Federated nnU-Net for Privacy-Preserving Medical Image Segmentation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915467143151616 |
|---|---|
| author | Skorupko, Grzegorz Avgoustidis, Fotios Martín-Isla, Carlos Garrucho, Lidia Kessler, Dimitri A. Pujadas, Esmeralda Ruiz Díaz, Oliver Bobowicz, Maciej Gwoździewicz, Katarzyna Bargalló, Xavier Jaruševičius, Paulius Osuala, Richard Kushibar, Kaisar Lekadir, Karim |
| author_facet | Skorupko, Grzegorz Avgoustidis, Fotios Martín-Isla, Carlos Garrucho, Lidia Kessler, Dimitri A. Pujadas, Esmeralda Ruiz Díaz, Oliver Bobowicz, Maciej Gwoździewicz, Katarzyna Bargalló, Xavier Jaruševičius, Paulius Osuala, Richard Kushibar, Kaisar Lekadir, Karim |
| contents | 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 collected data is stored in the same location where nnU-Net is trained. This centralized approach has various limitations, such as potential leakage of sensitive patient information and violation of patient privacy. Federated learning has emerged as a key approach for training segmentation models in a decentralized manner, enabling collaborative development while prioritising patient privacy. In this paper, we propose FednnU-Net, a plug-and-play, federated learning extension of the nnU-Net framework. To this end, we contribute two federated methodologies to unlock decentralized training of nnU-Net, namely, Federated Fingerprint Extraction (FFE) and Asymmetric Federated Averaging (AsymFedAvg). We conduct a comprehensive set of experiments demonstrating high and consistent performance of our methods for breast, cardiac and fetal segmentation based on a multi-modal collection of 6 datasets representing samples from 18 different institutions. To democratize research as well as real-world deployments of decentralized training in clinical centres, we publicly share our framework at https://github.com/faildeny/FednnUNet . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_02549 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Federated nnU-Net for Privacy-Preserving Medical Image Segmentation Skorupko, Grzegorz Avgoustidis, Fotios Martín-Isla, Carlos Garrucho, Lidia Kessler, Dimitri A. Pujadas, Esmeralda Ruiz Díaz, Oliver Bobowicz, Maciej Gwoździewicz, Katarzyna Bargalló, Xavier Jaruševičius, Paulius Osuala, Richard Kushibar, Kaisar Lekadir, Karim Computer Vision and Pattern Recognition Artificial Intelligence 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 collected data is stored in the same location where nnU-Net is trained. This centralized approach has various limitations, such as potential leakage of sensitive patient information and violation of patient privacy. Federated learning has emerged as a key approach for training segmentation models in a decentralized manner, enabling collaborative development while prioritising patient privacy. In this paper, we propose FednnU-Net, a plug-and-play, federated learning extension of the nnU-Net framework. To this end, we contribute two federated methodologies to unlock decentralized training of nnU-Net, namely, Federated Fingerprint Extraction (FFE) and Asymmetric Federated Averaging (AsymFedAvg). We conduct a comprehensive set of experiments demonstrating high and consistent performance of our methods for breast, cardiac and fetal segmentation based on a multi-modal collection of 6 datasets representing samples from 18 different institutions. To democratize research as well as real-world deployments of decentralized training in clinical centres, we publicly share our framework at https://github.com/faildeny/FednnUNet . |
| title | Federated nnU-Net for Privacy-Preserving Medical Image Segmentation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2503.02549 |