EUVIMEDEUVIMED entdecken
Crossref

Modality-Agnostic Federated Learning With Adaptive Updates for Heterogeneous Medical Image Tasks

Wenwen Zhang, Zhenyu Tang, Hao Zhang, Shaohao Rui, Z Jane Wang, Xiaosong Wang

IEEE Transactions on Medical Imaging · 2026-06 · 45 (6) · 3276-3286

DOI: 10.1109/tmi.2026.3671287 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Medical Imaging, 2026-06. Verfasst von Wenwen Zhang und 5 weiteren Autor:innen. Hauptthemen laut MEDLINE: Federated Learning, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 42 Literaturangaben. Gefördert von: National Key Research and Development Program of China, Shanghai Artificial Intelligence Laboratory.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Federated learning (FL) enables collaborative model training across decentralized medical datasets while preserving data privacy. Its practical adoption remains limited due to data heterogeneity, specifically, differences in input imaging modality (e.g., CT or MRI) and client task (e.g., segmentation or classification) across participating institutions (clients). Such data heterogeneity poses significant challenges for jointly learning a unified global model that generalizes across clients with different input modality and task. To address this, we propose FedCMT, a modality-agnostic FL framework that adaptively aggregates heterogeneous client models. FedCMT supports flexible input modalities and diverse local tasks by incorporating group-wise adapters and personalized decoders that capture modality- and task-specific features. To enhance collaboration across clients, FedCMT employs a conflict-averse module that extracts modality-invariant representations and mitigates inter-client feature conflicts. FedCMT also integrates a global-to-local knowledge distillation mechanism to balance global consistency and local specialization. The proposed FedCMT maintains stability while fostering shared knowledge in diverse medical imaging modalities. We evaluate FedCMT on ten CT and MR datasets involving up to eight federated clients performing segmentation or classification tasks. Experimental results show that FedCMT consistently outperforms state-of-the-art FL baselines, yielding an average improvement of 4.76% over state-of-the-art methods and 4.01% over standalone training. These results demonstrate FedCMT as a promising adaptable FL for real-world medical image analysis.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Federated LearningImage Processing, Computer-AssistedHumansMagnetic Resonance ImagingTomography, X-Ray ComputedAlgorithmsAdaptive AlgorithmsDatabases, Factual

Förderung

  • National Key Research and Development Program of China
  • Shanghai Artificial Intelligence Laboratory

Zitieren

APA

Zhang, W., Tang, Z., Zhang, H., Rui, S., Wang, Z. J., & Wang, X. (2026). Modality-Agnostic Federated Learning With Adaptive Updates for Heterogeneous Medical Image Tasks. IEEE Transactions on Medical Imaging, 45(6), 3276-3286. https://doi.org/10.1109/tmi.2026.3671287

Vancouver

Zhang W, Tang Z, Zhang H, Rui S, Wang ZJ, Wang X. Modality-Agnostic Federated Learning With Adaptive Updates for Heterogeneous Medical Image Tasks. IEEE Transactions on Medical Imaging. 2026;45(6):3276-3286. doi:10.1109/tmi.2026.3671287

BibTeX
@article{Zhang2026,
  author = {Zhang, Wenwen and Tang, Zhenyu and Zhang, Hao and Rui, Shaohao and Wang, Z Jane and Wang, Xiaosong},
  title = {Modality-Agnostic Federated Learning With Adaptive Updates for Heterogeneous Medical Image Tasks},
  journal = {IEEE Transactions on Medical Imaging},
  year = {2026},
  volume = {45},
  number = {6},
  pages = {3276--3286},
  doi = {10.1109/tmi.2026.3671287}
}
Kostenlos starten →