Detection of Diabetic Retinopathy Using Principal Component Analysis and Deep Neural Networks

Diabetic Retinopathy (DR) is a common problem of diabetes mellitus, which causes lesions on the retina that effect vision. If it is not identified early, it can lead to blindness. Early detection of DR and treatment can significantly reduce the risk of vision loss.  In this paper, Principal component analysis technique is used for selecting the best features and deep neural network is used for classifying the presence and absence of DR.