Title: Optimisation of dataset for classification of diabetic retinopathy using support vector machine with minimal processing

Authors: Amol Golwankar; Pranav Pailkar; Purvika Patil; Rajendra G. Sutar

Addresses: Department of Electronics, Sardar Patel Institute of Technology, Mumbai 400058, Maharashtra, India ' Department of Electronics, Sardar Patel Institute of Technology, Mumbai 400058, Maharashtra, India ' Department of Electronics, Sardar Patel Institute of Technology, Mumbai 400058, Maharashtra, India ' Department of Electronics, Sardar Patel Institute of Technology, Mumbai 400058, Maharashtra, India

Abstract: Diabetic retinopathy is a disease observed in the retinal region caused by a reduced level of insulin in a body or when the pancreas cannot properly process it. If the disease is not recognised in time it may cause permanent blindness. This paper illustrates an optimised approach towards developing a classifier that helps in diagnosing the disease and helps in checking its severity. A large dataset of 1,900 retinal photographs obtained from Kaggle's Diabetic Retinopathy Detection Dataset was used. The proposed classifier classifies the retinal pictures based on the relevant feature values calculated from extracted primary features of the pre-processed and raw images. Classification is performed by support vector machine algorithm that classifies the retinal images into stages or categories such as normal image with no signs of retinopathy, image with mild retinopathy, image with moderate retinopathy, image with severe retinopathy and image showing proliferation of blood vessels respectively, with the accuracy of 91.2 percentages.

Keywords: diabetic retinopathy; retinal images; pre-processing; feature extraction; machine learning; support vector machine; SVM.

DOI: 10.1504/IJBET.2021.120192

International Journal of Biomedical Engineering and Technology, 2021 Vol.37 No.4, pp.382 - 394

Received: 14 Jul 2018
Accepted: 18 Dec 2018
Published online: 11 Jan 2022 *

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