Key result
DINOv2 classifies carotid atherosclerosis from retinal images with AUC 0.71 and predicts future cardiovascular mortality.
Why the study?
Carotid atherosclerosis is a key predictor of CVD, but optimal selection and fine-tuning strategies of vision foundation models for classifying carotid atherosclerosis from retinal images remain unclear.
Can vision foundation models fine-tuned on retinal images accurately classify carotid atherosclerosis and predict future cardiovascular disease mortality?
Cohort (n=39,620)
No
Can vision foundation models fine-tuned on retinal images accurately classify carotid atherosclerosis and predict future cardiovascular disease mortality?
Deep learning foundation models, particularly DINOv2 with low-rank adaptation, can opportunistically screen for carotid atherosclerosis and predict future cardiovascular mortality using non-invasive retinal images.
Answers are grounded in this paper and cite their sources.
May facilitate opportunistic CVD risk assessment via retinal imaging; leaves open prospective validation before clinical integration.
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.
No takes yet. Share an insight, caveat, or question.
Lee et al. (2025) conducted a cohort in Carotid atherosclerosis (n=39,620). DINOv2 with low-rank adaptation (LoRA) vs. Other foundation models and fine-tuning methods was evaluated on Carotid atherosclerosis classification (AUC 0.71, 95% CI 0.68-0.73). DINOv2 with low-rank adaptation achieved the best performance for classifying carotid atherosclerosis from retinal images with an AUC of 0.71 and significantly predicted future cardiovascular mortality.
Synapse has enriched 10 related papers. Consider them for comparative context: