<div><div><div><p>Diabetic Retinopathy (DR) is an intricacy of dia- betes that affects the eyes. In this paper, we have proposed a hybrid pre-processing and feature extraction technique named as Microaneurysm Retinal vein Haemorrhage Exudate (MRHE) extraction using Feature Enhancement and Edge Detection (FEED) which can extract all the features in a single step and with very less complexity. To classify the presence of DR, we have used an efficient Deep Convolutional Neural Network (D-CNN), model. The D-CNN model is trained with four salient features namely retinal veins, MA’s, exudates, and haemorrhages which were extracted from the raw images using image-processing techniques. After training and testing the D-CNN model, we were able to classify the presence of DR based on the features extracted from the testing data. To implement this proposed method, we have used a dataset from the STructured Analysis of the Retina (STARE) Database, which comprises of retinal images taken under various imaging conditions using fundus photography. To demonstrate the legitimacy of the proposed method, we have compared our method with the existing DR detection and classification methods such as SVM, ANN,etc.. Performance evaluation results in terms of Accuracy and Recall show that the proposed algorithm outperforms other existing DR classification methods.</p></div></div></div>
Deep Convolutional Neural Network-Based Early Automated Detection of Diabetic Retinopathy Using Fundus Image
