An Efficient DenseNet for Diabetic Retinopathy Screening

Abstract

This study aims to propose a novel deep learning framework, i.e., efficient DenseNet, for identifying diabetic retinopathy severity levels in retinal images. Diabetic retinopathy is an eye condition that damages blood vessels in the retina. Detecting diabetic retinopathy at the early stage can avoid retinal detachment and effects leading to blindness in diabetic adults. A thin-layered efficient DenseNet model has been proposed with fewer training learnable parameters, leading to higher classification accuracy than the other deep learning models. The proposed deep learning framework for diabetic retinopathy severity level detection has an inbuilt automatic pre-processing module. Afterward, the efficient DenseNet model and classifier will provide data augmentation and higher-level feature extraction. The proposed efficient DenseNet framework is trained and tested using 13000 retinal fundus images within the diabetic retinopathy database and combined with the k-nearest neighbor classifier demonstrating the best classification accuracy of 98.40%.