Article

Comparison of foundation models and transfer learning strategies for diabetic retinopathy classification

2026-04-20

Abstract excerpt

Diabetic retinopathy (DR) is a leading cause of vision impairment, requiring accurate and scalable diagnostic tools. Foundation models are increasingly applied to clinical imaging, but concerns remain about their calibration. We evaluated DINOv3, RETFound, and VisionFM for DR classification using different transfer learning strategies in BRSET (n = 16,266) and mBRSET (n = 5,164). Models achieved high discriminatio...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 2f322747-a9e8-5c80-8e5b-fe47c6212144
DOI: 10.64898/2026.04.17.26351092

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Comparison of foundation models and transfer learning strategies for diabetic retinopathy classificationDOI 10.64898/2026.04.17.26351092Read

Toward Personalized Diabetic Retinopathy Screening: Deep Learning Fundus Image Analysis and Clinical Risk FactorsSemantic proximity Read

Revealing the Impact of Pre-training Data on Medical Foundation ModelsSemantic proximity Read

An Efficient and Interpretable Foundation Model for Retinal Image Analysis in Disease DiagnosisSemantic proximity Read

Evaluating ChatGPT-4’s Role in Diagnosing and Grading Diabetic Retinopathy from Fundus ImagesSemantic proximity Read

Contrastive learning-based pretraining improves representation and transferability of diabetic retinopathy classification modelsSemantic proximity Read

How does AI detect diabetic retinopathy from retinal photos? A heatmap analysis of 54 deep learning modelsSemantic proximity Read

Evaluating medical AI models beyond predictive performance: a diabetic retinopathy screening case studySemantic proximity Read

Eye Disease Classification by Advanced Deep Transfer Learning System Using Resnet50 & XceptionSemantic proximity Read

UWF-FM: A Foundation Model for Comprehensive Ultra-Widefield Retinal AssessmentSemantic proximity Read

Deep Learning for Diabetic Retinopathy Detection: A Review of Multimodal Data Fusion ApproachesSemantic proximity Read

Artificial Intelligence for the Diagnosis of De Novo Diabetic Retinopathy: A Scoping Review of Global EvidenceSemantic proximity Read

Comparing tangible retinal image characteristics with deep learning features reveals their complementarity for gene association and disease predictionSemantic proximity Read