Ophthalmology foundation models for clinically significant age macular degeneration detection

<i>Objective</i>. Self-supervised learning (SSL) has enabled vision transformers (ViTs) to learn robust representations from large-scale natural image datasets, enhancing their generalization across domains. In retinal imaging, foundation models pretrained on either natural or ophthalmic data have shown promise, but the benefits of in-domain pretraining remain uncertain.<i>Approach</i>. To investigate this, we benchmark six SSL-pretrained ViTs on seven digital fundus image (DFI) datasets totaling 70 000 expert-annotated images for the task of moderate-to-late age-related macular degeneration (AMD) identification.<i>Main results</i>. Our results show that DINOv2, pretrained on natural images, shows similar performance than domain-specific models. These findings highlight the value of foundation models in improving AMD identification, and challenge the assumption that in-domain pretraining is necessary.<i>Significance</i>. We present our model AMDNet, which performs state-of-the-art out-of-domain AUROCs on six public datasets. Furthermore, we release BRAMD, an open-access dataset (<i>n</i> = 587) of DFIs with AMD labels from Brazil. Project page:www.aimlab-technion.com/lirot-ai.