Journal article

Development and validation of a deep-learning algorithm for the detection of neovascular age-related macular degeneration from colour fundus photographs

Stuart Keel, Zhixi Li, Jane Scheetz, Liubov Robman, James Phung, Galina Makeyeva, KhinZaw Aung, Chi Liu, Xixi Yan, Wei Meng, Robyn Guymer, Robert Chang, Mingguang He

Clinical & Experimental Ophthalmology | WILEY | Published : 2019

Abstract

IMPORTANCE: Detection of early onset neovascular age-related macular degeneration (AMD) is critical to protecting vision. BACKGROUND: To describe the development and validation of a deep-learning algorithm (DLA) for the detection of neovascular age-related macular degeneration. DESIGN: Development and validation of a DLA using retrospective datasets. PARTICIPANTS: We developed and trained the DLA using 56 113 retinal images and an additional 86 162 images from an independent dataset to externally validate the DLA. All images were non-stereoscopic and retrospectively collected. METHODS: The internal validation dataset was derived from real-world clinical settings in China. Gold standard gradi..

View full abstract

Grants

Awarded by National Key R&D Program of China


Awarded by National Natural Science Foundation of China


Awarded by National Health & Medical Research Council of Australia (NHMRC)


Funding Acknowledgements

This research was supported in part by the National Key R&D Program of China (2018YFC0116500), Fundamental Research Funds of the State Key Laboratory in Ophthalmology, National Natural Science Foundation of China (81420108008), Bupa Health Foundation Australia grant, and a MACH 2018 MRFF Rapid Applied Research Translation grant. Prof. Mingguang He receives support from the University of Melbourne at Research Accelerator Program and the CERA Foundation. The Centre for Eye Research Australia receives Operational Infrastructure Support from the Victorian State Government.Cohort recruitment in the MCCS was funded by VicHealth and The Cancer Council Victoria. Further MCCS funding: the National Health & Medical Research Council of Australia (NHMRC) Program Grant 209 057, Capacity Building Grant 251 533 and Enabling Grant 396 414. The ophthalmic component was funded by the Ophthalmic Research Institute of Australia; American Health Assistance Foundation, Jack Brockhoff Foundation, John Reid Charitable Trust, Perpetual Trustees and Royal Victorian Eye and Ear Hospital.