Code for the coursework "Identification of Diabetic Retinopathy in retinal fundus images using Convolutional Neural Networks".
Abstract Diabetes retinopathy is one of the main causes of treatable vision impairments in the world. Its diagnosis requires experienced ophthalmologists to identify the presence of retinal lesions in the eye. This paper presents a Convolutional Neural Network (CNN) model for the identification and grading of Diabetic Retinopathy (DR) in retinal fundus images. A subset of 1,000 images of the Diabetic Retinopathy dataset available in Kaggle was used achieving 74.5% of accuracy. The presented CNN was developed in python using Keras framework and executed in the Kaggle server.
Keywords Diabetic Retinopathy, Networks, Medical imaging. Convolutional Neural