Title: New methodology based on images processing for the diabetic retinopathy disease classification

Authors: Ilham Bensmail; Mahammed Messadi; Amel Feroui; Amine Lazouni; Abdelhafid Bessaid

Addresses: Biomedical Laboratory, Department of Biomedical Engineering, Technology Faculty, University of Tlemcen 13000, Algeria ' Biomedical Laboratory, Department of Biomedical Engineering, Technology Faculty, University of Tlemcen 13000, Algeria ' Biomedical Laboratory, Department of Biomedical Engineering, Technology Faculty, University of Tlemcen 13000, Algeria ' Biomedical Laboratory, Department of Biomedical Engineering, Technology Faculty, University of Tlemcen 13000, Algeria ' Biomedical Laboratory, Department of Biomedical Engineering, Technology Faculty, University of Tlemcen 13000, Algeria

Abstract: Diabetes is a chronic disease that cannot be cured, but can be treated and controlled. In the long run, a high blood sugar level causes complications, especially in the eyes, which leads to the development of diabetic retinopathy (DR). Poor care could cause blindness to the sick person. In this paper, we propose a new system for early detection of the DR. The tested algorithm includes several important phases, especially, the detection of the retinal lesions caused by the disease (microaneurysms and haemorrhages), through pretreatment and segmentation processes, as well as the classification of the different stages of non-proliferative DR. Several classifiers have been tested and the support vector machine (SVM) has given a very good sensitivity, specificity, and accuracy of 97.56%, 99.01%, 97.52%, respectively. These values show that our approach can be used for diagnostic assistance in ophthalmology.

Keywords: diabetic retinopathy; microaneurysms; machine learning; haemorrhages; classification; K-nearest neighbour; KNN; support vector machine; SVM; multilayer perceptron; MLP; radial basic function; RBF; C4.5.

DOI: 10.1504/IJBET.2022.124017

International Journal of Biomedical Engineering and Technology, 2022 Vol.39 No.2, pp.170 - 187

Received: 29 Jan 2019
Accepted: 26 Apr 2019
Published online: 11 Jul 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article