often rely on simple concatenation of features, which cannot adaptively balance the contributions of biomarkers such as amyloid PET and MRI across brain regions. In this work, we propose MREF-AD, a Multimodal Regional Expert Fusion model for AD diagnosis. It is a Mixture-of-Experts (MoE) framework that models mesoscopic brain regions within each modality as independent experts and employs a gating network to learn subject-specific fusion weights. Utilizing tabular neuroimaging and demographic information from the Alzheimer's Disease Neuroimaging Initiative (ADNI), MREF-AD achieves competitive performance over strong classic and deep baselines while providing interpretable, modality- and region-level insight into how structural and molecular imaging jointly contribute to AD diagnosis.