Abstract:
Diabetic Retinopathy (DR) is a serious and common complication of diabetes that can lead to vision loss and blindness if not detected and treated early. It is a condition that damages the blood vessels in the retina, the light-sensitive tissue at the back of the eye, causing them to leak blood and other fluids, and eventually leading to the growth of abnormal blood vessels. The severity of DR is usually categorized into five stages based on the degree of damage to the blood vessels and the retina. These stages include no DR, mild non-proliferative DR, moderate non-proliferative DR, severe non-proliferative DR, and proliferative DR. Previously numerous methods have been proposed to address this issue but have not achieved high accuracy for detection of the last three stages with efficient models. Therefore, this work proposes an ensemble approach for the timely and accurate detection of DR using deep learning techniques. In this method, we are implementing convolution neural network models
to process retinal images to recognize lesions and determine the presence and the severity level of diabetic retinopathy. The models’ parameters are optimized using the transfer learning methodology for mapping an image with the corresponding label. The proposed system uses two publicly available datasets APTOS and MESSIDOR, to test and train the models, which contain retinal images with five different severity levels. The proposed system outperforms the previous methods in terms of accuracy. In addition, a web application is designed to make the system accessible to medical professionals and patients, providing a user-friendly interface for uploading retinal images and obtaining the severity classification results. This system could potentially improve the early detection and treatment of diabetic retinopathy, thereby preventing vision loss and blindness.
