A Novel Hybrid Machine Learning Model for Auto-Classification of Retinal Diseases
This work addresses the problem of limited access to specialists for retinal disease diagnosis, but it is incremental as it combines existing methods.
The authors tackled automatic clinical diagnosis of retinal diseases by proposing a hybrid model combining SVM and DNNs, achieving 89.73% accuracy on a new dataset of 32 disease classes, which is comparable to professional ophthalmologists.
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.