Logo PTI Logo FedCSIS

Position Papers of the 21st Conference on Computer Science and Intelligence Systems

Annals of Computer Science and Information Systems, Volume 48

Why Federated, Privacy-Preserving Data Spaces are the Future of Digital Pathology

,

DOI: http://dx.doi.org/10.15439/2026F8271

Citation: Mohammadreza Azimi,

Full text

Abstract. The clinical and research potential of histopatholog- ical data remains largely untapped due to its sensitive nature and the logistical barriers to multi-institutional sharing. Centralized data aggregation, the dominant paradigm for training robust AI models, conflicts directly with patient privacy regulations, hospital data governance policies, and the risks of exposing raw whole slide images. Federated data spaces are necessary for sharing and analyzing histopathological samples because they enable collaborative data use while ensuring that sensitive patient information remains protected behind local firewalls. This archi- tecture overcomes current limitations such as strict regulatory and privacy constraints, challenges with data heterogeneity, and risks associated with transferring raw data, thereby supporting scalable, multi-institutional analysis through advanced privacy- preserving techniques. This review examines why federated architectures, combined with privacy-preserving techniques such as differential privacy and secure aggregation, are essential for unlocking the full poten- tial of histopathological data for rare disease research, unbiased AI development, and clinical discovery without compromising patient confidentiality.

References

  1. M. Hammad and S. Ahmad, “Future Directions for AI in Medical Image Analysis,” in AI for Medical Image Analysis: Reconciling Innovation and Ethical Considerations. Cham, Switzerland: Springer Nature Switzerland, 2026, pp. 233–264, https://doi.org/10.1007/ 978-3-032-02963-8_9.
  2. M. Soliman et al., “Secondary use of health data: Applications, models, algorithms, and ethical considerations,” AI and Ethics, vol. 6, no. 2, article 165, 2026, https://doi.org/10.1007/s43681-026-01017-2.
  3. E. Witt, “The digital looking glass: Ethical aspects of large data collections,” Bundesgesundheitsblatt–Gesundheitsforschung– Gesundheitsschutz, vol. 58, no. 8, pp. 853–858, 2015, https://doi.org/10.1007/s00103-015-2187-5.
  4. J. Casaletto et al., “Federated analysis for privacy-preserving data sharing: A technical and legal primer,” Annual Review of Genomics and Human Genetics, vol. 24, no. 1, pp. 347–368, 2023, https://doi.org/10.1146/annurev-genom-110122-084756.
  5. E. S. Dove, G. T. Laurie, and B. M. Knoppers, “Data sharing and privacy,” in Genomic and Precision Medicine. Academic Press, 2017, pp. 143–160, https://doi.org/10.1016/b978-0-12-800681-8.00010-4.
  6. B. Malin, D. Karp, and R. H. Scheuermann, “Technical and policy approaches to balancing patient privacy and data sharing in clinical and translational research,” Journal of Investigative Medicine, vol. 58, no. 1, pp. 11–18, 2010, https://doi.org/10.2310/jim.0b013e3181c9b2ea.
  7. S. Yazijy, R. Schölly, and P. Kellmeyer, “Towards a toolbox for privacypreserving computation on health data,” Studies in Health Technology and Informatics, vol. 290, pp. 234–237, 2022, https://doi.org/10. 3233/shti220069.
  8. P. R. Silva, J. Vinagre, and J. Gama, “Towards federated learning: An overview of methods and applications,” Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, vol. 13, no. 2, article e1486, 2023, https://doi.org/10.1002/widm.1486.
  9. Y. Zhang et al., “FedSODA: Federated cross-assessment and dynamic aggregation for histopathology segmentation,” in Proc. IEEE Int. Conf. Acoustics, Speech and Signal Processing (ICASSP), Seoul, Republic of Korea, 2024, pp. 1606–1610, https://doi.org/10.1109/ICASSP48485. 2024.10447367.
  10. A. K. Conduah, S. Ofoe, and D. Siaw-Marfo, “Data privacy in healthcare: Global challenges and solutions,” Digital health, vol. 11, 2025. https://doi.org/10.1177/20552076251343959.
  11. A. Jimenez-Pastor et al., “Data harmonization and challenges toward the generation of repositories: Sharing practices and approaches,” in Trustworthy AI in Cancer Imaging Research. Cham, Switzerland: Springer Nature Switzerland, 2025, pp. 121–142, https://doi.org/10.1007/ 978-3-031-89963-8_6.
  12. P. N. Schofield, J. M. Ward, and J. P. Sundberg, “Show and tell: Disclosure and data sharing in experimental pathology,” Disease Models & Mechanisms, vol. 9, no. 6, pp. 601–605, 2016, https://doi.org/10. 1242/dmm.026054.
  13. S. C. Koganti et al., “Task-ready PanNuke and NuCLS datasets: Reorganization, synthetic data generation, and experimental evaluation,” IEEE Access, vol. 13, pp. 137986–138005, 2025, https://doi.org/10.1109/ access.2025.3589477.
  14. S. S. Sandhu et al., “Medical imaging applications of federated learning,” Diagnostics, vol. 13, no. 19, article 3140, 2023, https://doi.org/10. 3390/diagnostics13193140.
  15. N. Appavu, “Examining federated learning architecture’s capability to protect data privacy during the training of collaborative healthcare models,” in Proc. 9th Int. Conf. Inventive Systems and Control (ICISC), 2025, pp. 1–6, https://doi.org/10.1109/icisc65841.2025.11187468.
  16. M. Singh et al., “Advancing AI integration in healthcare using federated learning: Trends and challenges in federated learning for AI-enabled healthcare,” in Enabling Collaborative Health Intelligence With Federated Learning. Boca Raton, FL, USA: CRC Press, 2026, pp. 29–56. https://doi.org/10.4018/979-8-3373-3306-9.ch002.
  17. S. M. Hosseini et al., “Cluster-based secure multi-party computation in federated learning for histopathology images,” in Distributed, Collaborative, and Federated Learning, Lecture Notes in Computer Science. Cham, Switzerland: Springer Nature Switzerland, 2022, pp. 150–161, https://doi.org/10.1007/978-3-031-18523-6_11.
  18. A. V. Sri et al., “Privacy-preserving federated learning for retinal disease diagnosis using Paillier homomorphic encryption with multiple encryption keys,” IEEE Access, early access, 2026, https://doi.org/ 10.1109/access.2026.3664444.
  19. H. Wang et al., “MVFL: Verifiable privacy-preserving federated learning using multi-key homomorphic encryption,” The Journal of Supercomputing, vol. 81, no. 8, article 915, 2025, https://doi.org/10.1007/ s11227-025-07419-z.
  20. I. Walskaar, M. C. Tran, and F. O. Catak, “A practical implementation of medical privacy-preserving federated learning using multi-key homomorphic encryption and Flower framework,” Cryptography, vol. 7, no. 4, article 48, 2023, https://doi.org/10.3390/cryptography7040048.
  21. S. Shukla et al., “Federated learning with differential privacy for breast cancer diagnosis enabling secure data sharing and model integrity,” Scientific Reports, vol. 15, no. 1, article 13061, 2025, https://doi.org/10.1038/s41598-025-95858-2.
  22. A. Najdi et al., “Technical framework to ensure data subject’s rights in GDPR: A conceptual design,” in Proc. Australasian Computer Science Week (ACSW), 2025, pp. 40–47, https://doi.org/10.1145/3727166. 3727190.
  23. A. Mitrovska et al., “Federated learning governance using Eclipse Dataspace Components connectors,” in Proc. IEEE Int. Conf. Big Data, 2024, pp. 6860–6867, https://doi.org/10.1109/bigdata62323.2024. 10826122.
  24. M. Polato, “FLuke: Federated Learning Utility frameworK for experimentation and research,” Future Generation Computer Systems, vol. 167, article 108241, 2025, https://doi.org/10.1016/j.future.2025.108241.
  25. B. Lutnick et al., “A cloud-based tool for federated segmentation of whole-slide images,” in Medical Imaging 2022: Digital and Computational Pathology, vol. 12039, SPIE, 2022, article 120390B, https://doi.org/10.1117/12.2613502.
  26. M. Y. Lu et al., “Federated learning for computational pathology on gigapixel whole-slide images,” Medical Image Analysis, vol. 76, article 102298, 2022, https://doi.org/10.1016/j.media.2021.102298.
  27. B. Lutnick et al., “A tool for federated training of segmentation models on whole-slide images,” Journal of Pathology Informatics, vol. 13, article 100101, 2022, https://doi.org/10.1016/j.jpi.2022.100101.
  28. P. Yao et al., “HEGD-FL: A privacy-preserving decentralized federated learning framework based on homomorphic encryption,” in Proc. IEEE Int. Symp. Parallel and Distributed Processing with Applications (ISPA), 2024, pp. 1305–1312, https://doi.org/10.1109/ispa63168. 2024.00012.
  29. H. Park and J. Lee, “LMSA: A lightweight multi-key secure aggregation framework for privacy-preserving healthcare AIoT,” Computer Modeling in Engineering & Sciences, vol. 143, no. 1, article 827, 2025, https://doi.org/10.32604/cmes.2025.061178.
  30. D. K. Murala et al., “MedShieldFL: A privacy-preserving hybrid federated learning framework for intelligent healthcare systems,” Scientific Reports, vol. 15, no. 1, article 43144, 2025, https://doi.org/10.1038/ s41598-025-27303-3.
  31. Y. Lin et al., “Federated learning with hyper-network: A case study on whole-slide image analysis,” Scientific Reports, vol. 13, no. 1, article 1724, 2023, https://doi.org/10.1038/s41598-023-28974-6.
  32. Y. Feng et al., “Dual-dimensional optimization framework: Feature fusion for cross-modal medical image segmentation,” in Proc. Int. Conf. Computer Engineering and Networks, Singapore: Springer Nature Singapore, 2025, pp. 405–416, https://doi.org/10.1007/ 978-981-95-3320-6_25.
  33. J. Wicaksana et al., “FedMix: Mixed supervised federated learning for medical image segmentation,” IEEE Transactions on Medical Imaging, vol. 42, no. 7, pp. 1955–1968, 2023, https://doi.org/10.1109/tmi. 2022.3233405.
  34. F. Zhu et al., “Model-level attention and batch-instance style normalization for federated learning on medical image segmentation,” Information Fusion, vol. 107, article 102348, 2024, https://doi.org/10.1016/j. inffus.2024.102348.
  35. L. Wang et al., “Discovering maximum frequency consensus: Lightweight federated learning for medical image segmentation,” in Proc. 33rd ACM Int. Conf. Multimedia (MM), 2025, pp. 5117–5126, https://doi.org/10.1145/3746027.3755528.
  36. T. Deng et al., “FedDBL: Communication- and data-efficient federated deep-broad learning for histopathological tissue classification,” IEEE Transactions on Cybernetics, vol. 54, no. 12, pp. 7851–7864, 2024, https://doi.org/10.1109/tcyb.2024.3403927.
  37. S. Shukla et al., “Federated learning in computational pathology: Classification of tall cell patterns in papillary thyroid carcinoma,” in Medical Imaging 2024: Digital and Computational Pathology, vol. 12933, SPIE, 2024, article 129330Q, https://doi.org/10.1117/12.3006890.
  38. Y. Shen et al., “A federated learning system for histopathology image analysis with an orchestral stain-normalization GAN,” IEEE Transactions on Medical Imaging, vol. 42, no. 7, pp. 1969–1981, 2023, https://doi.org/10.1109/tmi.2022.3221724.
  39. Y. Wang et al., “Federated deep multiple instance learning for histopathological whole-slide image classification,” Biomedical Signal Processing and Control, vol. 113, article 109059, 2026, https://doi.org/10.1016/j.bspc.2025.109059.
  40. P. Sahoo et al., “FedMRL: Data heterogeneity-aware federated multiagent deep reinforcement learning for medical imaging,” in Medical Image Computing and Computer-Assisted Intervention (MICCAI 2024), Lecture Notes in Computer Science. Cham, Switzerland: Springer Nature Switzerland, 2024, pp. 438–448, https://doi.org/10.1007/ 978-3-031-72384-1_60.
  41. A. Hassani and I. Rekik, “UniFed: A universal federation of a mixture of highly heterogeneous medical image classification tasks,” in Machine Learning in Medical Imaging, Lecture Notes in Computer Science. Cham, Switzerland: Springer Nature Switzerland, 2024, pp. 32-42 https://doi.org/10.1007/978-3-031-73290-4_4.
  42. S. Arya et al., “Federated impression for learning with distributed heterogeneous data,” in International Conference on Medical Image Computing and Computer-Assisted Intervention, Cham, Switzerland: Springer Nature Switzerland, 2024, pp. 215-225 https://doi.org/10. 1007/978-3-031-77610-6_20.
  43. S. Bakas et al., “Federated learning in healthcare: From research to realworld deployment,” Annual Review of Biomedical Engineering, vol. 28, 2026, https://doi.org/10.1146/annurev-bioeng-080125-041414.
  44. S. Haggenmüller et al., “Federated learning for decentralized artificial intelligence in melanoma diagnostics,” JAMA Dermatology, vol. 160, no. 3, pp. 303–311, 2024, https://dx.doi.org/10.1001/jamadermatol.2023.5550.
  45. U. Baid et al., “Pan-cancer tumor infiltrating lymphocyte detection based on federated learning,” in Proc. IEEE Int. Conf. Big Data, 2024, pp. xx– xx, https://doi.org/10.1109/bigdata62323.2024.10825083.
  46. R. H. Junejo et al., “Federated ViT: A distributed deep learning framework for skin cancer classification,” IEEE Access, vol. 13, 2025, https://doi.org/10.1109/access.2025.3612477.
  47. M. Delehouzee et al., “Performance analysis of aggregation algorithms in cross-silo federated learning for non-IID data,” in Proc. 4th Int. Conf. Embedded and Distributed Systems (EDiS), 2024,pp. 74-79, https://doi.org/10.1109/EDiS63605.2024.10783224.
  48. H. Pan et al., “Adaptive aggregation weights for federated segmentation of pancreas MRI,” in Proc. IEEE Int. Symp. Biomedical Imaging (ISBI), 2025, pp. 1-5, https://doi.org/10.1109/ISBI60581.2025.10981148.
  49. L. A. Schoenpflug et al., “Navigating real-world challenges: A case study on federated learning in computational pathology,” Journal of Pathology Informatics, vol. 16, article 100464, 2025, https://doi. org/10.1016/j.jpi.2025.100464.
  50. M. Lablans, S. Bartholomaus, and F. Uckert, “Providing trust and interoperability to federate distributed biobanks,” in User Centred Networked Health Care. Amsterdam, The Netherlands: IOS Press, 2011, pp. 644– 648, https://doi.org/10.3233/978-1-60750-806-9-644.
  51. B. Clarke et al., “Large-scale implementation of digital pathology for clinical diagnoses: Experience, challenges, and lessons learned,” Critical Reviews in Clinical Laboratory Sciences, early access, 2025, https://doi.org/10.1080/10408363.2025.2549309.
  52. M. Touhami et al., “Federated learning for histopathology image classification: A systematic review,” Diagnostics, vol. 16, no. 1, article 137, 2026, https://doi.org/10.3390/diagnostics16010137.
  53. S. Fonio, “Benchmarking federated learning frameworks for medical imaging tasks,” in Image Analysis and Processing, Lecture Notes in Computer Science. Cham, Switzerland: Springer Nature Switzerland, 2023, https://doi.org/10.1007/978-3-031-51026-7_20.
  54. M. Chavero-Diez et al., “Federated learning frameworks: Quality and interoperability for biomedical research,” NAR Genomics and Bioinformatics, vol. 8, no. 1, article lqag010, 2026, https://doi.org/10.1093/ nargab/lqag010.
  55. M. Romanchikova et al., “The need for measurement science in digital pathology,” Journal of Pathology Informatics, vol. 13, article 100157, 2022, https://doi.org/10.1016/j.jpi.2022.100157.
  56. E. Alozie et al., “Technical considerations of federated learning in digital healthcare systems,” in Federated Learning for Digital Healthcare Systems. Academic Press, 2024, pp. 237–282, https://doi.org/10. 1016/b978-0-443-13897-3.00009-6.
  57. S. Shukla and S. Doyle, “Federated learning in computational pathology: A literature review,” Journal of Medical Imaging, vol. 12, no. 6, article 061412, 2025, https://doi.org/10.1117/1.jmi.12.6.061412.
  58. R. Haripriya et al., “Federated adaptive aggregation: Improving privacy and scalability in healthcare AI,” Cluster Computing, vol. 28, article 617, 2025, https://doi.org/10.1007/s10586-025-05290-4.
  59. J. Yang et al., “Matrix Gaussian mechanisms for differentially private learning,” IEEE Transactions on Mobile Computing, vol. 22, no. 2, pp. 1036–1048, 2023, https://doi.org/10.1109/tmc.2021.3093316.
  60. Y. Li et al., “An optimized scheme of federated learning based on differential privacy,” in Blockchain and Trustworthy Systems. Singapore: Springer Nature Singapore, 2023, https://doi.org/10.1007/ 978-981-99-8101-4_20.
  61. D. Cui and C. Wang, “PD-ADPVFL: Performance-driven adaptive differential privacy vertical federated learning,” in Intelligent Computing. Singapore: Springer Nature Singapore, 2025, https://doi.org/10. 1007/978-981-96-9958-2_23.
  62. M. H. Alhazmi, “Adaptive federated clustering for uncertainty-aware learning on decentralized big data platforms,” PLOS ONE, vol. 20, no. 12, article e0337069, 2025, https://doi.org/10.1371/journal.pone. 0337069.
  63. A. N. Onaizah et al., “Deep learning-based brain tumour architecture for weight sharing optimization in federated learning,” Expert Systems, vol. 42, no. 2, article e13643, 2025, https://doi.org/10.1111/exsy.13643.
  64. L. A. Schoenpflug et al., “A review on federated learning in computational pathology,” Computational and Structural Biotechnology Journal, vol. 23, pp. 3938–3945, 2024, https://doi.org/10.1016/j.csbj.2024. 10.037.
  65. S. Suwer et al., “Privacy-by-design with federated learning will drive future rare disease research,” Journal of Neuromuscular Diseases, vol. 13, no. 1, pp. 6–19, 2026, https://doi.org/10.1177/22143602241296276.