BrainNet-MoE: Brain-Inspired Mixture-of-Experts Learning for Neurological Disease Identification
This work addresses a critical diagnostic challenge in neurology for patients with neurodegenerative diseases, but it appears incremental as it builds on existing AI methods with a novel system-level approach.
The authors tackled the problem of early differentiation between Alzheimer's disease and Lewy body dementia, which is challenging due to clinical overlap and rarity, by developing BrainNet-MoE, a brain-inspired mixture-of-experts model, achieving superior classification accuracy with interpretable insights.
The Lewy body dementia (LBD) is the second most common neurodegenerative dementia after Alzheimer's disease (AD). Early differentiation between AD and LBD is crucial because they require different treatment approaches, but this is challenging due to significant clinical overlap, heterogeneity, complex pathogenesis, and the rarity of LBD. While recent advances in artificial intelligence (AI) demonstrate powerful learning capabilities and offer new hope for accurate diagnosis, existing methods primarily focus on designing "neural-level networks". Our work represents a pioneering effort in modeling system-level artificial neural network called BrainNet-MoE for brain modeling and diagnosing. Inspired by the brain's hierarchical organization of bottom-up sensory integration and top-down control, we design a set of disease-specific expert groups to process brain sub-network under different condition, A disease gate mechanism guides the specializa-tion of expert groups, while a transformer layer enables communication be-tween all sub-networks, generating a comprehensive whole-brain represen-tation for downstream disease classification. Experimental results show superior classification accuracy with interpretable insights into how brain sub-networks contribute to different neurodegenerative conditions.