Are Traditional Deep Learning Model Approaches as Effective as a Retinal-Specific Foundation Model for Ocular and Systemic Disease Detection?

2025-01-21

AI Summary

General-purpose vision models often underperform in medical imaging tasks, particularly for systemic disease prediction from retinal images under limited labeled data. Method: This study systematically compares the retinal-specific self-supervised foundation model RETFound against generic vision models (ResNet50, ViT-base, SwinV2) across ophthalmic and systemic disease detection. Evaluation employs multicenter internal and external validation (SEED, APTOS-2019, UK Biobank), supervised fine-tuning, and AUC-based performance assessment, with statistical inference via Bonferroni-corrected Z-tests. Contribution/Results: On large-scale ophthalmic tasks, all models achieve comparable performance. However, RETFound significantly outperforms generic models in small-sample (≤400 samples) systemic disease prediction (p<0.05, AUC gains up to 0.06), demonstrating superior external generalizability. This work provides the first empirical evidence of retinal foundation models’ unique advantage for low-data systemic health inference, clarifies the applicability boundaries between foundation and conventional supervised models, and delivers critical translational evidence for clinical deployment of medical imaging foundation models.

Technology Category

• Computer Vision: Other Foundations of Computer Vision
• Machine Learning: Other Foundations of Machine Learning
• Cognitive Modeling & Cognitive Systems: Other Foundations of Cognitive Modeling & Systems

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Background: RETFound, a self-supervised, retina-specific foundation model (FM), showed potential in downstream applications. However, its comparative performance with traditional deep learning (DL) models remains incompletely understood. This study aimed to evaluate RETFound against three ImageNet-pretrained supervised DL models (ResNet50, ViT-base, SwinV2) in detecting ocular and systemic diseases. Methods: We fine-tuned/trained RETFound and three DL models on full datasets, 50%, 20%, and fixed sample sizes (400, 200, 100 images, with half comprising disease cases; for each DR severity class, 100 and 50 cases were used. Fine-tuned models were tested internally using the SEED (53,090 images) and APTOS-2019 (3,672 images) datasets and externally validated on population-based (BES, CIEMS, SP2, UKBB) and open-source datasets (ODIR-5k, PAPILA, GAMMA, IDRiD, MESSIDOR-2). Model performance was compared using area under the receiver operating characteristic curve (AUC) and Z-tests with Bonferroni correction (P<0.05/3). Interpretation: Traditional DL models are mostly comparable to RETFound for ocular disease detection with large datasets. However, RETFound is superior in systemic disease detection with smaller datasets. These findings offer valuable insights into the respective merits and limitation of traditional models and FMs.

Problem

• Retinal Analysis
• Disease Detection
• Deep Learning Models

Innovation

• RETFound model
• disease detection
• small data performance