Diabetic retinopathy screening based on CNN

This contribution is focused on image recognition methods that are suitable for diagnostic purposes in ophthalmology. Particularly it is an identification of bright lesions in fundus images that are a side effect of disease called diabetic retinopathy. To achieve the goal, we used retinal images from the publicly available database, MESSIDOR. These images were pre-processed, transformed and normalized, in order to enhance their quality and to increase the amount of input data. For classification purposes we split them into multiple groups (clusters). To classify the images according to whether or not they have some types of anomalies, we proposed a convolutional neural network (CNN) with 4 convolutional layers. We've used accuracy criteria and the cross-validation method to evaluate the classification efficiency.