Federated Learning with Homomorphic Encryption for Privacy-Preserving Multi-Hospital Training of Diabetic Retinopathy Detection Models Using Fundus Photographs

cirpublications.com-dcfz-1790880682-v319635436 1790880682 Clinical Intelligence Research Press info@cirpublications.com Clinical Intelligence Research Press Journal of Artificial Intelligence for Healthcare Systems J. Artif. Intell. Healthc. Syst. 3149-8981 2023 2 2 Federated Learning with Homomorphic Encryption for Privacy-Preserving Multi-Hospital Training of Diabetic Retinopathy Detection Models Using Fundus Photographs Oliver Grant David Clark Sophia Nguyen 2023 10.68159/v319635436 https://cirpublications.com/pub/journal/1/article/v319635436 Raman R, Srinivasan S, Virmani S, Sivaprasad S, Rao C, Rajalakshmi R, et al. Fundus photograph-based deep learning algorithms in detecting diabetic retinopathy. Eye (Lond). 2019;33(1):97-109. 10.1038/s41433-018-0269-y Ghorbanzadeh O, Blaschke T, Gholamnia K, Meena SR, Tiede D, Aryal J, et al. Evaluation of different machine learning methods and deep-learning convolutional neural networks for landslide detection. Remote Sens. 2019;11(2):196. 10.3390/rs11020196 Kim KM, Heo TY, Kim A, Kim J, Han KJ, Yun J, et al. Development of a fundus image-based deep learning diagnostic tool for various retinal diseases. J Pers Med. 2021;11(5):321. 10.3390/jpm11050321 Matta S, Hassine MB, Lecat C, Borderie L, Le Guilcher A, Massin P, et al. Federated learning for diabetic retinopathy detection in a multi-center fundus screening network. In: 2023 45th Annu Int Conf IEEE Eng Med Biol Soc (EMBC); 2023 Jul 24; Sydney, Australia. New York: IEEE; 2023. p. 1-4. 10.1109/EMBC40787.2023.10340431 Mohan NJ, Murugan R, Goel T, Roy P. DRFL: federated learning in diabetic retinopathy grading using fundus images. IEEE Trans Parallel Distrib Syst. 2023;34(6):1789-801. 10.1109/TPDS.2023.3264455 Chetoui M, Akhloufi MA. Federated learning for diabetic retinopathy detection using vision transformers. BioMedInformatics. 2023;3(4):948-61. 10.3390/biomedinformatics3040060 Zhang W, Wang Q, Li M. Privacy-preserving collaborative training for medical image analysis based on multi-blockchain. Comb Chem High Throughput Screen. 2021;24(7):933-46. 10.2174/1386207323666201114114834 Ziller A, Passerat-Palmbach J, Ryffel T, Usynin D, Trask A, Junior ID, et al. Privacy-preserving medical image analysis. arXiv [Preprint]. 2020:arXiv:2012.06354. Vizitiu A, Niță CI, Puiu A, Suciu C, Itu LM. Applying deep neural networks over homomorphic encrypted medical data. Comput Math Methods Med. 2020;2020:3910250. Nguyen-Van T, Nguyen-Van T, Nguyen TT, Bui-Huu D, Le-Nhat Q, Pham TV, et al. A homomorphic encryption approach for privacy-preserving deep learning in digital health care service. In: Asian Conf Intell Inf Database Syst; 2022 Nov 28; Ho Chi Minh City, Vietnam. Cham: Springer; 2022. p. 520-33. 10.1007/978-3-031-21743-2_43 Ali A, Pasha MF, Guerrieri A, Guzzo A, Sun X, Saeed A, et al. A novel homomorphic encryption and consortium blockchain-based hybrid deep learning model for industrial internet of medical things. IEEE Trans Netw Sci Eng. 2023;10(5):2402-18. 10.1109/TNSE.2023.3245670 Lo J, Timothy TY, Ma D, Zang P, Owen JP, Zhang Q, et al. Federated learning for microvasculature segmentation and diabetic retinopathy classification of OCT data. Ophthalmol Sci. 2021;1(4):100069. 10.1016/j.xops.2021.100069 Wood A, Najarian K, Kahrobaei D. Homomorphic encryption for machine learning in medicine and bioinformatics. ACM Comput Surv. 2020;53(4):1-35. 10.1145/3394658 Jiang X, Qian J, Gu A, Ma X, Jin K, Zhang X, et al. SynthFed: Privacy-preserving long-tail ophthalmic diagnosis via VQ-VAE and GPT-augmented federated learning. Biomed Signal Process Control. 2026;113:109181. 10.1016/j.bspc.2025.109181 Bonawitz K, Ivanov V, Kreuter B, Marcedone A, McMahan HB, Patel S, et al. Practical secure aggregation for privacy-preserving machine learning. In: Proc 2017 ACM SIGSAC Conf Comput Commun Secur; 2017 Oct 30; Dallas, TX, USA. New York: ACM; 2017. p. 1175-91. 10.1145/3133956.3133982 Gong X, Sharma A, Karanam S, Wu Z, Chen T, Doermann D, et al. Ensemble attention distillation for privacy-preserving federated learning. In: Proc IEEE/CVF Int Conf Comput Vis (ICCV); 2021; Montreal, Canada. New York: IEEE; 2021. p. 15076-86. 10.1109/ICCV48922.2021.01482 Newton P, Choudhury O, Horne B, Ravipati V, Bhargavi D, Ratan U. Client-private secure aggregation for privacy-preserving federated learning. In: Workshop on Federated Learning: Recent Advances and New Challenges (NeurIPS 2022); 2022; New Orleans, LA, USA. 2022. Cabrero-Holgueras J, Pastrana S. Towards realistic privacy-preserving deep learning over encrypted medical data. Front Cardiovasc Med. 2023;10:1117360. 10.3389/fcvm.2023.1117360 Sarwar A, Hossain MS, Bhuiyan RA, Mahmud T, Zaman S, Hossin MI, et al. Homomorphic encryption on deep learning in accurate prediction of brain tumour. In: 2023 Int Conf Next-Generation Comput IoT Mach Learn (NCIM); 2023 Jun 16; Dhaka, Bangladesh. New York: IEEE; 2023. p. 1-6. 10.1109/NCIM59001.2023.10270338 Acar A, Aksu H, Uluagac AS, Conti M. A survey on homomorphic encryption schemes: theory and implementation. ACM Comput Surv. 2018;51(4):1-35. 10.1145/3214303 Zhang L, Xu J, Vijayakumar P, Sharma PK, Ghosh U. Homomorphic encryption-based privacy-preserving federated learning in IoT-enabled healthcare system. IEEE Trans Netw Sci Eng. 2022;10(5):2864-80. 10.1109/TNSE.2022.3224053 Crihan G, Crăciun M, Dumitriu L. An efficient hybrid authentication mechanism based on biometric fingerprint recognition and homomorphic encryption. Verma T, Jin L, Zhou J, Huang J, Tan M, Choong BC, et al. Privacy-preserving continual learning methods for medical image classification: a comparative analysis. Front Med. 2023;10:1227515. 10.3389/fmed.2023.1227515 Sultana M, Hossain A, Laila F, Taher KA, Islam MN. Towards developing a secure medical image sharing system based on zero trust principles and blockchain technology. BMC Med Inform Decis Mak. 2020;20(1):256. 10.1186/s12911-020-01278-0 Ryffel T, Trask A, Dahl M, Wagner B, Mancuso J, Rueckert D, et al. A generic framework for privacy preserving deep learning. arXiv [Preprint]. 2018:arXiv:1811.04017. Singh A, Singh KK. FedDDR: A federated improved DenseNet for classification of diabetic retinopathy. CEUR Workshop Proc. 2023;1613:73-80. Vujosevic S, Aldington SJ, Silva P, Hernández C, Scanlon P, Peto T, et al. Screening for diabetic retinopathy: new perspectives and challenges. Lancet Diabetes Endocrinol. 2020;8(4):337-47. 10.1016/S2213-8587(19)30411-5 Al Zabadi H, Taha I, Zagha R. Clinical and molecular characteristics of diabetic retinopathy and its severity complications among diabetic patients: a multicenter cross-sectional study. J Clin Med. 2022;11(14):3945. 10.3390/jcm11143945 Ahuja R, Sharma SC, Ali M. A diabetic disease prediction model based on classification algorithms. Ann Emerg Technol Comput. 2019.