{"ID":2876689,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.21458","arxiv_id":"2508.21458","title":"Federated Fine-tuning of SAM-Med3D for MRI-based Dementia Classification","abstract":"While foundation models (FMs) offer strong potential for AI-based dementia diagnosis, their integration into federated learning (FL) systems remains underexplored. In this benchmarking study, we systematically evaluate the impact of key design choices: classification head architecture, fine-tuning strategy, and aggregation method, on the performance and efficiency of federated FM tuning using brain MRI data. Using a large multi-cohort dataset, we find that the architecture of the classification head substantially influences performance, freezing the FM encoder achieves comparable results to full fine-tuning, and advanced aggregation methods outperform standard federated averaging. Our results offer practical insights for deploying FMs in decentralized clinical settings and highlight trade-offs that should guide future method development.","short_abstract":"While foundation models (FMs) offer strong potential for AI-based dementia diagnosis, their integration into federated learning (FL) systems remains underexplored. In this benchmarking study, we systematically evaluate the impact of key design choices: classification head architecture, fine-tuning strategy, and aggrega...","url_abs":"https://arxiv.org/abs/2508.21458","url_pdf":"https://arxiv.org/pdf/2508.21458v1","authors":"[\"Kaouther Mouheb\",\"Marawan Elbatel\",\"Janne Papma\",\"Geert Jan Biessels\",\"Jurgen Claassen\",\"Huub Middelkoop\",\"Barbara van Munster\",\"Wiesje van der Flier\",\"Inez Ramakers\",\"Stefan Klein\",\"Esther E. Bron\"]","published":"2025-08-29T09:43:02Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}