A Disease-Specific Foundation Model Using Over 100K Fundus Images: Release and Validation for Abnormality and Multi-Disease Classification on Downstream Tasks

TL;DR

This study introduces a large, disease-specific pretrained AI model for fundus images that improves accuracy and efficiency in detecting retinal abnormalities and multiple diseases, outperforming general models.

Contribution

The paper presents a novel, large-scale, disease-specific pretrained fundus model trained on over 57,000 images, enhancing downstream task performance and reducing labeled data needs.

Findings

Achieved superior performance across various retinal disease classification tasks.

Outperformed general AI models in fundus image analysis.

Provided disease-specific visualizations for better interpretability.

Abstract

Artificial intelligence applied to retinal images offers significant potential for recognizing signs and symptoms of retinal conditions and expediting the diagnosis of eye diseases and systemic disorders. However, developing generalized artificial intelligence models for medical data often requires a large number of labeled images representing various disease signs, and most models are typically task-specific, focusing on major retinal diseases. In this study, we developed a Fundus-Specific Pretrained Model (Image+Fundus), a supervised artificial intelligence model trained to detect abnormalities in fundus images. A total of 57,803 images were used to develop this pretrained model, which achieved superior performance across various downstream tasks, indicating that our proposed model outperforms other general methods. Our Image+Fundus model offers a generalized approach to improve model performance while reducing the number of labeled datasets required. Additionally, it provides more disease-specific insights into fundus images, with visualizations generated by our model. These disease-specific foundation models are invaluable in enhancing the performance and efficiency of deep learning models in the field of fundus imaging.