Detection of Diabetic Retinopathy using Deep Neural Network

Diabetic retinopathy (DR) is a common complication of diabetes which is one of the leading causes of blindness worldwide. However, DR is hard to detect in the early stages and the diagnostic procedure can be time-consuming and abundant expertise is needed. Therefore, we proposed a computer-aided diagnosis method based on a deep learning algorithm to automatically diagnose DR and divide color retinal fundus photographs in to five grades. Besides, a novel pre-processing algorithm is adopted to enhance the quality and uniformity of input retinal images and a transfer learning method to achieve better performance. Finally, the system is evaluated based on a test set with 7023 images and an accuracy of 80.0% and a kappa score of 0.64 are achieved.