Ensemble of deep convolutional neural networks is more accurate and reliable than board-certified ophthalmologists at detecting multiple diseases in retinal fundus photographs

Discussion
We developed a deep learning model and found that it could more accurately and reliably classify four categories of fundus images compared with board-certified ophthalmologists. This work provides proof-of-principle that an algorithm is capable of accurate and reliable recognition of multiple retinal diseases using only fundus photographs.

Source: British Journal of Ophthalmology - February 21, 2024 Category: Opthalmology Authors: Pandey, P. U., Ballios, B. G., Christakis, P. G., Kaplan, A. J., Mathew, D. J., Ong Tone, S., Wan, M. J., Micieli, J. A., Wong, J. C. Y. Tags: Open access Retina Source Type: research