Developing a privacy-preserving deep learning model for glaucoma detection: a multicentre study with federated learning.
An Ran RanXi WangPoemen P ChanMandy O M WongHunter YuenNai Man LamNoel C Y ChanWilson W K YipAlvin L YoungHon-Wah YungRobert T ChangSuria S MannilYih-Chung ThamChing-Yu ChengTien Yin WongChi Pui PangPheng-Ann HengClement Chee Yung ThamCarol Yim-Lui CheungPublished in: The British journal of ophthalmology (2023)
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.
Keyphrases