A foundation model for generalizable disease detection from retinal images

Medical artificial intelligence (Al) offers great potential for recognizing signs of health conditions in retinal images and expediting the diagnosis of eye diseases and systemic disorders. However, the development of Al models requires substantial annotation and models are usually task-specific with limited generalizability to different clinicaI applications. Here, we present RETFound, a foundation model for retinal images that learns generalizable representations from unlabelled retinal images and provides a basis for label-efficient model adaptation in severaI applications. Specifically, RETFound is trained on 1.6 miliion unlabelled retinal images by means of self-supervised learning and then adapted to disease detection tasks with explicit labels. We show that adapted RETFound consistently outperforms severaI comparison models in the diagnosis and prognosis of sight-threatening eye diseases, as well as incident prediction of complex systemic disorders such as heart failure and myocardial infarction with fewer labelled data. RETFound provides a generalizable solution to improve model performance and alleviate the annotation workload of experts to enable broad clinicaI Al applications from retinal imaging.

*Author(s): Yukun Zhou, Mark A. Chia, Siegfried K. Wagner, Murat S. Ayhan, Dominic J. Williamson1 Mateo G. Lozano, Robbert R. Struyven, Timing Liu, Moucheng Xu, Peter Woodward-Court , Yuka Kihara, Andre Altmann, Aaron Y. Lee, Eric J. Topol, Alastair K. Denniston, Daniel C. Alexander & Pearse A. Keane.

https://www.nature.com/articles/s41586-023-06555-x/

Experimental Paper of the Month manager: Anthony Khawaja

Editorial Board: Humma Shahid, Karl Mercieca, Francisco Goni

Editors in Chief: Francesco Oddone, Manuele Michelessi