Title: Automatic recognition of exudative maculopathy using neural networks

Authors: M. Kalaivani; J.A. Sylvia; Cynthia David; H. Greeshma; C. Jhayachandar; M. Kaushik Prakash

Addresses: Biomedical Engineering, Jerusalem College of Engineering, Chennai 600100, Tamil Nadu, India. ' Jerusalem College of Engineering, Chennai 600100, Tamil Nadu, India. ' Jerusalem College of Engineering, Chennai 600100, Tamil Nadu, India. ' Jerusalem College of Engineering, Chennai 600100, Tamil Nadu, India. ' Jerusalem College of Engineering, Chennai 600100, Tamil Nadu, India. ' Jerusalem College of Engineering, Chennai 600100, Tamil Nadu, India

Abstract: Diabetic retinopathy is a common complication of diabetes, caused by changes in the blood vessels of the retina. Exudates are one of the primary signs of diabetic retinopathy. Hence, detection of exudates is an important diagnostic task. Detection of exudates by ophthalmologists normally takes time and is open to human error. An automatic method for the detection of exudate regions is introduced; the system also detects the exudates in and around the macular region, which indicates an increased severity of disease. We based our work on this technique because it is very fast and requires lower computing power.

Keywords: diabetic retinopathy; exudates; dilated pupil images; macula; exudative maculopathy; neural networks; diabetes; blood vessels; retina; automated detection.

DOI: 10.1504/IJBET.2011.042497

International Journal of Biomedical Engineering and Technology, 2011 Vol.7 No.1, pp.46 - 56

Published online: 21 Jan 2015 *

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