A Novel Hybrid Machine Learning Model for Auto-Classification of Retinal Diseases

TL;DR

This paper introduces a hybrid machine learning model combining DNNs and SVMs for automatic retinal disease diagnosis, achieving high accuracy comparable to ophthalmologists, and provides a new dataset for 32 retina disease classes.

Contribution

It presents a novel hybrid model integrating DNNs and SVMs for retinal disease classification and introduces a new comprehensive retina disease dataset.

Findings

Achieved 89.73% diagnosis accuracy

Model performance comparable to ophthalmologists

Introduced a new retina disease dataset with 32 classes

Abstract

Automatic clinical diagnosis of retinal diseases has emerged as a promising approach to facilitate discovery in areas with limited access to specialists. We propose a novel visual-assisted diagnosis hybrid model based on the support vector machine (SVM) and deep neural networks (DNNs). The model incorporates complementary strengths of DNNs and SVM. Furthermore, we present a new clinical retina label collection for ophthalmology incorporating 32 retina diseases classes. Using EyeNet, our model achieves 89.73% diagnosis accuracy and the model performance is comparable to the professional ophthalmologists.