Title: Automated segmentation of foveal avascular zone in digital colour retinal fundus images

Authors: Hanung Adi Nugroho; Dhimas Arief Dharmawan; Litasari; Latifah Listyalina

Addresses: Department of Electrical Engineering and Information Technology, Faculty of Engineering, Universitas Gadjah Mada, Yogyakarta, Indonesia ' Department of Electrical Engineering and Information Technology, Faculty of Engineering, Universitas Gadjah Mada, Yogyakarta, Indonesia ' Department of Electrical Engineering and Information Technology, Faculty of Engineering, Universitas Gadjah Mada, Yogyakarta, Indonesia ' Faculty of Science and Technology - Electrical Engineering, Universitas Respati Yogyakarta, Yogyakarta, Indonesia

Abstract: One of the diabetes complications, diabetic retinopathy (DR), is characterised by the damage of retinal vessels, especially on the macular region. Located at the centre of retina and appeared as a cloudy dark spot in colour fundus image, macula is a fundamental area for high acumen of colour vision. Foveal avascular zone (FAZ) is located at the centre of macula and encircled by interconnected capillary beds. FAZ has a round or oval shape with an average diameter of 500-600 μm. In DR patients, the FAZ becomes larger due to the loss of perifoveal retinal vessels. In this study, a scheme for automated segmentation of FAZ in colour fundus images is proposed. The scheme consists of four stages: pre-processing, image enhancement, vessels segmentation and FAZ segmentation. Result shows that the average sensitivity, specificity and accuracy obtained are 80.86%, 99.17% and 97.49%. This indicates that the proposed scheme has successfully detected the FAZ.

Keywords: accuracy; diabetes; diabetic retinopathy; foveal avascular zone; FAZ; fundus images; matched filter; macula; perifoveal retinal vessels; sensitivity; specificity; image segmentation; digital images; colour images; retina; colour vision.

DOI: 10.1504/IJBET.2017.082223

International Journal of Biomedical Engineering and Technology, 2017 Vol.23 No.1, pp.1 - 18

Received: 03 Sep 2015
Accepted: 08 Feb 2016

Published online: 13 Feb 2017 *

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