FedEYE: A Scalable and Flexible End-to-end Federated Learning Platform for Ophthalmology

Bingjie Yan1,2,3,#, Danmin Cao6,#, Xinlong Jiang1,2,3,#, Yiqiang Chen1,2,3,7,*, Weiwei Dai4,5,*, Fan Dong1,2,3, Wuliang Huang1,2,3, Teng Zhang1,2,3, Chenlong Gao1,2,3, Qian Chen1,2,3, Zhen Yan1,2,3, Zhirui Wang1,2,3,
1Institute of Computing Technology, Chinese Academy of Sciences, 2Beijing Key Laboratory of Mobile Computing and Pervasive Device, 3University of Chinese Academy of Sciences, 4Institute of Digital Ophthalmology and Visual Science, Changsha Aier Eye Hospital, 5AnHui Aier Eye Hospital, Anhui Medical University, 6Aier Eye Hospital of Wuhan University, 7Peng Cheng Laboratory, #Equal Contribution, *Correspondence
Paper Code

FedEYE empowers ophthalmologists to apply AI techniques to private data.

Abstract

Data-driven machine learning, as a promising approach, possesses the capability to build high-quality, exact, and robust models from ophthalmic medical data. However, ophthalmic medical data presently exist across disparate data silos with privacy limitations, making it challenging to conduct centralized training. While machine learning and AI may not be ophthalmologists' primary areas of expertise, considerable impediments arise in the associated realm of research. To address these issues, we design and develop FedEYE, a scalable and flexible end-to-end ophthalmic federated learning platform. During FedEYE design, we adhere to four fundamental design principles, ensuring that ophthalmologists can effortlessly create independent and federated AI research tasks. Benefiting from the design principles and architecture of FedEYE, it encloses numerous key features, including rich and customizable capabilities, separation of concerns, scalability, and flexible deployment. We also validated the applicability of FedEYE by employing several prevalent neural networks on six ophthalmic disease image classification tasks. Our FedEYE platform is now available at https://fedeye.aierchina.com/.

Related Links

There are many excellent jobs here that are relevant to us.

BibTeX

@article{yan2024fedeye,
    title={FedEYE: A scalable and flexible end-to-end federated learning platform for ophthalmology},
    author={Yan, Bingjie and Cao, Danmin and Jiang, Xinlong and Chen, Yiqiang and Dai, Weiwei and Dong, Fan and Huang,
    Wuliang and Zhang, Teng and Gao, Chenlong and Chen, Qian and others},
    journal={Patterns},
    publisher={Elsevier}
}