Zhou, Yukun ORCID: 0000-0002-0840-6422, Chia, Mark A, Wagner, Siegfried K, Ayhan, Murat S ORCID: 0000-0002-3184-2353, Williamson, Dominic J ORCID: 0000-0001-5219-9312, Struyven, Robbert R ORCID: 0000-0002-2201-859X, Liu, Timing ORCID: 0000-0003-2834-3040, Xu, Moucheng, Lozano, Mateo G ORCID: 0000-0003-1686-7189, Woodward-Court, Peter ORCID: 0000-0002-7913-1403 et al (show 8 more authors)
(2023)
A foundation model for generalizable disease detection from retinal images.
Nature, 622 (7981).
pp. 156-163.
PDF
A foundation model for generalizable disease detection from retinal images.pdf - Open Access published version Download (22MB) | Preview |
Abstract
Medical artificial intelligence (AI) offers great potential for recognizing signs of health conditions in retinal images and expediting the diagnosis of eye diseases and systemic disorders<sup>1</sup>. However, the development of AI models requires substantial annotation and models are usually task-specific with limited generalizability to different clinical applications<sup>2</sup>. 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 several applications. Specifically, RETFound is trained on 1.6 million 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 several 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 clinical AI applications from retinal imaging.
Item Type: | Article |
---|---|
Uncontrolled Keywords: | UK Biobank Eye & Vision Consortium, Retina, Humans, Eye Diseases, Myocardial Infarction, Artificial Intelligence, Heart Failure, Supervised Machine Learning |
Divisions: | Faculty of Health and Life Sciences Faculty of Health and Life Sciences > Institute of Life Courses and Medical Sciences |
Depositing User: | Symplectic Admin |
Date Deposited: | 30 Nov 2023 16:55 |
Last Modified: | 30 Nov 2023 16:55 |
DOI: | 10.1038/s41586-023-06555-x |
Open Access URL: | https://doi.org/10.1038/s41586-023-06555-x |
Related URLs: | |
URI: | https://livrepository.liverpool.ac.uk/id/eprint/3177116 |