Optimizing retinal images based carotid atherosclerosis prediction with explainable foundation models.
Authors
Affiliations (5)
Affiliations (5)
- Department of Biomedical Sciences, Seoul National University Graduate School, Seoul, South Korea.
- College of Medicine, Seoul National University, Seoul, South Korea.
- XAIMED Co. Ltd, Seoul, South Korea.
- XAIMED Co. Ltd, Seoul, South Korea. [email protected].
- Harvard Retinal Imaging Lab, Massachusetts Eye and Ear, Harvard Medical School, Boston, MA, USA. [email protected].
Abstract
Carotid atherosclerosis is a key predictor of cardiovascular disease (CVD), necessitating early detection. While foundation models (FMs) show promise in medical imaging, their optimal selection and fine-tuning strategies for classifying carotid atherosclerosis from retinal images remain unclear. Using data from 39,620 individuals, we evaluated four vision FMs with three fine-tuning methods. Performance was evaluated by predictive performance, clinical utility by survival analysis for future CVD mortality, and explainability by Grad-CAM with vessel segmentation. DINOv2 with low-rank adaptation showed the best overall performance (area under the receiver operating characteristic curve = 0.71; sensitivity = 0.87; specificity = 0.44), prognostic relevance (hazard ratio = 2.20, P-trend < 0.05), and vascular alignment. While further external validation on a broader clinical context is necessary to improve the model's generalizability, these findings support the feasibility of opportunistic atherosclerosis and CVD screening using retinal imaging and highlight the importance of a multi-dimensional evaluation framework for optimal FM selection in medical artificial intelligence.