Hemorrhage Diabetic Retinopathy Detection based on Fundus Image using Neural Network and FCM Segmentation

Abstract

Hemorrhage Diabetic Retinopathy is a type of diabetes that attacks the blood vessels of the retina. This disease can cause blindness, but early treatment can minimize this. This research proposes a method of detecting blood vessels in the retina caused by Hemorrhage Diabetic Retinopathy. Detection is based on the Fundus image based on several stages of preprocessing, segmentation, and detection. At the preprocessing stage, the fundus image with the RGB image format is taken the green channel to do a contrast enhancement operation with CLAHE and segmentation with FCM. Then the detection is done using the Neural Network method. At the experimental stage, 100 testing images are used which are divided into two classes, namely Hemorrhage and Non-Hemorrhage. Detection results showed from 100 images, only one image was detected incorrectly, so it can be concluded that the detection accuracy reached 99%.