Metraipolis › archive › dc_fa797abe3751
Med-DualLoRA: Local Adaptation of Foundation Models for 3D Cardiac MRI — arXiv:2603.10967
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2603.10967
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-10T18:41:58.650Z
- SHA-256 of the archived text
46cc7803d6c878bc12a27f793cf7b9603ca1db38b1137440017a02eb9543e583- Stable URL of this page
https://metraipolis.com/documento/dc_fa797abe3751
How to cite
Med-DualLoRA: Local Adaptation of Foundation Models for 3D Cardiac MRI — arXiv:2603.10967 — arXiv (en), https://arxiv.org/abs/2603.10967 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fa797abe3751 (Metraipolis archive dc_fa797abe3751, sha256 46cc7803d6c878bc12a27f793cf7b9603ca1db38b1137440017a02eb9543e583)
BibTeX
@misc{dcfa797abe3751,
title = {Med-DualLoRA: Local Adaptation of Foundation Models for 3D Cardiac MRI — arXiv:2603.10967},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2603.10967},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fa797abe3751; sha256 46cc7803d6c878bc12a27f793cf7b9603ca1db38b1137440017a02eb9543e583},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2603.10967. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Foundation models (FMs) show great promise for robust downstream performance across medical imaging tasks and modalities, including cardiac magnetic resonance (CMR), following task-specific adaptation. However, adaptation using single-site data may lead to suboptimal performance and increased model bias, while centralized fine-tuning on clinical data is often infeasible due to privacy constraints. Federated fine-tuning offers a privacy-preserving alternative; yet conventional approaches struggle under heterogeneous, non-IID multi-center data and incur substantial communication overhead when adapting large models. In this work, we study federated FM fine-tuning for 3D CMR disease detection and propose Med-DualLoRA, a client-aware parameter-efficient fine-tuning (PEFT) federated framework that disentangles globally shared and local low-rank adaptations (LoRA) through additive decomposition. Global and local LoRA modules are trained locally, but only the global component is shared and aggregated across sites, keeping local adapters private. This design improves personalization while significantly reducing communication cost, and experiments show that adapting only two transformer blocks preserves performance while further improving efficiency. We evaluate our method on a multi-center state-of-the-art cine 3D CMR FM fine-tuned for disease detection using ACDC and combined M\&Ms datasets, treating each vendor as a federated client. Med-DualLoRA achieves statistically significant improved performance (balanced accuracy 0.768, specificity 0.612) compared to other federated PEFT baselines, while maintaining communication efficiency. Our approach provides a scalable solution for local federated adaptation of medical FMs under realistic clinical constraints. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2603.10967 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-10T18:37:37.557Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).