Journal article
A foundation model for generalizable disease detection from retinal images
- 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. However, the development of AI models requires substantial annotation and models are usually task-specific with limited generalizability to different clinical 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 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.
- Publication status:
- Published
- Peer review status:
- Peer reviewed
Actions
Access Document
- Files:
-
-
(Supplementary materials, zip, 2.5MB, Terms of use)
-
(Preview, Version of record, pdf, 21.1MB, Terms of use)
-
- Publisher copy:
- 10.1038/s41586-023-06555-x
Authors
Contributors
+ Allen, N
- Institution:
- University of Oxford
- Division:
- MSD
- Department:
- Nuffield Department of Population Health
- Sub department:
- Clinical Trial Service Unit
- Role:
- Contributor
+ Gallacher, J
- Institution:
- University of Oxford
- Division:
- MSD
- Department:
- Psychiatry
- Role:
- Contributor
+ Engineering and Physical Sciences Research Council
More from this funder
- Funder identifier:
- https://ror.org/0439y7842
- Grant:
- EP/V034537/1
- Publisher:
- Springer Nature
- Journal:
- Nature More from this journal
- Volume:
- 622
- Issue:
- 7981
- Pages:
- 156-163
- Place of publication:
- England
- Publication date:
- 2023-09-13
- Acceptance date:
- 2023-08-18
- DOI:
- EISSN:
-
1476-4687
- ISSN:
-
0028-0836
- Pmid:
-
37704728
- Language:
-
English
- Pubs id:
-
1535032
- Local pid:
-
pubs:1535032
- Deposit date:
-
2025-06-25
- ARK identifier:
Terms of use
- Copyright holder:
- Zhou et al.
- Copyright date:
- 2023
- Rights statement:
- © The Author(s) 2023. Open Access. This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder.
- Licence:
- CC Attribution (CC BY)
If you are the owner of this record, you can report an update to it here: Report update to this record