Diabetic retinopathy detection using convolutional neural network with residual blocks

Abstract

Diabetic Retinopathy (DR) is a disease that happens in the patient eyes of long-term diabetics. It also affects the retina which causes eye blindness. Therefore, DR has to be detected at its early stage to decrease the risk of blindness. Several researchers suggested approaches to detect the blood abnormalities (hemorrhages, Hard and soft exudates, and micro-aneurysms) in the retina images using deep learning models. The limitation with these approaches is the performance degradation and required high training time. To solve this, we suggest a model for automated detection of DR severity using a convolutional neural network (CNN) and residual blocks (DRCNNRB). Deep learning models work effectively when they have been trained on vast datasets. Data Augmentation helps to increase the training samples as a result avoids the data imbalance problem. In our model, basic data augmentation techniques such as zooming, shearing, rotation, flipping, and rescaling are applied in DRCNNRB to solve the data imbalance problem. Pre-processing techniques are used to enhance the quality of the image. Extensive experimental results on the Diabetic Retinopathy 2015 Data Colored Resized database conclude that DRCNNRB provides better performance compared to other state-of-the-art works. Thus, DRCNNRB achieves better efficiency for real-time diagnosis.