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

TL;DR

This study compares a retina-specific foundation model (RETFound) with traditional deep learning models for disease detection, finding RETFound excels in systemic disease detection with small datasets, while traditional models perform similarly on ocular diseases with large datasets.

Contribution

It provides a comprehensive comparison between RETFound and traditional DL models, highlighting the conditions under which each approach performs best.

Findings

RETFound outperforms traditional models in systemic disease detection with small datasets.

Traditional DL models are comparable to RETFound in ocular disease detection with large datasets.

RETFound shows potential advantages in data-scarce scenarios for systemic diseases.

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.