Not Only Grey Matter: OmniBrain for Robust Multimodal Classification of Alzheimer's Disease
Sharshar, Ahmed Ashraf, Yasser Bakr, Tameem Hassan, Salma Elgendy, Hosam Yaqub, Mohammad Guizani, Mohsen
Sharshar, Ahmed
Ashraf, Yasser
Bakr, Tameem
Hassan, Salma
Elgendy, Hosam
Yaqub, Mohammad
Guizani, Mohsen
Supervisor
Department
Computer Vision
Embargo End Date
Type
Conference proceeding
Date
License
Language
Collections
Research Projects
Organizational Units
Journal Issue
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.
Citation
A. Sharshar, Y. Ashraf, T. Bakr, S. Hassan, H. Elgendy, M. Yaqub , et al., "Not Only Grey Matter: OmniBrain for Robust Multimodal Classification of Alzheimer's Disease," 2026, pp. 1311-1320.
Source
Conference
2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)
Keywords
31 Biological Sciences, 46 Information and Computing Sciences, 4611 Machine Learning, 3 Good Health and Well Being
Subjects
Source
2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)
Publisher
IEEE