Federated nnU-Net for Privacy-Preserving Medical Image Segmentation

2025-03-04

AI Summary

To address patient privacy leakage and data silos in multi-center medical image segmentation, this paper proposes the first privacy-preserving federated learning framework tailored for nnU-Net. Methodologically, it introduces (1) Federated Fingerprint Extraction (FFE), which locally computes generalizable, low-entropy model fingerprints—replacing raw images for upload—and (2) Asymmetric Federated Averaging (AsymFedAvg), designed to handle cross-institutional data heterogeneity and enhance aggregation robustness and fairness. Evaluated across six public benchmarks encompassing breast, cardiac, and fetal segmentation tasks from 18 clinical institutions, the framework achieves performance on par with centralized training and significantly outperforms existing federated approaches. The implementation is open-source, modular, and plug-and-play. This work establishes a scalable, regulatory-compliant distributed training paradigm for privacy-sensitive medical AI.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Computer Vision: Segmentation
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Security and Privacy: Data transparency and provenance

Abstract

The nnU-Net framework has played a crucial role in medical image segmentation and has become the gold standard in multitudes of applications targeting different diseases, organs, and modalities. However, so far it has been used primarily in a centralized approach where the data collected from hospitals are stored in one center and used to train the nnU-Net. This centralized approach has various limitations, such as leakage of sensitive patient information and violation of patient privacy. Federated learning is one of the approaches to train a segmentation model in a decentralized manner that helps preserve patient privacy. In this paper, we propose FednnU-Net, a federated learning extension of nnU-Net. We introduce two novel federated learning methods to the nnU-Net framework - Federated Fingerprint Extraction (FFE) and Asymmetric Federated Averaging (AsymFedAvg) - and experimentally show their consistent performance for breast, cardiac and fetal segmentation using 6 datasets representing samples from 18 institutions. Additionally, to further promote research and deployment of decentralized training in privacy constrained institutions, we make our plug-n-play framework public. The source-code is available at https://github.com/faildeny/FednnUNet .

Problem

• Addresses privacy risks in centralized medical image segmentation.
• Proposes federated learning to protect patient data privacy.
• Introduces FednnU-Net with novel methods for decentralized training.

Innovation

• Federated learning for decentralized medical image segmentation
• Introduces Federated Fingerprint Extraction (FFE) method
• Proposes Asymmetric Federated Averaging (AsymFedAvg) technique