Auto-Classification of Retinal Diseases in the Limit of Sparse Data Using a Two-Streams Machine Learning Model

TL;DR

This paper introduces a hybrid machine learning model combining SVM and DNNs for retinal disease diagnosis, utilizing a new dataset, EyeNet2, and achieves accuracy comparable to ophthalmologists, especially effective with limited data.

Contribution

The paper presents a novel two-stream hybrid model and a new retinal disease dataset, advancing automatic diagnosis in data-scarce clinical settings.

Findings

Achieved 90.43% diagnosis accuracy on EyeNet2

Model performance comparable to professional ophthalmologists

Effective in scenarios with limited data

Abstract

Automatic clinical diagnosis of retinal diseases has emerged as a promising approach to facilitate discovery in areas with limited access to specialists. Based on the fact that fundus structure and vascular disorders are the main characteristics of retinal diseases, we propose a novel visual-assisted diagnosis hybrid model mixing the support vector machine (SVM) and deep neural networks (DNNs). Furthermore, we present a new clinical retina dataset, called EyeNet2, for ophthalmology incorporating 52 retina diseases classes. Using EyeNet2, our model achieves 90.43\% diagnosis accuracy, and the model performance is comparable to the professional ophthalmologists.