Multi-model deep learning for dementia detection: addressing data and model limitations
The findings highlight the limitations of current architectures in sMRI dementia classification, including suboptimal feature extraction and class-specific biases. While certain models, such as multimodal attention and 3D-CNN, performed better overall, precision and generalization remain challenges. Future work should focus on improved data representation through advanced computer vision methods and architectural modifications to enhance diagnostic accuracy and computational efficiency.
Authors
- Sultan H. Alamri (ORCID: https://orcid.org/0000-0003-4991-6223)
- Fathy Eassa (ORCID: https://orcid.org/0000-0003-3987-9051)
- Haneen Banjar (ORCID: https://orcid.org/0000-0003-4475-4878)
- Fares Jammal
- Areej Y. Bayahya (ORCID: https://orcid.org/0000-0002-7924-984X)
- Omar Talabay
Institutions
- King Abdulaziz University (SA)
- Institute for the Future (US)
- University of Business and Technology (SA)
Publication Details
- Journal
- Frontiers in Neuroscience
- Published
- 2025-11-25
- DOI
- https://doi.org/10.3389/fnins.2025.1638022
- Primary Topic
- Dementia and Cognitive Impairment Research
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- King Abdulaziz University