Diabetic retinopathy detection using deep learning based neural network along with machine learning algorithms

Abstract

Diabetic retinopathy (DA) is an eye disease caused by retinal damage as a result of long-term diabetes mellitus. Microaneurysms (MA)are an indicator of DA and are small red spots formed on the retina caused by the ballooning of a weak blood artery.The DA is mainly classified between Proliferate diabetic retinopathy (PDR) and Non-proliferative diabetic retinopathy (NPDR). Non-proliferative is an earlier stage of DA. In our study we will classify the images into 5 stages based on their severity of DA taken from a dataset. The existing modelshave usedLogistic Regression (LR), Support Vector Machine (SVM), gradient boosting techniques such as XGBoost and Logistic Regression with Elastic-Net penalty (LR-EN), to classify wavelet features among the groups. In our project study we used theDeeplearning-based algorithmFast R-CNN (Region Convolutional Neural Network) to build the model and tested its accuracy in training as well as testing the same model with other Machine learning techniques like Decision Tree, k-nearest neighbors (k-NN) classifier, GaussianNaïve Bayes, Kernel-SVM. Our project study shows that Decision Tree had the best training accuracy with 99.31% whereas in case ofthe best predicted testing accuracy it is k-Nearest Neighbors (k-NN) Classifier with 71.29%.