Article Sidebar

Submitted
November 13, 2025
Accepted
January 15, 2026
Published
January 16, 2026
Download
PDF
Statistic
Read Counter : 1 Download : 1

Main Article Content

Abstract

Machine learning has achieved diagnostic performance comparable to clinical experts on medical imaging, yet centralized training paradigms necessitate patient data aggregation, risking violations of privacy regulations such as GDPR and HIPAA. In 2023, 1,853 healthcare data breaches were reported in the United States, compromising over 133 million medical records, rendering raw inter-institutional data exchange increasingly unsustainable. Federated Learning (FL) offers a viable solution by enabling collaborative model training without data transfer. However, prior studies predominantly evaluate single algorithms and often neglect non-IID Dirichlet-distributed conditions and probabilistic calibration metrics like log-loss. This study rigorously compares FedAvg, FedProx, FedSVRG, and FedAtt across three MedMNIST v2 datasets—PneumoniaMNIST (binary), DermaMNIST, and BloodMNIST (multi-class)—using three clients under non-IID Dirichlet partitioning (α=0.1) over 50 communication rounds. FedProx demonstrates the most consistent performance and stability, achieving accuracy of 0.9521 and log-loss of 0.1850 on PneumoniaMNIST; 0.8595 and 0.4066 on BloodMNIST; and 0.5747 and 1.5996 on DermaMNIST. It also exhibits fastest convergence and superior probability calibration. Thus, FedProx’s proximal regularization enhances FL robustness against extreme clinical heterogeneity, establishing it as a scalable, privacy-preserving framework for cross-institutional medical image diagnostics.

Keywords

aggregation healthcare federated learning data transfer privacy-preserving

Article Details

License

Copyright (c) 2026 Michael Angello Qadosy Riyadi, Adinda Mariasti Dewi, Zahid Abdullah Nur Mukhlishin, Zalsabilah Rezky Amelia Arep

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

How to Cite
Riyadi, M. A. Q., Dewi, A. M., Mukhlishin, Z. A. N., & Arep, Z. R. A. . (2026). Comparative Evaluation of Federated Learning Algorithms in Dirichlet Non-IID Medical Imaging. Jurnal Sains, Nalar, Dan Aplikasi Teknologi Informasi, 5(1), 32–44. https://doi.org/10.20885/snati.v5.i1.44597
Download Citation
Endnote/Zotero/Mendeley (RIS)
BibTeX

References

  1. K. Bhavsar, A. Abugabah, J. Singla, A. Ali, A. Bashir, and Nikita, “A Comprehensive Review on Medical Diagnosis Using Machine Learning,” Comput. Mater. Contin., vol. 67, pp. 1997–2014, Dec. 2020, doi: 10.32604/cmc.2021.014943.
  2. S. K. Zhou et al., “A Review of Deep Learning in Medical Imaging: Imaging Traits, Technology Trends, Case Studies With Progress Highlights, and Future Promises,” Proc. IEEE, vol. 109, no. 5, pp. 820–838, 2021, doi: 10.1109/JPROC.2021.3054390.
  3. G. Litjens et al., “A Survey on Deep Learning in Medical Image Analysis,” Med. Image Anal., vol. 42, pp. 60–88, 2017, doi: 10.1016/j.media.2017.07.005.
  4. A. Garg and V. Mago, “Role of machine learning in medical research: A survey,” Comput. Sci. Rev., vol. 40, p. 100370, May 2021, doi: 10.1016/j.cosrev.2021.100370.
  5. C. Prince, N. Omrani, and F. Schiavone, “Online privacy literacy and users’ information privacy empowerment: the case of GDPR in Europe,” Inf. Technol. People, vol. 37, no. 8, pp. 1–24, Jan. 2024, doi: 10.1108/ITP-05-2023-0467.
  6. M. Taufiq and A. S. Kenyo, “The Legal Protection of Personal Data in the Digital Era: A Comparative Study of Indonesian Law and the GDPR,” Int. J. Bus. Law Educ., vol. 6, no. 2, pp. 1260–1268, Aug. 2025, doi: 10.56442/ijble.v6i2.1178.
  7. K. Theodos and S. Sittig, “Health Information Privacy Laws in the Digital Age: HIPAA Doesn’t Apply,” Perspect. Health Inf. Manag., vol. 18, no. Winter, p. 1l, 2020.
  8. K. Li, A. Lohachab, M. Dumontier, and others, “Privacy preservation in blockchain-based healthcare data sharing: A systematic review,” Peer--Peer Netw. Appl., vol. 18, p. 302, 2025, doi: 10.1007/s12083-025-02148-9.
  9. M. M. Ahmed, O. J. Okesanya, M. Oweidat, Z. K. Othman, S. S. Musa, and D. E. Lucero-Prisno III, “The ethics of data mining in healthcare: challenges, frameworks, and future directions,” BioData Min., vol. 18, no. 1, p. 47, 2025, doi: 10.1186/s13040-025-00461-w.
  10. K. Anyaso and V. Okoye, “The Impact of Big Data and Predictive Analytics on U.S. Healthcare Delivery: Opportunities, Challenges, and Future Directions,” World J. Adv. Res. Rev., vol. 24, no. 1, pp. 2275–2287, 2024, doi: 10.30574/wjarr.2024.24.1.3266.
  11. L. C. Bell and E. Shimron, “Sharing Data Is Essential for the Future of AI in Medical Imaging,” Radiol. Artif. Intell., vol. 6, no. 1, p. e230337, 2024, doi: 10.1148/ryai.230337.
  12. G. Choi, W. C. Cha, S. U. Lee, and S.-Y. Shin, “Survey of medical applications of federated learning,” Healthc. Inform. Res., vol. 30, no. 1, pp. 3–15, 2024, doi: 10.4258/hir.2024.30.1.3.
  13. C. Zhang, Y. Xie, H. Bai, B. Yu, W. Li, and Y. Gao, “A survey on federated learning,” Knowl.-Based Syst., vol. 216, p. 106775, 2021, doi: https://doi.org/10.1016/j.knosys.2021.106775.
  14. Q. Yang, Y. Liu, T. Chen, and Y. Tong, “Federated Machine Learning: Concept and Applications,” ACM Trans Intell Syst Technol, vol. 10, no. 2, Jan. 2019, doi: 10.1145/3298981.
  15. H. Zhu, J. Xu, S. Liu, and Y. Jin, “Federated learning on non-IID data: A survey,” Neurocomputing, vol. 465, Sep. 2021, doi: 10.1016/j.neucom.2021.07.098.
  16. L. Kwak and H. Bai, “The Role of Federated Learning Models in Medical Imaging,” Radiol. Artif. Intell., vol. 5, no. 3, p. e230136, 2023, doi: 10.1148/ryai.230136.
  17. Y. Zhao, M. Li, L. Lai, N. Suda, D. Civin, and V. Chandra, “Federated Learning with Non-IID Data,” 2018, doi: 10.48550/ARXIV.1806.00582.
  18. J. Liu, J. Huang, Y. Zhou, and others, “From distributed machine learning to federated learning: a survey,” Knowl. Inf. Syst., vol. 64, pp. 885–917, 2022, doi: 10.1007/s10115-022-01664-x.
  19. F. Sufi, “Addressing Data Scarcity in the Medical Domain: A GPT-Based Approach for Synthetic Data Generation and Feature Extraction,” Information, vol. 15, no. 5, p. 264, 2024, doi: 10.3390/info15050264.
  20. R. Schäfer, T. Nicke, H. Höfener, and others, “Overcoming data scarcity in biomedical imaging with a foundational multi-task model,” Nat. Comput. Sci., vol. 4, pp. 495–509, 2024, doi: 10.1038/s43588-024-00662-z.
  21. J. Gehrmann, E. Herczog, S. Decker, and others, “What prevents us from reusing medical real-world data in research,” Sci. Data, vol. 10, p. 459, 2023, doi: 10.1038/s41597-023-02361-2.
  22. I. Araf, A. Idri, and I. Chairi, “Cost-sensitive learning for imbalanced medical data: a review,” Artif. Intell. Rev., vol. 57, p. 80, 2024, doi: 10.1007/s10462-023-10652-8.
  23. K. Y. Chen, C. R. Shyu, Y. Y. Tsai, and others, “Effective Non-IID Degree Estimation for Robust Federated Learning in Healthcare Datasets,” J. Healthc. Inform. Res., vol. 9, pp. 437–464, 2025, doi: 10.1007/s41666-025-00195-8.
  24. H. Zhao, D. Sui, Y. Wang, L. Ma, and L. Wang, “Privacy-Preserving Federated Learning Framework for Multi-Source Electronic Health Records Prognosis Prediction,” Sensors, vol. 25, no. 8, p. 2374, 2025, doi: 10.3390/s25082374.
  25. Z. Deng, Y. Yang, and K. Suzuki, “Federated Active Learning Framework for Efficient Annotation Strategy in Skin-Lesion Classification,” J. Invest. Dermatol., vol. 145, no. 2, pp. 303–311, 2025, doi: 10.1016/j.jid.2024.05.023.
  26. D. Ryu, T. Bak, D. Ahn, and others, “Deep learning-based label-free hematology analysis framework using optical diffraction tomography,” Heliyon, vol. 9, no. 8, p. e18297, 2023, doi: 10.1016/j.heliyon.2023.e18297.
  27. J. Cui, Y. Li, Q. Zhang, Z. He, and S. Zhao, “A Federated Learning Framework Using FedProx Algorithm for Privacy-Preserving Palmprint Recognition,” in Biometric Recognition, S. Yu, W. Jia, X. Shu, X. Yuan, J. Gui, J. Tang, C. Shan, and Q. Liu, Eds., Singapore: Springer Nature Singapore, 2025, pp. 187–196. doi: https://doi.org/10.1007/978-981-96-1071-6_17.
  28. C. Mathew and P. Asha, “FedProx: FedSplit algorithm based federated learning for statistical and system heterogeneity in medical data communication,” J Internet Serv Inf Secur, vol. 14, no. 3, pp. 353–370, 2024, doi: 10.58346/JISIS.2024.I3.021.
  29. M. R. Rostami and S. S. Kia, “Federated Learning Using Variance Reduced Stochastic Gradient for Probabilistically Activated Agents.” 2023. [Online]. Available: https://arxiv.org/abs/2210.14362
  30. C. M. Thwal, Y. L. Tun, K. Kim, S.-B. Park, and C. S. Hong, “Transformers with Attentive Federated Aggregation for Time Series Stock Forecasting,” in 2023 International Conference on Information Networking (ICOIN), IEEE, Jan. 2023, pp. 499–504. doi: 10.1109/icoin56518.2023.10048928.
  31. M. Chaudhary, L. Gaur, and A. Chakrabarti, “Detecting the Employee Satisfaction in Retail: A Latent Dirichlet Allocation and Machine Learning approach,” in 2022 3rd International Conference on Computation, Automation and Knowledge Management (ICCAKM), 2022, pp. 1–6. doi: 10.1109/ICCAKM54721.2022.9990186.
  32. S. Bates, T. Hastie, and R. Tibshirani, “Cross-Validation: What Does It Estimate and How Well Does It Do It?,” J. Am. Stat. Assoc., vol. 119, no. 546, pp. 1434–1445, 2024, doi: 10.1080/01621459.2023.2197686.
  33. J. Yang, R. Shi, and B. Ni, “MedMNIST Classification Decathlon: A Lightweight AutoML Benchmark for Medical Image Analysis,” in 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), 2021, pp. 191–195. doi: 10.1109/ISBI48211.2021.9434062.
  34. A. T. Hutcheson and K. G. Brown, “Chi-Square,” in Statistics for Psychology Research, Cham: Palgrave Macmillan, 2024. doi: 10.1007/978-3-031-60970-1_10.
  35. A. Zeimbekakis, E. D. Schifano, and J. Yan, “On Misuses of the Kolmogorov–Smirnov Test for One-Sample Goodness-of-Fit,” Am. Stat., vol. 78, no. 4, pp. 481–487, 2024, doi: 10.1080/00031305.2024.2356095.
  36. T. Li, A. K. Sahu, A. Talwalkar, and V. Smith, “Federated Learning: Challenges, Methods, and Future Directions,” IEEE Signal Process. Mag., vol. 37, no. 3, pp. 50–60, 2020, doi: 10.1109/MSP.2020.2975749.
  37. J. Reyes, L. Di Jorio, C. Low-Kam, and M. Kersten-Oertel, “Precision-Weighted Federated Learning,” Comput. Intell., vol. 41, no. 6, p. e70150, 2025, doi: https://doi.org/10.1111/coin.70150.
  38. T. Kołodziej and P. Rościszewski, “Towards Scalable Simulation of Federated Learning,” in International Conference on Neural Information Processing, Springer, 2021, pp. 248–256.
  39. H. Reguieg, M. E. Hanjri, M. E. Kamili, and A. Kobbane, “A Comparative Evaluation of FedAvg and Per-FedAvg Algorithms for Dirichlet Distributed Heterogeneous Data,” in 2023 10th International Conference on Wireless Networks and Mobile Communications (WINCOM), 2023, pp. 1–6. doi: 10.1109/WINCOM59760.2023.10322899.
  40. S. P. Karimireddy, S. Kale, M. Mohri, S. Reddi, S. Stich, and A. T. Suresh, “SCAFFOLD: Stochastic Controlled Averaging for Federated Learning,” in Proceedings of the 37th International Conference on Machine Learning, H. D. III and A. Singh, Eds., in Proceedings of Machine Learning Research, vol. 119. PMLR, Jul. 2020, pp. 5132–5143. [Online]. Available: https://proceedings.mlr.press/v119/karimireddy20a.html
  41. S. M. Anwar, M. Majid, A. Qayyum, and others, “Medical Image Analysis using Convolutional Neural Networks: A Review,” J. Med. Syst., vol. 42, no. 11, p. 226, 2018, doi: 10.1007/s10916-018-1088-1.
  42. G. Naidu, T. Zuva, and E. M. Sibanda, “A Review of Evaluation Metrics in Machine Learning Algorithms,” in Artificial Intelligence Application in Networks and Systems, R. Silhavy and P. Silhavy, Eds., Cham: Springer International Publishing, 2023, pp. 15–25. doi: https://doi.org/10.1007/978-3-031-35314-7_2.
  43. A. Xiong and others, “A Multi-Task Based Clustering Personalized Federated Learning Method,” Big Data Min. Anal., vol. 7, no. 4, pp. 1017–1030, Dec. 2024, doi: 10.26599/BDMA.2024.9020001.
  44. C. Smestad and J. Li, “A Systematic Literature Review on Client Selection in Federated Learning,” in Proceedings of the 27th International Conference on Evaluation and Assessment in Software Engineering, in EASE ’23. New York, NY, USA: Association for Computing Machinery, 2023, pp. 2–11. doi: 10.1145/3593434.3593438.
  45. Y. Shanmugarasa, H. Paik, S. S. Kanhere, and L. Zhu, “A systematic review of federated learning from clients’ perspective: challenges and solutions,” Artif. Intell. Rev., vol. 56, no. Suppl 2, pp. 1773–1827, 2023, doi: 10.1007/s10462-023-10563-8.
  46. H. Lin, X. Hu, S. Bai, and Y. Liu, “Personalized Federated Learning Algorithm Based on User Grouping and Group Signatures,” in Information and Communications Security, J. Han, Y. Xiang, G. Cheng, W. Susilo, and L. Chen, Eds., in Lecture Notes in Computer Science, vol. 16218. Springer, Singapore, 2026. doi: 10.1007/978-981-95-3543-9_24.
  47. Y. Liu, S. Li, W. Li, H. Qian, and H. Xia, “A Personalized Federated Learning Algorithm Based on Dynamic Weight Allocation,” Electronics, vol. 14, no. 3, p. 484, 2025, doi: 10.3390/electronics14030484.
  48. H. Yang, J. Li, M. Hao, and others, “An efficient personalized federated learning approach in heterogeneous environments: a reinforcement learning perspective,” Sci. Rep., vol. 14, p. 28877, 2024, doi: 10.1038/s41598-024-80048-3.
  49. M. Adnan, S. Kalra, J. C. Cresswell, G. W. Taylor, and H. R. Tizhoosh, “Federated learning and differential privacy for medical image analysis,” Sci. Rep., vol. 12, no. 1, p. 1953, 2022, doi: 10.1038/s41598-022-05539-7.
  50. M. Mohammadi, M. Vejdanihemmat, M. Lotfinia, and others, “Differential privacy for medical deep learning: methods, tradeoffs, and deployment implications,” Npj Digit. Med., 2026, doi: 10.1038/s41746-025-02280-z.
  51. X. Yang, J. Luo, and M. N. Mohammed, “Federation Learning of Optimized Convolutional Neural Network Structure for Intrusion Detection,” in 2022 Second International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies (ICAECT), Bhilai, India, 2022, pp. 1–7. doi: 10.1109/ICAECT54875.2022.9807964.
  52. Divya, N. Anand, and G. Sharma, “Convolutional neural network (CNN) and federated learning-based privacy preserving approach for skin disease classification,” J. Supercomput., vol. 80, pp. 24559–24577, 2024, doi: 10.1007/s11227-024-06309-0.
  53. S. Mehta, V. Kukreja, and R. Gupta, “Exploring the Potential of Federated Learning CNN for Interactive Virtual Tours of UNESCO Cultural Heritage Sites: A Case Study,” in 2023 14th International Conference on Computing Communication and Networking Technologies (ICCCNT), Delhi, India, 2023, pp. 1–6. doi: 10.1109/ICCCNT56998.2023.10307071.
  54. D. Süer Tümen and M. Nergiz, “Federated Learning-Based CNN Models for Orthodontic Skeletal Classification and Diagnosis,” Diagnostics, vol. 15, no. 7, p. 920, 2025, doi: 10.3390/diagnostics15070920.