Flexible Multimodal Neuroimaging Fusion for Alzheimer's Disease Progression Prediction

2025-09-08

AI Summary

Alzheimer’s disease (AD) exhibits high inter-subject heterogeneity in cognitive decline rates, and existing multimodal neuroimaging prediction models lack robustness under common clinical scenarios involving missing modalities. To address this, we propose PerM-MoE—a personalized multimodal Mixture-of-Experts model explicitly designed for modality dropout. Its core innovation lies in replacing the conventional single routing mechanism with independent, dynamic modality-specific routers—one per imaging modality (T1, FLAIR, Aβ-PET, tau-PET)—enabling adaptive activation and efficient utilization of expert subnetworks conditioned on available modalities. Evaluated on the ADNI cohort, PerM-MoE demonstrates superior performance across diverse modality-missing settings, achieving significant improvements in predicting 2-year CDR-SB change compared to state-of-the-art baselines. The model exhibits strong robustness to missing data while maintaining clinical practicality through interpretable, modality-aware routing and lightweight expert specialization.

Technology Category

• Machine Learning: Mixture of Experts (MoE)
• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Alzheimer's disease (AD) is a progressive neurodegenerative disease with high inter-patient variance in rate of cognitive decline. AD progression prediction aims to forecast patient cognitive decline and benefits from incorporating multiple neuroimaging modalities. However, existing multimodal models fail to make accurate predictions when many modalities are missing during inference, as is often the case in clinical settings. To increase multimodal model flexibility under high modality missingness, we introduce PerM-MoE, a novel sparse mixture-of-experts method that uses independent routers for each modality in place of the conventional, single router. Using T1-weighted MRI, FLAIR, amyloid beta PET, and tau PET neuroimaging data from the Alzheimer's Disease Neuroimaging Initiative (ADNI), we evaluate PerM-MoE, state-of-the-art Flex-MoE, and unimodal neuroimaging models on predicting two-year change in Clinical Dementia Rating-Sum of Boxes (CDR-SB) scores under varying levels of modality missingness. PerM-MoE outperforms the state of the art in most variations of modality missingness and demonstrates more effective utility of experts than Flex-MoE.

Problem

• Predicting Alzheimer's cognitive decline progression accurately
• Handling missing neuroimaging modalities during clinical inference
• Improving multimodal fusion flexibility under high missingness

Innovation

• Sparse mixture-of-experts method
• Independent routers per modality
• Handles high modality missingness