Not Only Grey Matter: OmniBrain for Robust Multimodal Classification of Alzheimer's Disease

Ahmed Sharshar, Yasser Ashraf, Tameem Bakr, Salma Hassan, Hosam Elgendy, Mohammad Yaqub, Mohsen Guizani

Abstract: Alzheimer's disease affects over 55 million people world-wide and is projected to more than double by 2050, necessitating rapid, accurate, and scalable diagnostics. However, existing approaches are limited because they can-not achieve clinically acceptable accuracy, generalization across datasets, robustness to missing modalities, and explainability all at the same time. This inability to satisfy all these requirements simultaneously undermines their reliability in clinical settings. We propose OmniBrain, a mul-timodal framework that integrates brain MRI, radiomics, gene expression, and clinical data using a unified model with cross-attention and modality dropout. OmniBrain achieves 92.2±2.4% accuracy on the ANMerge dataset and generalizes to the MRI-only ADNI dataset with 70.4 ± 2.7% accuracy, outperforming unimodal and prior multimodal approaches. Explainability analyses highlight neuropatho-logically relevant brain regions and genes, enhancing clinical trust. OmniBrain offers a robust, interpretable, and practical solution for real-world Alzheimer's diagnosis.

External IDs:dblp:conf/iccv/SharsharABHEYG25