{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T15:57:18Z","timestamp":1778255838083,"version":"3.51.4"},"reference-count":82,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T00:00:00Z","timestamp":1738800000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T00:00:00Z","timestamp":1738800000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Federated learning is a renowned technique for utilizing decentralized data while preserving privacy. However, real-world applications often face challenges like partially labeled datasets, where only a few locations have certain expert annotations, leaving large portions of unlabeled data unused. Leveraging these could enhance transformer architectures\u2019 ability in regimes with small and diversely annotated sets. We conduct the largest federated cardiac CT analysis to date (<jats:italic>n<\/jats:italic> = 8, 104) in a real-world setting across eight hospitals. Our two-step semi-supervised strategy distills knowledge from task-specific CNNs into a transformer. First, CNNs predict on unlabeled data per label type and then the transformer learns from these predictions with label-specific heads. This improves predictive accuracy and enables simultaneous learning of all partial labels across the federation, and outperforms UNet-based models in generalizability on downstream tasks. Code and model weights are made openly available for leveraging future cardiac CT analysis.<\/jats:p>","DOI":"10.1038\/s41746-025-01434-3","type":"journal-article","created":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T07:07:00Z","timestamp":1738825620000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Real world federated learning with a knowledge distilled transformer for cardiac CT imaging"],"prefix":"10.1038","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0804-5794","authenticated-orcid":false,"given":"Malte","family":"T\u00f6lle","sequence":"first","affiliation":[]},{"given":"Philipp","family":"Garthe","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2816-6793","authenticated-orcid":false,"given":"Clemens","family":"Scherer","sequence":"additional","affiliation":[]},{"given":"Jan Moritz","family":"Seliger","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8072-1988","authenticated-orcid":false,"given":"Andreas","family":"Leha","sequence":"additional","affiliation":[]},{"given":"Nina","family":"Kr\u00fcger","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9371-2709","authenticated-orcid":false,"given":"Stefan","family":"Simm","sequence":"additional","affiliation":[]},{"given":"Simon","family":"Martin","sequence":"additional","affiliation":[]},{"given":"Sebastian","family":"Eble","sequence":"additional","affiliation":[]},{"given":"Halvar","family":"Kelm","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4981-5732","authenticated-orcid":false,"given":"Moritz","family":"Bednorz","sequence":"additional","affiliation":[]},{"given":"Florian","family":"Andr\u00e9","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7102-534X","authenticated-orcid":false,"given":"Peter","family":"Bannas","sequence":"additional","affiliation":[]},{"given":"Gerhard","family":"Diller","sequence":"additional","affiliation":[]},{"given":"Norbert","family":"Frey","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4121-7161","authenticated-orcid":false,"given":"Stefan","family":"Gro\u00df","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0737-7375","authenticated-orcid":false,"given":"Anja","family":"Hennemuth","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2359-2294","authenticated-orcid":false,"given":"Lars","family":"Kaderali","sequence":"additional","affiliation":[]},{"given":"Alexander","family":"Meyer","sequence":"additional","affiliation":[]},{"given":"Eike","family":"Nagel","sequence":"additional","affiliation":[]},{"given":"Stefan","family":"Orwat","sequence":"additional","affiliation":[]},{"given":"Moritz","family":"Seiffert","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5347-7441","authenticated-orcid":false,"given":"Tim","family":"Friede","sequence":"additional","affiliation":[]},{"given":"Tim","family":"Seidler","sequence":"additional","affiliation":[]},{"given":"Sandy","family":"Engelhardt","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,2,6]]},"reference":[{"key":"1434_CR1","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1038\/s42256-023-00625-5","volume":"5","author":"T R\u00e4dsch","year":"2023","unstructured":"R\u00e4dsch, T. et al. Labelling instructions matter in biomedical image analysis. Nat. Mach. Intell. 5, 273\u2013283 (2023).","journal-title":"Nat. Mach. Intell."},{"key":"1434_CR2","unstructured":"Rahimi, S., Oktay, O., Alvarez-Valle, J. & Bharadwaj, S. Addressing the exorbitant cost of labeling medical images with active learning. In: International Conference on Machine Learning and Medical Imaging and Analysis (2021)."},{"key":"1434_CR3","unstructured":"European Parliament and Council of the European Union: Regulation (EU) 2016\/679: General Data Protection Regulation https:\/\/gdpr.eu\/ (2016)."},{"key":"1434_CR4","first-page":"2398","volume":"3","author":"N Rieke","year":"2020","unstructured":"Rieke, N. et al. The future of digital health with federated learning. Nat. Digit. Med. 3, 2398\u20136352 (2020).","journal-title":"Nat. Digit. Med."},{"key":"1434_CR5","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1038\/s42256-020-0186-1","volume":"2","author":"GA Kaissis","year":"2020","unstructured":"Kaissis, G. A., Makowski, M. R., R\u00fcckert, D. & Braren, R. F. Secure, privacy-preserving and federated machine learning in medical imaging. Nat. Mach. Intell. 2, 305\u2013311 (2020).","journal-title":"Nat. Mach. Intell."},{"key":"1434_CR6","doi-asserted-by":"publisher","first-page":"473","DOI":"10.1038\/s42256-021-00337-8","volume":"3","author":"G Kaissis","year":"2021","unstructured":"Kaissis, G. et al. End-to-end privacy preserving deep learning on multi-institutional medical imaging. Nat. Mach. Intell. 3, 473\u2013484 (2021).","journal-title":"Nat. Mach. Intell."},{"key":"1434_CR7","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-021-00489-2","volume":"4","author":"A Sadilek","year":"2021","unstructured":"Sadilek, A. et al. Privacy-first health research with federated learning. npj Digit Med. 4, 132 (2021).","journal-title":"npj Digit Med."},{"key":"1434_CR8","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-33407-5","volume":"13","author":"S Pati","year":"2022","unstructured":"Pati, S. et al. Federated learning enables big data for rare cancer boundary detection. Nat. Commun. 13, 7346 (2022).","journal-title":"Nat. Commun."},{"key":"1434_CR9","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1038\/s41591-021-01506-3","volume":"27","author":"I Dayan","year":"2021","unstructured":"Dayan, I. et al. Federated learning for predicting clinical outcomes in patients with COVID-19. Nat. Med. 27, 1735\u20131743 (2021).","journal-title":"Nat. Med."},{"key":"1434_CR10","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1038\/s41591-022-02155-w","volume":"29","author":"J Ogier du Terrail","year":"2023","unstructured":"Ogier du Terrail, J. et al. Federated learning for predicting histological response to neoadjuvant chemotherapy in triple-negative breast cancer. Nat. Med. 29, 135\u2013146 (2023).","journal-title":"Nat. Med."},{"key":"1434_CR11","doi-asserted-by":"publisher","first-page":"755","DOI":"10.1161\/CIRCULATIONAHA.121.058696","volume":"146","author":"S Goto","year":"2022","unstructured":"Goto, S. et al. Multinational federated learning approach to train ECG and echocardiogram models for hypertrophic cardiomyopathy detection. Circulation 146, 755\u2013769 (2022).","journal-title":"Circulation"},{"key":"1434_CR12","first-page":"3551","volume":"12","author":"A Linardos","year":"2022","unstructured":"Linardos, A. et al. Federated learning for multi-center imaging diagnostics: a simulation study in cardiovascular disease. Nat. Sci. Rep. 12, 3551 (2022).","journal-title":"Nat. Sci. Rep."},{"key":"1434_CR13","doi-asserted-by":"publisher","first-page":"3543","DOI":"10.1109\/TMI.2021.3090082","volume":"40","author":"VM Campello","year":"2021","unstructured":"Campello, V. M. et al. Multi-Centre, Multi-Vendor and Multi-Disease Cardiac Segmentation: The M&Ms Challenge. IEEE Trans. Med. Imaging 40, 3543\u20133554 (2021).","journal-title":"IEEE Trans. Med. Imaging"},{"key":"1434_CR14","doi-asserted-by":"publisher","first-page":"2514","DOI":"10.1109\/TMI.2018.2837502","volume":"37","author":"O Bernard","year":"2018","unstructured":"Bernard, O. et al. Deep Learning Techniques for Automatic MRI Cardiac Multi-Structures Segmentation and Diagnosis: Is the Problem Solved? IEEE Trans. Med. Imaging 37, 2514\u20132525 (2018).","journal-title":"IEEE Trans. Med. Imaging"},{"key":"1434_CR15","doi-asserted-by":"publisher","unstructured":"Oquab, M. et al. DINOv2: Learning Robust Visual Features without Supervision. https:\/\/doi.org\/10.48550\/arXiv:2304.07193 (2023).","DOI":"10.48550\/arXiv:2304.07193"},{"key":"1434_CR16","doi-asserted-by":"publisher","unstructured":"Liu, J. et al. CLIP-Driven Universal Model for Organ Segmentation and Tumor Detection. International Conference on Medical Image Computing and Computer-Assisted Intervention. https:\/\/doi.org\/10.1109\/ICCV51070.2023.01934 (2023).","DOI":"10.1109\/ICCV51070.2023.01934"},{"key":"1434_CR17","doi-asserted-by":"publisher","unstructured":"Touvron, H. et al. LLaMA: Open and Efficient Foundation Language Models. https:\/\/doi.org\/10.48550\/arXiv:2302.13971 (2023).","DOI":"10.48550\/arXiv:2302.13971"},{"key":"1434_CR18","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","volume":"18","author":"F Isensee","year":"2021","unstructured":"Isensee, F., Jaeger, P. F., Kohl, S. A. A., Petersen, J. & Maier-Hein, K. H. nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat. Methods 18, 203\u2013211 (2021).","journal-title":"Nat. Methods"},{"key":"1434_CR19","doi-asserted-by":"publisher","first-page":"103156","DOI":"10.1016\/j.media.2024.103156","volume":"95","author":"S Kim","year":"2024","unstructured":"Kim, S. et al. Federated learning with knowledge distillation for multi-organ segmentation with partially labeled datasets. Med. Image Anal. 95, 103156 (2024).","journal-title":"Med. Image Anal."},{"key":"1434_CR20","doi-asserted-by":"crossref","unstructured":"Ulrich, C. et al. MultiTalent: A Multi-Dataset Approach to Medical Image Segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Interventions (2023).","DOI":"10.1007\/978-3-031-43898-1_62"},{"key":"1434_CR21","doi-asserted-by":"publisher","first-page":"5521","DOI":"10.3390\/app13095521","volume":"13","author":"J Maur\u00edcio","year":"2023","unstructured":"Maur\u00edcio, J., Domingues, I. & Bernardino, J. Comparing vision transformers and convolutional neural networks for image classification: A literature review. Appl. Sci. 13, 5521 (2023).","journal-title":"Appl. Sci."},{"key":"1434_CR22","doi-asserted-by":"publisher","first-page":"1789","DOI":"10.1007\/s11263-021-01453-z","volume":"129","author":"J Gou","year":"2021","unstructured":"Gou, J., Yu, B., Maybank, S. J. & Tao, D. Knowledge distillation: A survey. Int. J. Comput. Vis. 129, 1789\u20131819 (2021).","journal-title":"Int. J. Comput. Vis."},{"key":"1434_CR23","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-29763-x","volume":"13","author":"C Wu","year":"2022","unstructured":"Wu, C. et al. Communication-efficient federated learning via knowledge distillation. Nat. Commun. 13, 2032 (2022).","journal-title":"Nat. Commun."},{"key":"1434_CR24","doi-asserted-by":"publisher","unstructured":"Hinton, G., Vinyals, O. & Dean, J. Distilling the knowledge in a neural network. In: Advances in Neural Information Processing Systems Workshop. https:\/\/doi.org\/10.48550\/arXiv:1503.02531 (2014).","DOI":"10.48550\/arXiv:1503.02531"},{"key":"1434_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, F., Zhu, X., Ye, M. Fast human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). https:\/\/openaccess.thecvf.com\/content_CVPR_2019\/papers\/Zhang_Fast_Human_Pose_Estimation_CVPR_2019_paper.pdf (2019).","DOI":"10.1109\/CVPR.2019.00363"},{"key":"1434_CR26","first-page":"13657","volume":"35","author":"P Passban","year":"2021","unstructured":"Passban, P., Wu, Y., Rezagholizadeh, M. & Liu, Q. ALP-KD: Attention-based layer projection for knowledge distillation. Proc. AAAI Conf. Artif. Intell. 35, 13657\u201313665 (2021).","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"1434_CR27","unstructured":"Touvron, H. et al. Training data-efficient image transformers distillation through attention. In: itProceedings of the 38th International Conference on Machine Learning, vol. 139, pp. 10347\u201310357 https:\/\/proceedings.mlr.press\/v139\/touvron21a.html (2021)."},{"key":"1434_CR28","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1109\/TNNLS.2020.2970494","volume":"32","author":"H Chen","year":"2021","unstructured":"Chen, H., Wang, Y., Xu, C., Xu, C. & Tao, D. Learning student networks via feature embedding. IEEE Trans. Neural Netw. Learn. Syst. 32, 25\u201335 (2021).","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"1434_CR29","doi-asserted-by":"crossref","unstructured":"Passalis, N., Tzelepi, M. & Tefas, A. Heterogeneous knowledge distillation using information flow modeling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). https:\/\/arxiv.org\/10.48550\/arXiv.2005.00727 (2020).","DOI":"10.1109\/CVPR42600.2020.00241"},{"key":"1434_CR30","unstructured":"Afonin, A., Karimireddy, S.P. Towards model agnostic federated learning using knowledge distillation. In: itProceedings of the International Conference on Learning Representations (ICLR) https:\/\/openreview.net\/forum?id=lQI_mZjvBxj (2022)."},{"key":"1434_CR31","doi-asserted-by":"publisher","first-page":"102287","DOI":"10.1016\/j.compmedimag.2023.102287","volume":"109","author":"A Zeng","year":"2023","unstructured":"Zeng, A. et al. ImageCAS: A large-scale dataset and benchmark for coronary artery segmentation based on computed tomography angiography images. Comput. Med. Imaging Graph. 109, 102287 (2023).","journal-title":"Comput. Med. Imaging Graph."},{"key":"1434_CR32","unstructured":"World Health Organization: Cardiovascular diseases (CVDs) https:\/\/www.who.int\/news-room\/fact-sheets\/detail\/cardiovascular-diseases-(cvds) (June 2021)."},{"key":"1434_CR33","doi-asserted-by":"publisher","first-page":"2388","DOI":"10.1093\/eurheartj\/ehs220","volume":"33","author":"P Genereux","year":"2012","unstructured":"Genereux, P. et al. Transcatheter aortic valve implantation 10-year anniversary: review of current evidence and clinical implications. Eur. Heart J. 33, 2388\u20132398 (2012).","journal-title":"Eur. Heart J."},{"key":"1434_CR34","doi-asserted-by":"publisher","first-page":"1597","DOI":"10.1056\/NEJMoa1008232","volume":"363","author":"MB Leon","year":"2010","unstructured":"Leon, M. B. et al. Transcatheter aortic-valve implantation for aortic stenosis in patients who cannot undergo surgery. N. Engl. J. Med. 363, 1597\u20131607 (2010).","journal-title":"N. Engl. J. Med."},{"key":"1434_CR35","first-page":"115","volume":"14","author":"Y Sammour","year":"2021","unstructured":"Sammour, Y. et al. Incidence, predictors, and implications of permanent pacemaker requirement after transcatheter aortic valve replacement. JACC: Cardiovasc. Intervent. 14, 115\u2013134 (2021).","journal-title":"JACC: Cardiovasc. Intervent."},{"key":"1434_CR36","doi-asserted-by":"publisher","first-page":"e001164","DOI":"10.1136\/openhrt-2019-001164","volume":"7","author":"V Mauri","year":"2020","unstructured":"Mauri, V. et al. Impact of device landing zone calcification patterns on paravalvular regurgitation after transcatheter aortic valve replacement with different next-generation devices. Open Heart 7, e001164 (2020).","journal-title":"Open Heart"},{"key":"1434_CR37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.carrev.2021.07.010","volume":"35","author":"A Musallam","year":"2022","unstructured":"Musallam, A. et al. Impact of left ventricular outflow tract calcification on outcomes following transcatheter aortic valve replacement. Cardiovasc. Revasculariz. Med. 35, 1\u20137 (2022).","journal-title":"Cardiovasc. Revasculariz. Med."},{"key":"1434_CR38","doi-asserted-by":"publisher","first-page":"1061","DOI":"10.4244\/EIJ-D-21-00363","volume":"17","author":"TH J\u00f8rgensen","year":"2022","unstructured":"J\u00f8rgensen, T. H. et al. Membranous septum morphology and risk of conduction abnormalities after transcatheter aortic valve implantation. EuroIntervention 17, 1061\u20131069 (2022).","journal-title":"EuroIntervention"},{"key":"1434_CR39","doi-asserted-by":"publisher","first-page":"11","DOI":"10.3390\/jimaging8010011","volume":"8","author":"G Aoyama","year":"2022","unstructured":"Aoyama, G. et al. Automatic aortic valve cusps segmentation from CT images based on the cascading multiple deep neural networks. J. Imaging 8, 11 (2022).","journal-title":"J. Imaging"},{"key":"1434_CR40","doi-asserted-by":"publisher","first-page":"3591314","DOI":"10.1155\/2019\/3591314","volume":"2019","author":"P Astudillo","year":"2019","unstructured":"Astudillo, P. et al. Enabling automated device size selection for transcatheter aortic valve implantation. J. Intervent. Cardiol. 2019, 3591314 (2019).","journal-title":"J. Intervent. Cardiol."},{"key":"1434_CR41","doi-asserted-by":"publisher","first-page":"507","DOI":"10.1007\/s11548-021-02554-3","volume":"17","author":"N Kr\u00fcger","year":"2022","unstructured":"Kr\u00fcger, N. et al. Cascaded neural network-based CT image processing for aortic root analysis. Int. J. Comput. Assist. Radiol. Surg. 17, 507\u2013519 (2022).","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"1434_CR42","doi-asserted-by":"publisher","unstructured":"Hatamizadeh, A. et al. UNETR: Transformers for 3D Medical Image Segmentation. In: Winter Conference on Applications of Computer Vision (WACV). pp. 1748-1758 https:\/\/doi.org\/10.1109\/WACV51458.2022.00181 (2022).","DOI":"10.1109\/WACV51458.2022.00181"},{"key":"1434_CR43","doi-asserted-by":"publisher","unstructured":"Hatamizadeh, A. et al. Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Images. In: Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries. pp. 272-284 https:\/\/doi.org\/10.1007\/978-3-031-08999-2_22 (2022).","DOI":"10.1007\/978-3-031-08999-2_22"},{"key":"1434_CR44","doi-asserted-by":"publisher","first-page":"833","DOI":"10.21037\/jtd-23-1384","volume":"16","author":"M Renker","year":"2024","unstructured":"Renker, M. & Korosoglou, G. The role of computed tomography prior to transcatheter aortic valve implantation: preprocedural planning and simultaneous coronary artery assessment. J. Thorac. Dis. 16, 833\u2013838 (2024).","journal-title":"J. Thorac. Dis."},{"key":"1434_CR45","doi-asserted-by":"publisher","unstructured":"Pati, S. et al. The Federated Tumor Segmentation (FeTS) Challenge. https:\/\/doi.org\/10.5281\/zenodo.10990499 (2021).","DOI":"10.5281\/zenodo.10990499"},{"key":"1434_CR46","doi-asserted-by":"publisher","first-page":"2948","DOI":"10.1109\/TMI.2023.3270140","volume":"42","author":"X Xu","year":"2023","unstructured":"Xu, X., Deng, H. H., Gateno, J. & Yan, P. Federated multi-organ segmentation with inconsistent labels. IEEE Trans. Med. Imaging 42, 2948\u20132960 (2023).","journal-title":"IEEE Trans. Med. Imaging"},{"key":"1434_CR47","doi-asserted-by":"publisher","first-page":"101979","DOI":"10.1016\/j.media.2021.101979","volume":"70","author":"G Shia","year":"2020","unstructured":"Shia, G., Xiaoa, L., Chenb, Y., Zhoua, S. K. & Zhou, K. Marginal loss and exclusion loss for partially supervised multi-organ segmentation. Med. Image Anal. 70, 101979 (2020).","journal-title":"Med. Image Anal."},{"key":"1434_CR48","doi-asserted-by":"publisher","unstructured":"Liu, P., Sun, M., Zhou, S.K. Multi-site organ segmentation with federated partial supervision and site adaptation https:\/\/doi.org\/10.48550\/arXiv.2302.03911 (2023).","DOI":"10.48550\/arXiv.2302.03911"},{"key":"1434_CR49","doi-asserted-by":"publisher","unstructured":"Wang, P. et al. ConDistFL: Conditional distillation for federated learning from partially annotated data. In: Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2023 Workshops, pp. 311\u2013321 https:\/\/doi.org\/10.1007\/978-3-031-47401-9_30 (2023).","DOI":"10.1007\/978-3-031-47401-9_30"},{"key":"1434_CR50","doi-asserted-by":"publisher","unstructured":"Zhou, Y. et al. Prior-aware neural network for partially-supervised multi-organ segmentation. 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 10671\u201310680 https:\/\/doi.org\/10.1109\/ICCV.2019.01077 (2019).","DOI":"10.1109\/ICCV.2019.01077"},{"key":"1434_CR51","doi-asserted-by":"publisher","unstructured":"T\u00f6lle, M. et al. FUNAvg: Federated uncertainty weighted averaging for distributed datasets with diverse labels. In: Medical Image Computing and Computer-Assisted Intervention (MICCAI), pp. 405\u2013415 https:\/\/doi.org\/10.1007\/978-3-031-72117-5_38 (2024).","DOI":"10.1007\/978-3-031-72117-5_38"},{"key":"1434_CR52","doi-asserted-by":"publisher","unstructured":"Seo, H. et al. Federated knowledge distillation. In: Machine Learning and Wireless Communications https:\/\/doi.org\/10.1017\/9781108966559 (2022).","DOI":"10.1017\/9781108966559"},{"key":"1434_CR53","doi-asserted-by":"publisher","unstructured":"Mora, A., Tenison, I., Bellavista, P. & Rish, I. Knowledge distillation for federated learning: a practical guide. https:\/\/doi.org\/10.48550\/arXiv.2211.04742 (2022).","DOI":"10.48550\/arXiv.2211.04742"},{"key":"1434_CR54","doi-asserted-by":"publisher","unstructured":"Gong, X. et al. Ensemble attention distillation for privacy-preserving federated learning. In: International Conference on Computer Vision https:\/\/doi.org\/10.1109\/ICCV48922.2021.01480 (2021).","DOI":"10.1109\/ICCV48922.2021.01480"},{"key":"1434_CR55","doi-asserted-by":"publisher","unstructured":"Tung, F., Mori, G. Similarity-preserving knowledge distillation. In: Computer Vision and Pattern Recognition https:\/\/doi.org\/10.1109\/ICCV.2019.00145 (2019).","DOI":"10.1109\/ICCV.2019.00145"},{"key":"1434_CR56","doi-asserted-by":"publisher","unstructured":"Silva, S., Altmann, A., Gutman, B. & Lorenzi, M. Fed-BioMed: A General Open-Source Frontend Framework for Federated Learning in Healthcare. In: Domain Adaptation and Representation Transfer, and Distributed and Collaborative Learning, pp. 201\u2013210 https:\/\/doi.org\/10.1007\/978-3-030-60548-3_20 (2020).","DOI":"10.1007\/978-3-030-60548-3_20"},{"key":"1434_CR57","doi-asserted-by":"publisher","first-page":"1027","DOI":"10.1200\/CCI.20.00045","volume":"4","author":"J Scherer","year":"2020","unstructured":"Scherer, J. et al. Joint Imaging Platform for Federated Clinical Data Analytics. JCO Clin. Cancer Inform. 4, 1027\u20131038 (2020).","journal-title":"JCO Clin. Cancer Inform."},{"key":"1434_CR58","doi-asserted-by":"publisher","unstructured":"T\u00f6lle, M., Burger, L., Kelm, H. & Engelhardt, S. Towards unified multi-modal dataset creation for deep learning utilizing structured reports. In: German Workshop on Medical Image Computing https:\/\/doi.org\/10.1007\/978-3-658-44037-4 (2024).","DOI":"10.1007\/978-3-658-44037-4"},{"key":"1434_CR59","doi-asserted-by":"publisher","unstructured":"Usynin, D. et al. Adversarial interference and its mitigations in privacy-preserving collaborative machine learning. Nature Machine Intelligence https:\/\/doi.org\/10.1038\/s42256-021-00390-3 (2021).","DOI":"10.1038\/s42256-021-00390-3"},{"key":"1434_CR60","doi-asserted-by":"publisher","unstructured":"He, Z., Zhang, T. & Lee, R.B. Model inversion attacks against collaborative inference. In: 35th Annual Computer Security Applications Conference, pp. 148\u2013162 https:\/\/doi.org\/10.1145\/3359789.3359824 (2019).","DOI":"10.1145\/3359789.3359824"},{"key":"1434_CR61","unstructured":"Zhu, L., Liu, Z. & Han, S. Deep leakage from gradients. In: Advances in Neural Information Processing Systems, vol. 32 https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2019\/file\/60a6c4002cc7b29142def8871531281a-Paper.pdf (2019)."},{"key":"1434_CR62","doi-asserted-by":"publisher","unstructured":"He, Y., Rahimian, S., Schiele, B. & Fritz, M. Segmentations-Leak: Membership Inference Attacks and Defenses in Semantic Image Segmentation. In: European Conference on Computer Vision (ECCV), pp. 519-535 https:\/\/doi.org\/10.1007\/978-3-030-58592-1_31 (2020).","DOI":"10.1007\/978-3-030-58592-1_31"},{"key":"1434_CR63","doi-asserted-by":"crossref","unstructured":"Wang, J., Zhang, H. Bilateral adversarial training: Towards fast training of more robust models against adversarial attacks. In: International Conference on Computer Vision (ICCV) https:\/\/openaccess.thecvf.com\/content_ICCV_2019\/html\/Wang_Bilateral_Adversarial_Training_Towards_Fast_Training_of_More_Robust_Models_ICCV_2019_paper.html (2019).","DOI":"10.1109\/ICCV.2019.00673"},{"key":"1434_CR64","doi-asserted-by":"publisher","unstructured":"Chen, D., Yu, N., Zhang, Y. & Fritz, M. GAN-Leaks: A taxonomy of membership inference attacks against generative models. In: ACM SIGSAC Conference on Computer and Communications Security. pp. 343-362 https:\/\/doi.org\/10.1145\/3372297.3417238 (2020).","DOI":"10.1145\/3372297.3417238"},{"key":"1434_CR65","doi-asserted-by":"publisher","unstructured":"Ye, J. et al. Enhanced membership inference attacks against machine learning models. In: ACM SIGSAC Conference on Computer and Communications Security, pp. 3093\u20133106 https:\/\/doi.org\/10.1145\/3548606.3560675 (2022).","DOI":"10.1145\/3548606.3560675"},{"key":"1434_CR66","doi-asserted-by":"publisher","unstructured":"Papernot, N. et al. Scalable private learning with PATE. In: Proceedings of the International Conference on Learning Representations (ICLR) https:\/\/doi.org\/10.48550\/arXiv.1802.08908 (2018).","DOI":"10.48550\/arXiv.1802.08908"},{"key":"1434_CR67","doi-asserted-by":"publisher","unstructured":"T\u00f6lle, M., K\u00f6the, U., Andr\u00e9, F., Meder, B. & Engelhardt, S. Content-aware differential privacy with conditional invertible neural networks. In: Distributed, Collaborative, and Federated Learning, and Affordable AI and Healthcare for Resource Diverse Global Health, pp. 89\u201399 https:\/\/doi.org\/10.1007\/978-3-031-18523-6_9 (2022).","DOI":"10.1007\/978-3-031-18523-6_9"},{"key":"1434_CR68","doi-asserted-by":"publisher","unstructured":"Abadi, M. et al. Deep learning with differential privacy. In: Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security. pp. 308-318 https:\/\/doi.org\/10.1145\/2976749.2978318 (2016).","DOI":"10.1145\/2976749.2978318"},{"key":"1434_CR69","unstructured":"Gilad-Bachrach, R. et al. CryptoNets: Applying neural networks to encrypted data with high throughput and accuracy. In: Proceedings of The 33rd International Conference on Machine Learning. pp. 201-210 https:\/\/proceedings.mlr.press\/v48\/gilad-bachrach16.html (2016)."},{"key":"1434_CR70","first-page":"e230024","volume":"5","author":"J Wasserthal","year":"2023","unstructured":"Wasserthal, J. et al. TotalSegmentator: robust segmentation of 104 anatomical structures in CT images. Radiology: Artif. Intell. 5, e230024 (2023).","journal-title":"Radiology: Artif. Intell."},{"key":"1434_CR71","doi-asserted-by":"publisher","unstructured":"Wolf, I. et al. The medical imaging interaction toolkit (mitk): A toolkit facilitating the creation of interactive software by extending vtk and itk. In: Medical Imaging 2004: Visualization, Image-Guided Procedures, and Display, vol. 5367, pp. 533\u2013544 https:\/\/doi.org\/10.1117\/12.535112 (2004).","DOI":"10.1117\/12.535112"},{"key":"1434_CR72","doi-asserted-by":"publisher","unstructured":"\u00c7i\u00e7ek, \u00d6., Abdulkadir, A., Lienkamp, S.S., Brox, T. & Ronneberger, O. 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation. In: Medical Image Computing and Computer-Assisted Intervention (MICCAI), vol. 9901, pp. 424\u2013432 https:\/\/doi.org\/10.1007\/978-3-319-46723-8_49 (2016).","DOI":"10.1007\/978-3-319-46723-8_49"},{"key":"1434_CR73","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). pp. 770-778 https:\/\/doi.org\/10.1109\/CVPR.2016.90 (2016).","DOI":"10.1109\/CVPR.2016.90"},{"key":"1434_CR74","unstructured":"Loshchilov, I., Hutter, F. Decoupled weight decay regularization. In: International Conference on Learning Representations https:\/\/doi.org\/arxiv:1711.05101 (2019)."},{"key":"1434_CR75","doi-asserted-by":"publisher","unstructured":"Sudre, C.H. et al. Generalised Dice Overlap as a Deep Learning Loss Function for Highly Unbalanced Segmentations. Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, pp. 240\u2013248 https:\/\/doi.org\/10.1007\/978-3-319-67558-9_28 (2017).","DOI":"10.1007\/978-3-319-67558-9_28"},{"key":"1434_CR76","doi-asserted-by":"publisher","unstructured":"McMahan, H.B., Moore, E., Ramage, D., Hampson, S. & y Arcas, B. A. Communication-efficient learning of deep networks from decentralized data. In: AISTATS https:\/\/doi.org\/10.48550\/arXiv.1602.05629 (2017).","DOI":"10.48550\/arXiv.1602.05629"},{"key":"1434_CR77","unstructured":"Karimireddy, et al. SCAFFOLD: Stochastic controlled averaging for federated learning. In: Proceedings of the 37th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 119, pp. 5132\u20135143 (2020)."},{"key":"1434_CR78","doi-asserted-by":"publisher","unstructured":"Li, T. et al. Federated optimization in heterogeneous networks. In: MLSys https:\/\/doi.org\/10.48550\/arXiv.1812.06127 (2020).","DOI":"10.48550\/arXiv.1812.06127"},{"key":"1434_CR79","doi-asserted-by":"publisher","unstructured":"Paszke, A. et al. PyTorch: An Imperative Style, High-Performance Deep Learning Library. In: Advances in Neural Information Processing Systems, vol. 32 https:\/\/doi.org\/10.5555\/3454287.3455008 (2019).","DOI":"10.5555\/3454287.3455008"},{"key":"1434_CR80","doi-asserted-by":"publisher","unstructured":"Cardoso, M.J. et al. MONAI: An open-source framework for deep learning in healthcare https:\/\/doi.org\/10.48550\/arXiv.2211.02701 (2022).","DOI":"10.48550\/arXiv.2211.02701"},{"key":"1434_CR81","doi-asserted-by":"publisher","first-page":"106236","DOI":"10.1016\/j.cmpb.2021.106236","volume":"208","author":"F P\u00e9rez-Garc\u00eda","year":"2021","unstructured":"P\u00e9rez-Garc\u00eda, F., Sparks, R. & Ourselin, S. TorchIO: A Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning. Comput. Methods Prog. Biomed. 208, 106236 (2021).","journal-title":"Comput. Methods Prog. Biomed."},{"key":"1434_CR82","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v086.i08","volume":"86","author":"R Beare","year":"2018","unstructured":"Beare, R., Lowekamp, B. & Yaniv, Z. Image Segmentation, Registration and Characterization in R with SimpleITK. J. Stat. Softw. 86, 1\u201335 (2018).","journal-title":"J. Stat. Softw."}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01434-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01434-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01434-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T07:07:17Z","timestamp":1738825637000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01434-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,6]]},"references-count":82,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["1434"],"URL":"https:\/\/doi.org\/10.1038\/s41746-025-01434-3","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,6]]},"assertion":[{"value":"7 August 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 January 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 February 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"NF reports speaker honoraria, presentations or advisory board consultations from AstraZeneca, Bayer AG, Boehringer Ingelheim, Novartis, Pfizer, Daiichi Sankyo Deutschland. TS reports research, educational, or travel grants and honoraria for lectures or advisory board consultations from Abbott Vascular, AstraZeneca, BoehringerIngelheim, Bristol Myers Squibb, Corvia, Cytokinetics, Edwards Life Sciences, Medtronic, Myocardia, Novartis, Pfizer, Teleflex. AM reports consulting or lecturing fees from Medtronic, Bayer, Pfizer. CS reports speaker honorarium from AstraZeneca. SE reports speaker honorarium from Boehringer Ingelheim. None are related to the content of the manuscript. The authors declare no conflicts of interest.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"88"}}