The Classification of Hypertensive Retinopathy using Convolutional Neural Network

Changes in the retina of the eyes may occur due to high blood pressure, hypertensive retinopathy (HR) is a type of eye disease in which there is a change of the blood vessels of the eyes in the eye retina caused by arterial hypertension. HR signs occur because of narrowing of the arteries in the retina, bleeding in the retina of the eye and cotton wool spots. The diagnosis is conventionally performed by an ophthalmologist by performing fundus image analysis to determine the phases of HR disease symptoms. This paper proposes an early detection system of hypertensive retinopathy disease. We propose to use Fundus image as a Convolutional Neural Network (CNN) input to determine whether there are any HR symptoms or not. The proposed system is tested by DRIVE image dataset and base on experiment, the accuracy of proposed method is 98.6%, where the more the number of iterations the higher the accuracy level of the training