EUVIMEDEUVIMED entdecken
Crossref

Center-specific Federated Learning for Radiation Pneumonitis: A Cross-Center Adaptive Alternating Framework

Meng Yan, Zhixiang Wang, Liyu Ning, Jie Xuan, Zheng Zhang, Hongshui Li, Yaokai Wang, Ming Li, Gengmin Niu, Inigo Bermejo, Andre Dekker, Dirk De Ruysscher und 3 weitere

International Journal of Radiation Oncology*Biology*Physics · 2026-07

DOI: 10.1016/j.ijrobp.2026.06.3083 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Radiation Oncology*Biology*Physics, 2026-07. Verfasst von Meng Yan und 14 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiation Oncology, Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences, Zhejiang Key Laborator…. Die Arbeit nennt 58 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND AND PURPOSE Accurate prediction of symptomatic radiation pneumonitis (RP) is critical for radiotherapy, yet the generalization of deep learning models is hindered by restricted access to multi-center data. Although federated learning (FL) bypasses data-sharing restrictions, standard FL algorithms underperform on highly heterogeneous clinical data across institutions. Therefore, this study aims to evaluate the clinical feasibility of a center-specific federated learning approach. METHODS We evaluated the Federated Cross-Center Adaptive Alternating Model (FCAAM), a tailored framework designed to decouple globally transferable representations from the center-specific adaptations. The framework uses a dynamic weighting mechanism to handle data heterogeneity and employs differential privacy for enhanced security. The proposed FCAAM was evaluated for the prediction of RP using planning CT and dose images on a diverse cohort of 1,238 patients from four datasets representing real-world temporal and spatial shifts. Its performance was compared with single-center model, centralized model, and standard federated average model (FedAvg). RESULTS FCAAM demonstrated improved cross-center performance and consistent robustness compared to baseline. It achieved a stable area under the curve (AUC) across all four dataset test sets (0.71-0.77), outperforming the single-center models (all AUCs < 0.70) and FedAvg. FCAAM's performance was comparable to the centralized model and showed a relative improvement in sensitivity to small-sized datasets. Interpretability analysis confirmed that FCAAM learned clinically relevant features, and a web platform demonstrated the practical feasibility of applying FCAAM for multi-center collaboration. CONCLUSIONS FCAAM provides a privacy-preserving, robust and interpretable solution for multi-center RP prediction. This center-specific strategy shows potential to enhance clinical decision-making and reduce cross-center performance gaps, supporting safer personalized radiotherapy.

Autor:innen und Institutionen

  • Department of Radiation Oncology, Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences, Zhejiang Key Laboratory of Particle Radiotherapy Equipment, Hangzhou, China; Department of R…
  • Department of Radiology, Feinberg School of Medicine, Northwestern University, Chicago, Illinois, 60611.
  • Department of Radiation Oncology, Shanghai Chest Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, China.
  • Department of Radiation Oncology, Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences, Zhejiang Key Laboratory of Particle Radiotherapy Equipment, Hangzhou, China.
  • Department of Radiation Oncology, Key Laboratory of Cancer Prevention and Therapy, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center for Cancer, Tianjin's Clinical Research Cent…
  • Department of Radiation Oncology, The Second People Hospital of Dezhou, Dezhou City, China.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Yan, M., Wang, Z., Ning, L., Xuan, J., Zhang, Z., Li, H., Wang, Y., Li, M., Niu, G., Bermejo, I., Dekker, A., De Ruysscher, D., Wee, L., Zhao, L., & Zhang, Z. (2026). Center-specific Federated Learning for Radiation Pneumonitis: A Cross-Center Adaptive Alternating Framework. International Journal of Radiation Oncology*Biology*Physics. https://doi.org/10.1016/j.ijrobp.2026.06.3083

Vancouver

Yan M, Wang Z, Ning L, Xuan J, Zhang Z, Li H, et al. Center-specific Federated Learning for Radiation Pneumonitis: A Cross-Center Adaptive Alternating Framework. International Journal of Radiation Oncology*Biology*Physics. 2026. doi:10.1016/j.ijrobp.2026.06.3083

BibTeX
@article{Yan2026,
  author = {Yan, Meng and Wang, Zhixiang and Ning, Liyu and Xuan, Jie and Zhang, Zheng and Li, Hongshui and Wang, Yaokai and Li, Ming and Niu, Gengmin and Bermejo, Inigo and Dekker, Andre and De Ruysscher, Dirk and Wee, Leonard and Zhao, Lujun and Zhang, Zhen},
  title = {Center-specific Federated Learning for Radiation Pneumonitis: A Cross-Center Adaptive Alternating Framework},
  journal = {International Journal of Radiation Oncology*Biology*Physics},
  year = {2026},
  doi = {10.1016/j.ijrobp.2026.06.3083}
}
Kostenlos starten →