Flexible Multimodal Neuroimaging Fusion for Alzheimer's Disease Progression Prediction

Alzheimer's disease (AD) is a progressive neurodegenerati ve disease with high inter-patient variance in rate of cogniti ve 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 cas e in clinical settings. To increase multimodal model flexibility under hi gh modality missingness, we introduce PerM-MoE, a novel sparse mixture -of-experts method that uses independent routers for each modality in pl ace of the conventional, single router. Using T1-weighted MRI, FL AIR, amyloid beta PET, and tau PET neuroimaging data from the Alzheim er's Disease Neuroimaging Initiative (ADNI), we evaluate PerM-MoE, state-of-the-art Flex-MoE, and unimodal neuroimaging models on p redicting two-year change in Clinical Dementia Rating-Sum of Boxes (C DR-SB) scores under varying levels of modality missingness. PerM-MoE outperforms the state of the art in most variations of modality miss ingness and demonstrates more effective utility of experts than Flex-Mo E. Keywords: Alzheimer's disease Neuroimaging Multimodal fusion Mixture of experts Disease progression prediction