Purpose: To evaluate RETFound, a foundation artificial intelligence model, using a diverse clinical research dataset to assess its accuracy in detecting glaucoma using optic disc photographs. The model's accuracy for glaucoma detection was evaluated across race, age, glaucoma severity, and various training cycles (epochs) and dataset sample sizes.
Design: Evaluation of a diagnostic technology.
Participants: The study included 9787 color fundus photographs (CFPs) from 2329 participants of diverse race (White [73.4%], Black [13.6%] and other [13%]), disease severity (21.8% mild glaucoma, 7.2% moderate or advanced glaucoma, 60.3% not glaucoma, and 10.7% unreported), and age (48.8% <60 years, 51.1% >60 years) from the Diagnostic Innovations in Glaucoma Study and the African Descent and Glaucoma Evaluation Study. All fundus photographs were graded as "Glaucomatous" or "Non-glaucomatous."
Methods: The study employed RETFound, a self-supervised learning model, to perform binary glaucoma classification. The diagnostic accuracy of RETFound was iteratively tested across different combinations of dataset sample sizes (50-2000 optic disc photographs), training cycles (5-50), and study subpopulations stratified by severity of glaucoma, age, and race).
Main outcome measures: Diagnostic accuracy area under the receiver operating characteristic curve (AUC) for classifying CFP as "Glaucomatous" or "Non-glaucomatous."
Results: Performance increased with larger training datasets and more training cycles, improving from 50 training images and 5 epochs (AUC: 0.52) to 2000 training images and 50 epochs (AUC: 0.86), with reduced gain in performance from approximately 500 and 1000 training images (AUC of 0.82 and 0.83, respectively). Performance was consistent across race and age for all training size and cycle number combinations: Black (AUC = 0.87) vs. other (AUC = 0.86), and >60 years (AUC = 0.84) vs. <60 years (AUC = 0.87). Performance was significantly higher in patients with moderate to severe vs. mild glaucoma (AUC = 0.95 vs. 0.84, respectively).
Conclusions: Good RETFound performance was observed with a relatively small sample size of optic disc photographs used for fine-tuning and across differences in race and age. RETFound's ability to adapt across a range of CFP training conditions and populations suggests it is a promising tool to automate glaucoma detection in a variety of use cases.
Financial disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.
Keywords: Artificial intelligence; Fundus photographs; Glaucoma; RETFound; Self-supervised learning.
© 2024 Published by Elsevier Inc. on behalf of the American Academy of Ophthalmology.