Benchmarking Ophthalmology Foundation Models for Clinically Significant Age Macular Degeneration Detection
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910961006280704 |
|---|---|
| author | Cohen, Benjamin A. Fhima, Jonathan Meisel, Meishar Meital, Baskin Nakayama, Luis Filipe Berkowitz, Eran Behar, Joachim A. |
| author_facet | Cohen, Benjamin A. Fhima, Jonathan Meisel, Meishar Meital, Baskin Nakayama, Luis Filipe Berkowitz, Eran Behar, Joachim A. |
| contents | 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. 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. Our results show that iBOT pretrained on natural images achieves the highest out-of-distribution generalization, with AUROCs of 0.80-0.97, outperforming domain-specific models, which achieved AUROCs of 0.78-0.96 and a baseline ViT-L with no pretraining, which achieved AUROCs of 0.68-0.91. These findings highlight the value of foundation models in improving AMD identification and challenge the assumption that in-domain pretraining is necessary. Furthermore, we release BRAMD, an open-access dataset (n=587) of DFIs with AMD labels from Brazil. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_05291 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Benchmarking Ophthalmology Foundation Models for Clinically Significant Age Macular Degeneration Detection Cohen, Benjamin A. Fhima, Jonathan Meisel, Meishar Meital, Baskin Nakayama, Luis Filipe Berkowitz, Eran Behar, Joachim A. Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition Tissues and Organs 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. 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. Our results show that iBOT pretrained on natural images achieves the highest out-of-distribution generalization, with AUROCs of 0.80-0.97, outperforming domain-specific models, which achieved AUROCs of 0.78-0.96 and a baseline ViT-L with no pretraining, which achieved AUROCs of 0.68-0.91. These findings highlight the value of foundation models in improving AMD identification and challenge the assumption that in-domain pretraining is necessary. Furthermore, we release BRAMD, an open-access dataset (n=587) of DFIs with AMD labels from Brazil. |
| title | Benchmarking Ophthalmology Foundation Models for Clinically Significant Age Macular Degeneration Detection |
| topic | Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition Tissues and Organs |
| url | https://arxiv.org/abs/2505.05291 |