Improving personalized federated learning to optimize site-specific performance in computer-aided detection/diagnosis
We demonstrate that dynamically adjusting global model weights during personalized model updates can improve the stability and adaptability of PFL. The proposed method reduces the hyperparameter tuning costs and offers potential benefits for CAD software.
Authors
- Tomomi Takenaga (ORCID: https://orcid.org/0000-0001-7198-1588)
- Osamu Abe (ORCID: https://orcid.org/0000-0002-1180-2629)
- Aiki Yamada (ORCID: https://orcid.org/0009-0006-2682-0332)
- Soichiro Miki (ORCID: https://orcid.org/0000-0001-6365-6531)
- Toshiya Nakaguchi (ORCID: https://orcid.org/0000-0002-8348-6178)
- Takeharu Yoshikawa
- Shouhei Hanaoka (ORCID: https://orcid.org/0000-0002-7496-1651)
- Yukihiro Nomura (ORCID: https://orcid.org/0000-0001-6471-9936)
Institutions
- Chiba University (JP)
- University of Tokyo Hospital (JP)
Publication Details
- Journal
- Journal of Medical Imaging
- Published
- 2025-10-22
- DOI
- https://doi.org/10.1117/1.jmi.12.5.054503
- Citations
- 1
- Primary Topic
- Medical Imaging and Analysis
- Type
- article
- Field-Weighted Citation Impact
- 0.67