EUVIMEDEUVIMED entdecken
Crossref

FedDP: Dual Personalization in Federated Medical Image Segmentation

Jiacheng Wang, Yueming Jin, Danail Stoyanov, Liansheng Wang

IEEE Transactions on Medical Imaging · 2024-01 · 43 (1) · 297-308

DOI: 10.1109/tmi.2023.3299206 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Medical Imaging, 2024-01. Verfasst von Jiacheng Wang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 48-mal zitiert (Crossref) und nennt 55 Literaturangaben. Gefördert von: Wellcome Trust, Ministry of Science and Technology of the People's Republic of China, Wellcome/EPSRC Centre for Interventional and Surgical Sciences.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Personalized federated learning (PFL) addresses the data heterogeneity challenge faced by general federated learning (GFL). Rather than learning a single global model, with PFL a collection of models are adapted to the unique feature distribution of each site. However, current PFL methods rarely consider self-attention networks which can handle data heterogeneity by long-range dependency modeling and they do not utilize prediction inconsistencies in local models as an indicator of site uniqueness. In this paper, we propose FedDP, a novel fed erated learning scheme with d ual p ersonalization, which improves model personalization from both feature and prediction aspects to boost image segmentation results. We leverage long-range dependencies by designing a local query (LQ) that decouples the query embedding layer out of each local model, whose parameters are trained privately to better adapt to the respective feature distribution of the site. We then propose inconsistency-guided calibration (IGC), which exploits the inter-site prediction inconsistencies to accommodate the model learning concentration. By encouraging a model to penalize pixels with larger inconsistencies, we better tailor prediction-level patterns to each local site. Experimentally, we compare FedDP with the state-of-the-art PFL methods on two popular medical image segmentation tasks with different modalities, where our results consistently outperform others on both tasks. Our code and models are available at https://github.com/jcwang123/PFL-Seg-Trans.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Calibration

Förderung

  • Wellcome Trust
  • Ministry of Science and Technology of the People's Republic of China
  • Wellcome/EPSRC Centre for Interventional and Surgical Sciences
  • Horizon 2020 Future and Emerging Technologies

Zitieren

APA

Wang, J., Jin, Y., Stoyanov, D., & Wang, L. (2024). FedDP: Dual Personalization in Federated Medical Image Segmentation. IEEE Transactions on Medical Imaging, 43(1), 297-308. https://doi.org/10.1109/tmi.2023.3299206

Vancouver

Wang J, Jin Y, Stoyanov D, Wang L. FedDP: Dual Personalization in Federated Medical Image Segmentation. IEEE Transactions on Medical Imaging. 2024;43(1):297-308. doi:10.1109/tmi.2023.3299206

BibTeX
@article{Wang2024,
  author = {Wang, Jiacheng and Jin, Yueming and Stoyanov, Danail and Wang, Liansheng},
  title = {FedDP: Dual Personalization in Federated Medical Image Segmentation},
  journal = {IEEE Transactions on Medical Imaging},
  year = {2024},
  volume = {43},
  number = {1},
  pages = {297--308},
  doi = {10.1109/tmi.2023.3299206}
}
Kostenlos starten →