Developing a privacy-preserving deep learning model for glaucoma detection: a multicentre study with federated learning,British Journal of Ophthalmology

当前位置： X-MOL 学术 › Br. J. Ophthalmol. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

Developing a privacy-preserving deep learning model for glaucoma detection: a multicentre study with federated learning
British Journal of Ophthalmology ( IF 3.7 ) Pub Date : 2024-08-01 , DOI: 10.1136/bjo-2023-324188
An Ran Ran ₁ , Xi Wang _{2,

3,

4} , Poemen P Chan _{1,

5} , Mandy O M Wong ₅ , Hunter Yuen ₅ , Nai Man Lam ₅ , Noel C Y Chan _{6,

7} , Wilson W K Yip _{6,

7} , Alvin L Young _{6,

7} , Hon-Wah Yung ₈ , Robert T Chang ₉ , Suria S Mannil ₉ , Yih-Chung Tham _{10,

11,

12} , Ching-Yu Cheng _{10,

11,

12} , Tien Yin Wong _{10,

13,

14} , Chi Pui Pang ₁ , Pheng-Ann Heng ₃ , Clement C Tham _{1,

5} , Carol Y Cheung ₁₅

Affiliation

Department of Ophthalmology and Visual Sciences, The Chinese University of Hong Kong, Hong Kong SAR, China.
Zhejiang Lab, Hangzhou, China.
Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong SAR, China.
Department of Radiation Oncology, Stanford University School of Medicine, Palo Alto, California, USA.
Hong Kong Eye Hospital, Hong Kong SAR, China.
Ophthalmology and Visual Sciences, Prince of Wales Hospital, Hong Kong SAR, China.
Ophthalmology and Visual Sciences, Alice Ho Miu Ling Nethersole Hospital, Hong Kong SAR, China.
Tuen Mun Eye Centre, Hong Kong SAR, China.
Ophthalmology, Stanford University School of Medicine, Stanford, California, USA.
Singapore Eye Research Institute, Singapore National Eye Centre, Singapore.
Duke-National University of Singapore Medical School, Singapore.
Department of Ophthalmology, Yong Loo Lin School of Medicine, National University of Singapore, Singapore.
Tsinghua University, Beijing, China.
School of Clinical Medicine, Beijing Tsinghua Changgung Hospital, Beijing, China.
Department of Ophthalmology and Visual Sciences, The Chinese University of Hong Kong, Hong Kong SAR, China

Background Deep learning (DL) is promising to detect glaucoma. However, patients’ privacy and data security are major concerns when pooling all data for model development. We developed a privacy-preserving DL model using the federated learning (FL) paradigm to detect glaucoma from optical coherence tomography (OCT) images. Methods This is a multicentre study. The FL paradigm consisted of a ‘central server’ and seven eye centres in Hong Kong, the USA and Singapore. Each centre first trained a model locally with its own OCT optic disc volumetric dataset and then uploaded its model parameters to the central server. The central server used FedProx algorithm to aggregate all centres’ model parameters. Subsequently, the aggregated parameters are redistributed to each centre for its local model optimisation. We experimented with three three-dimensional (3D) networks to evaluate the stabilities of the FL paradigm. Lastly, we tested the FL model on two prospectively collected unseen datasets. Results We used 9326 volumetric OCT scans from 2785 subjects. The FL model performed consistently well with different networks in 7 centres (accuracies 78.3%–98.5%, 75.9%–97.0%, and 78.3%–97.5%, respectively) and stably in the 2 unseen datasets (accuracies 84.8%-87.7%, 81.3%-84.8%, and 86.0%–87.8%, respectively). The FL model achieved non-inferior performance in classifying glaucoma compared with the traditional model and significantly outperformed the individual models. Conclusion The 3D FL model could leverage all the datasets and achieve generalisable performance, without data exchange across centres. This study demonstrated an OCT-based FL paradigm for glaucoma identification with ensured patient privacy and data security, charting another course toward the real-world transition of artificial intelligence in ophthalmology. Data are available upon reasonable request. The study protocol, the statistical analysis plan and the packaged model are available upon reasonable request. Such requests are decided on a case-by-case basis. Proposals should be directed to carolcheung@cuhk.edu.hk.

更新日期：2024-07-23

点击分享查看原文

点击收藏

阅读更多本刊新发论文本刊介绍/投稿指南