Detecting Lesion Characteristics of Diabetic Retinopathy Using Machine Learning and Computer Vision

Abstract

One indicator of the severity of diabetic retinopathy is the existence of lesion characteristics in the eyes such as microaneurysm, hemorrhages, exudates, and neovascularization. Without proper early medical attention, this lesion could lead to blindness. Considering its importance, a system that could detect such lesions will be beneficial. This paper investigates the lesion characteristics of diabetic retinopathy from fundus images such as microaneurysm (redsmalldots), exudates, hemorrhages, and neovascularization. In this study, we present three of feature extraction methods, i.e., Local Binary Pattern (LBP), Gray Level Co-Occurrence Matrix (GLCM) and Segmentation Fractal Texture Analysis (SFTA). K-Nearest Neighbor (KNN) and Support Vector Machine (SVM) chosen as classifiers for classifying five classes (redsmalldots, hemorrhages, hard exudates, soft exudates, and neovascularization). The data used in this research obtained from DiaretDB0 database. The experimental results show that our proposed method can detect the lesion characteristics of diabetic retinopathy with higher accuracy of 86,84% and 96% for SVM and KNN, respectively.