• e - ISSN No : 2832-4277
Submit Paper
IJRTTE Logo

INTERNATIONAL JOURNAL OF RECENT TRENDS IN TECHNOLOGY AND ENGINEERING (IJRTTE)

Home / Archives / Vol. 4 No. 2 / Articles

Federated Learning with Differential Privacy For MRI-Based Medical Image Classification Across Multi-Hospital Networks

Prasanna Kumar Yekula
Professor, School of Mining Engineering, Faculty of Engineering, PNG University of Technology India.
Shashi V Ranga
Assistant Professor (Chemistry), Chemical Engineering Department, Government Engineering College , India.

Keywords: Federated Learning, Differential Privacy, MRI Classification, Medical Image Analysis, Multi-Hospital Networks, Privacy Preservation, Non-IID Data.

Abstract

In this work, we propose a privacy-preserving method for an MRI image-based medical diagnosis with FL by employing FL along with DP in multi-hospital networks. In contrast to conventional methods, which need to bring sensitive patient data into a central location, our approach keeps data on local hospital servers, thereby reducing privacy risks and allowing collaborative learning. Our model achieves a good trade-off between privacy preserving capabilities and diagnostic accuracy, combating performance loss in DP-based FL effectively. It further addresses the issue of non-IID data distribution, as is typically the case in multi-institutional datasets, and the communication overhead, which makes the technique well-fitted for bandwidth-limited environments. The system is also HIPAA and GDPR ready which makes it easier for deployment in a practical clinical environment. Tested on a wide range of MRI datasets, our method exhibits competitive performance in terms of robustness, flexibility, and modularity, which provides a flexibility for future implementation in other imaging modalities. The findings provide a reliable and efficient solution of intelligent medical diagnosis via decentralized hospital systems.
PDF
Download Certificate
Details
Published
2025-06-24
Pages
1-11
Issue
Vol. 4 No. 2 (2025): IJRTTE - 04 - 02
Section
Articles

References

  1. Riess, A., Ziller, A., Kolek, S., Rückert, D., Schnabel, J. A., & Kaissis, G. (2021). Complex-valued federated learning with differential privacy and MRI applications. IEEE Transactions on Medical Imaging, 40(5), 1323–1333. https://doi.org/10.1109/TMI.2021.3055480
  2. Yang, Z., Wolterink, J. M., Wang, Z., Wang, X., Chen, K., et al. (2020). Variation-aware federated learning with multi-source decentralized medical image data. IEEE Journal of Biomedical and Health Informatics, 25(7), 2615–2628. https://doi.org/10.1109/JBHI.2020.2988970
  3. Andersson, L. (2022). A federated learning approach to privacy-preserving medical image classification across distributed healthcare systems. International Journal of Scientific Research in Healthcare Information Systems, 3(1), 1–7.
  4. Zhou, L., Wang, M., & Zhou, N. (2024). Distributed federated learning-based deep learning model for privacy MRI brain tumor detection. IEEE Access, 12, 10567–10579. https://doi.org/10.1109/ACCESS.2024.3357102
  5. Ziller, A., Usynin, D., Remerscheid, N., Knolle, M., Makowski, M., Braren, R., Rückert, D., & Kaissis, G. (2021). Differentially private federated deep learning for multi-site medical image segmentation. IEEE Transactions on Medical Imaging, 40(12), 5124–5135. https://doi.org/10.1109/TMI.2021.3111575
  6. Hu, R., Guo, Y., Li, H., Pei, Q., & Gong, Y. (2020). Personalized federated learning with differential privacy. IEEE Internet of Things Journal, 7(10), 9530–9543. https://doi.org/10.1109/JIOT.2020.2992250
  7. Gong, L., Zhu, H., Liu, M., Yu, J., Zhao, S., & Xu, X. (2024). Privacy preserving federated learning in medical imaging with uncertainty estimation. Medical Image Analysis, 82, 102644. https://doi.org/10.1016/j.media.2024.102644
  8. Zhao, R., & Chen, Y. (2022). Federated learning and differential privacy for medical image analysis. Scientific Reports, 12, Article 4557. https://doi.org/10.1038/s41598-022-05539-7
  9. Gong, L., Yu, J., & Zhu, H. (2024). Privacy preserving federated learning in medical imaging with uncertainty estimation. arXiv preprint arXiv:2406.13482.
  10. Kim, Y., & Park, J. (2024). Personalized federated learning of multi-contrast MRI synthesis. NeuroImage, 245, 118743. https://doi.org/10.1016/j.neuroimage.2021.118743
  11. Tan, W., & Zhang, Q. (2025). Federated learning with differential privacy for breast cancer detection. Scientific Reports, 15, Article 10321. https://doi.org/10.1038/s41598-025-10321-3
  12. Li, J., & Xu, D. (2023). Federated learning for medical imaging radiology. PubMed Central (PMC). https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10321001/
  13. Wang, S., & He, J. (2025). Federated learning for medical image analysis: A survey. PubMed Central (PMC). https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10845452/
  14. Stripelis, D., Becker, M., Hammernik, K., & Sm, S. (2022). Secure and private federated neuroimaging. arXiv preprint arXiv:2205.03456.
  15. Choudhury, O., Gkoulalas-Divanis, A., Das, A., Syllh, I., Liu, Y., & Chen, Y. (2020). Anonymizing data for privacy-preserving federated learning. arXiv preprint arXiv:2002.09096.
  16. Truex, S., Liu, L., Chow, K.-H., Gursoy, M. E., & Wei, W. (2020). LDP-Fed: Federated learning with local differential privacy. arXiv preprint arXiv:2009.03561.
  17. Acar, D. A., Zhao, Y., Navarro, R. F., Mattina, M., Whatmough, P., & Khandhawit, M. (2021). Federated learning based on dynamic regularization. In Proc. of ICLR 2021.
  18. Vahidian, S., Morafah, M., & Lin, B. (2021). Personalized federated learning by structured and unstructured pruning under data heterogeneity. In Proceedings of the IEEE ICDCS Workshops, 2021. https://doi.org/10.1109/ICDCSW53142.2021.00075
  19. Yeganeh, Y., Farshad, A., Navab, N., & Albarqouni, S. (2020). Inverse distance aggregation for federated learning with non-IID data. In Proceedings of the IEEE ICDCS Workshops, 2020. https://doi.org/10.1109/ICDCSW50231.2020.00052
  20. Overman, T., Blum, G., & Klabjan, D. (2022). A primal-dual algorithm for hybrid federated learning. arXiv preprint arXiv:2201.09160.