PRIVACY-PRESERVING FEDERATED DEEP LEARNING FOR ROBUST MEDICAL IMAGE SEGMENTATION ACROSS MULTI-INSTITUTIONAL CLINICAL DATASETS
Article Sidebar
Main Article Content
Abstract
Early diagnosis and therapy planning in brain tumor treatment depend heavily on medical image segmentation. However, Traditional DNNs require data from medical practices to be collected in a central location, raising significant privacy concerns about patient data leakage, security risks, and institutional data-sharing limits. This study proposes a robust, multi-institutional medical image segmentation system that uses federated deep learning while maintaining the privacy of clinical data. The proposed system combines a U-Net-based convolutional neural network with a federated learning architecture. The goal is to obtain multi-institution segmentation models without directly sharing healthcare institutions' original MRI data. To enhance data protection, differential privacy measures, such as gradient clipping and the injection of Gaussian noise, were applied during model optimization and the exchange of model parameters. The brain tumor MRI dataset from BraTS 2020 was used for experiments and distributed across four simulated healthcare clients to mimic diverse institutional environments. The experimental implementation was carried out using Python and PyTorch on Google Colaboratory. The segmentation results were evaluated with Dice Similarity Coefficient (DSC) and Intersection over Union (IoU). The Dice and IoU values were 0.3628 and 0.2464 for the centralized U-Net, and 0.3295 and 0.2176 for the federated U-Net, respectively, indicating that the federated U-Net achieved the highest segmentation performance while maintaining effective collaborative learning and privacy preservation. While the DP-Federated model offered stronger privacy protection, segmentation accuracy was compromised, with lower Dice and IoU scores of 0.0408 and 0.0211, respectively, due to noise perturbation. The results suggest a federated learning model with suitable segmentation capabilities and a significant reduction in exposure to sensitive medical data.
Downloads
Article Details
Issue
Section
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
How to Cite
References
1. Abueed, O., Wang, Y., & Khasawneh, M. (2025). A Systematic Review of U‐Net Optimizations: Advancing Tumour Segmentation in Medical Imaging. IET Image Processing, 19(1), e70203. https://doi.org/10.1049/ipr2.70203 DOI: https://doi.org/10.1049/ipr2.70203
2. Aggarwal, K., Manso Jimeno, M., Ravi, K. S., Gonzalez, G., & Geethanath, S. (2023). Developing and deploying deep learning models in brain magnetic resonance imaging: a review. NMR in Biomedicine, 36(12), e5014. https://arxiv.org/pdf/2301.01241 DOI: https://doi.org/10.1002/nbm.5014
3. Albalawi, E., TR, M., Thakur, A., Kumar, V. V., Gupta, M., Khan, S. B., & Almusharraf, A. (2024). Integrated approach of federated learning with transfer learning for classification and diagnosis of brain tumor. BMC Medical Imaging, 24(1), 110. https://doi.org/10.1186/s12880-024-01261-0 DOI: https://doi.org/10.1186/s12880-024-01261-0
4. Altschuler, J., & Talwar, K. (2022). Privacy of noisy stochastic gradient descent: More iterations without more privacy loss. Advances in Neural Information Processing Systems, 35, 3788- 3800. https://proceedings.neurips.cc/paper_files/paper/2022/file/18561617ca0b4ffa293166b3186e04b0-Paper-Conference.pdf DOI: https://doi.org/10.52202/068431-0274
5. Andersen, E. (2022). Imagedata: A Python library to handle medical image data in NumPy array subclass Series. Journal of Open Source Software, 7(73), 4133. https://doi.org/10.21105/joss.04133 DOI: https://doi.org/10.21105/joss.04133
6. Azad, R., Aghdam, E. K., Rauland, A., Jia, Y., Avval, A. H., Bozorgpour, A., ... & Merhof, D. (2024). Medical image segmentation review: The success of U-Net. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(12), 10076-10095. https://doi.org/10.1109/TPAMI.2024.3435571 DOI: https://doi.org/10.1109/TPAMI.2024.3435571
7. Barbaria, S., Jemai, A., Ceylan, H. İ., Muntean, R. I., Dergaa, I., & Boussi Rahmouni, H. (2025, October). Advancing compliance with HIPAA and GDPR in healthcare: a blockchain-based strategy for secure data exchange in clinical research involving private health information. In Healthcare (Vol. 13, No. 20, p. 2594). MDPI. https://doi.org/10.3390/healthcare13202594 DOI: https://doi.org/10.3390/healthcare13202594
8. Cai, L., Li, Y., Fan, X., Song, K., Wang, R., & Lei, W. (2024). Low-contrast-enhanced contrastive learning for semi-supervised endoscopic image segmentation. arXiv preprint arXiv:2412.02314. https://arxiv.org/pdf/2412.02314
9. Chowdhury, T. K., & Kudapa, S. P. (2024). Federated Learning Models for Privacy-Preserving Data Sharing And Secure Analytics In Healthcare Industry. International Journal of Business and Economics Insights, 4(4), 91-133.https://doi.org/10.63125/c2dzn006 DOI: https://doi.org/10.63125/c2dzn006
10. Darzidehkalani, E., Ghasemi-Rad, M., & Van Ooijen, P. M. A. (2022). Federated learning in medical imaging: part I: toward multicentral health care ecosystems. Journal of the american college of radiology, 19(8), 969-974. https://doi.org/10.1016/j.jacr.2022.03.015 DOI: https://doi.org/10.1016/j.jacr.2022.03.015
11. Fareed, S., Yi, D., Hussain, B., Uddin, S., Arif, A., & Tajoor, A. N. (2025). Fedsegnet: A federated learning framework for 3d medical image segmentation. International Journal of Ethical AI Application, 1(2), 30-46. https://doi.org/10.64229/ttnjjp90 DOI: https://doi.org/10.64229/ttnjjp90
12. Gu, X., Sabrina, F., Fan, Z., & Sohail, S. (2023). A review of privacy enhancement methods for federated learning in healthcare systems. International Journal of Environmental Research and Public Health, 20(15), 6539. https://doi.org/10.3390/ijerph20156539 DOI: https://doi.org/10.3390/ijerph20156539
13. Hussain, D., Al-Masni, M. A., Aslam, M., Sadeghi-Niaraki, A., Hussain, J., Gu, Y. H., & Naqvi, R. A. (2024). Revolutionizing tumor detection and classification in multimodality imaging based on deep learning approaches: Methods, applications, and limitations. Journal of X-Ray Science and Technology, 32(4), 857-911. https://doi.org/10.3233/XST-230429 DOI: https://doi.org/10.3233/XST-230429
14. Hussain, S., Mubeen, I., Ullah, N., Shah, S. S. U. D., Khan, B. A., Zahoor, M., ... & Sultan, M. A. (2022). Modern diagnostic imaging technique applications and risk factors in the medical field: a review. BioMed research international, 2022(1), 5164970. https://doi.org/10.1155/2022/5164970 DOI: https://doi.org/10.1155/2022/5164970
15. Jiangtao, W., Ruhaiyem, N. I. R., & Panpan, F. (2025). A comprehensive review of U‐Net and its variants: advances and applications in medical image segmentation. IET Image Processing, 19(1), e70019. https://doi.org/10.1049/ipr2.70019 DOI: https://doi.org/10.1049/ipr2.70019
16. Kaggle.com (2020). Brain Tumor Segmentation(BraTS2020). (2020). Retrieved from www.kaggle.com website: https://www.kaggle.com/datasets/awsaf49/brats2020-training-data
17. Khan, A., Rauf, Z., Khan, A. R., Rathore, S., Khan, S. H., Shah, N., ... & Gwak, J. (2025). A recent survey of vision transformers for medical image segmentation. IEEE Access. https://doi.org/10.1109/ACCESS.2025.3618215 DOI: https://doi.org/10.1109/ACCESS.2025.3618215
18. Khan, N., Nisar, S., Khan, M. A., Rehman, Y. A. U., Noor, F., & Barb, G. (2025). Optimizing federated learning with aggregation strategies: A comprehensive survey. IEEE Open Journal of the Computer Society. https://doi.org/10.1109/OJCS.2025.3590102 DOI: https://doi.org/10.1109/OJCS.2025.3590102
19. Mollakuqe, E., Parduzi, A., Rexhepi, S., Dimitrova, V., Jakupi, S., Muharremi, R., ... & Qarkaxhija, J. (2024). Applications of homomorphic encryption in secure computation. Open Research Europe, 4, 10-12688. https://dx.doi.org/10.12688/openreseurope.18052.1 DOI: https://doi.org/10.12688/openreseurope.18052.1
20. Myakala, P. K., Jonnalagadda, A. K., & Bura, C. (2024). Federated learning and data privacy: A review of challenges and opportunities. International Journal of Research Publication and Reviews, 5(12), 10-55248. https://doi.org/10.55248/gengpi.5.1224.3512 DOI: https://doi.org/10.55248/gengpi.5.1224.3512
21. Nazir, S., & Kaleem, M. (2023). Federated learning for medical image analysis with deep neural networks. Diagnostics, 13(9), 1532. https://doi.org/10.3390/diagnostics13091532 DOI: https://doi.org/10.3390/diagnostics13091532
22. Nemati, A. A., Sadreddini, M. H., & Mahdizade, M. (2025). Comparative Federated Algorithms for Solving Non-IID Data Challenges. Transactions on Soft Computing, 1(1), 27-35. https://doi.org/10.48314/tsc.v1i1.35
23. Nworu, C. C., Ekpenyong, J. E., Chisimkwuo, J., Okwara, G., Agwu, O. J., & Onyeukwu, N. C. (2022). the effects of modified ReLU activation functions in image classification. J Biomed. Eng. Med. Dev., 7, 237. DOI: 10.35248/ 2475 7586.22.07.237
24. Salman, H. A., & Kalakech, A. (2024). Image enhancement using convolutional neural networks. Babylonian Journal of Machine Learning, 2024, 30-47. https://doi.org/10.58496/BJML/2024/003 DOI: https://doi.org/10.58496/BJML/2024/003
25. Sana, T. Z., Abdulla, S., Das, A., Nag, A., Hassan, M. M., Fiza, Z. Z., ... & Kabir, S. R. R. (2025). Advancing federated learning: A systematic literature review of methods, challenges, and applications. IEEE Access. https://doi.org/10.1109/ACCESS.2025.3605165 DOI: https://doi.org/10.1109/ACCESS.2025.3605165
26. Sistaninejhad, B., Rasi, H., & Nayeri, P. (2023). A review paper about deep learning for medical image analysis. Computational and Mathematical Methods in Medicine, 2023(1), 7091301. https://doi.org/10.1155/2023/7091301 DOI: https://doi.org/10.1155/2023/7091301
27. Ullah, F., Nadeem, M., Abrar, M., Amin, F., Salam, A., & Khan, S. (2023). Enhancing brain tumor segmentation accuracy through scalable federated learning with advanced data privacy and security measures. Mathematics, 11(19), 4189.https://doi.org/10.3390/math11194189 DOI: https://doi.org/10.3390/math11194189
28. Vashistha, P., Vashistha, D., Saxena, V. P., Kumhar, M., Bhatia, J., Gupta, R., ... & Tanwar, S. (2025). Federated Averaging Optimization for Efficient Skin Cancer Image Analysis. Procedia Computer Science, 258, 3794-3803. DOI: 10.1016/j.procs.2025.04.634 DOI: https://doi.org/10.1016/j.procs.2025.04.634
29. Veiga‐Canuto, D., L. Cerdá Alberich, C. Sangüesa Nebot, Martínez, B., Pötschger, U., Michela Gabelloni, …Martí-Bonmatí, L. (2022). Comparative Multicentric Evaluation of Inter-Observer Variability in Manual and Automatic Segmentation of Neuroblastic Tumors in Magnetic Resonance Images. Cancers, 14(15), 3648–3648. https://doi.org/10.3390/cancers14153648 DOI: https://doi.org/10.3390/cancers14153648
30. Xiao, H., Wan, J., & Devadas, S. (2023, November). Geometry of sensitivity: Twice sampling and hybrid clipping in differential privacy with optimal Gaussian noise and application to deep learning. In Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security (pp. 2636-2650). https://doi.org/10.1145/3576915.3623142 DOI: https://doi.org/10.1145/3576915.3623142
31. Xin, W., Jiaqian, L., Xueshuang, D., Haoji, Z., & Lianshan, S. (2024). A survey of differential privacy techniques for federated learning. IEEE Access, 13, 6539-6555. Digital Object Identifier 10.1109/ACCESS.2024.3523909 DOI: https://doi.org/10.1109/ACCESS.2024.3523909
32. Yang, Z., Yan, X., Chen, G., & Tian, X. (2025). Adaptive Differential Privacy for Satellite Image Recognition with Convergence-Guaranteed Optimization. Electronics, 14(18), 3680. https://doi.org/10.3390/electronics14183680 DOI: https://doi.org/10.3390/electronics14183680
33. Zhang, K., Wang, J., Wang, W., Zeng, T., Li, P., Wang, X., & Zhang, T. (2025). Federated learning with heterogeneous data and models based on global decision boundary distillation. Journal of King Saud University - Computer and Information Sciences, 37(5). https://doi.org/10.1007/s44443-025-00097-0 https://doi.org/10.1007/s44443-025-00097-0 DOI: https://doi.org/10.1007/s44443-025-00097-0
34. Zholshybek, N., & Bastarbekova, L. (2025). Harmonizing multicenter quantitative imaging data: sources of variability, statistical solutions, and practical workflows in CT and MRI. Exploration of Digital Health Technologies, 4. DOI: https://doi.org/10.37349/edht.2026.101185