Classification of diabetic and normal fundus images using new deep learning method

Diabetic Retinopathy (DR) is a complication resulting from diabetes due to changes in the retinal blood vessels. The person may lose eyesight because of damaged blood vessels. Although diabetes cannot be cured, but diabetic retinopathy can be treated successfully with laser surgery. So far, there has been a lot of research for diabetes diagnosis and classification of eye images by machine-learning algorithm and neural network, but these algorithms are good for a few images and features are extracted from pictures by manual or semi-automatic methods. With the emergence of deep learning leading to very good results in various areas of computer vision, the Convolutional Neural Network (CNN) was used by researchers as one of the most active algorithms in this area. One of the areas where this type of network has achieved very good results is the classification of the images. In this article, one of the available architectures of the deep convolutional neural network called ResNet is reviewed and will be used for classification of eye fundus Images into two groups of normal and diabetic images. This architecture has been used on the collection of eye fundus images available on the Kaggel website and simulation result has achieved 85% accuracy and 86% sensitivity. Classification of diabetic and normal fundus images using new deep learning method Mehdi Torabian Esfahani, Mahsa Ghaderi, Raheleh Kafiyeh 234