Title: Review on retinal blood vessel segmentation - an algorithmic perspective

Authors: Pearl Mary Samuel; Thanikaiselvan Veeramalai

Addresses: School of Electronics Engineering, VIT, Vellore, India ' School of Electronics Engineering, VIT, Vellore, India

Abstract: Medical image processing has progressed in leaps and bounds with the advent of radical medical imaging modalities. Blood vessel segmentation from the retinal fundus image is very useful in the diagnosis of chronic vascular diseases, arteriosclerosis, diabetic retinopathy, hypertension, etc. This review paper aims to bring out the existing algorithms developed for the segmentation of vessels in the fundus. This paper covers various segmentation approaches categorised under template matching, multi-scale approach, region growing, active contour model and pattern recognition methods. Pattern recognition is further classified as unsupervised, supervised and deep learning approaches. Performance metrics such as accuracy, specificity, sensitivity, and area under the curve measures for these algorithms performed on the appropriate retinal databases are tabulated and discussed. Moreover, this paper discusses the impact of retinal blood vessel segmentation in screening cardiovascular and cerebrovascular diseases. Also, this paper recommends a universal blood vessel segmentation algorithm for the medical vasculature images.

Keywords: diabetic retinopathy; supervised learning; convolutional neural network; CNN; deep neural network; DNN; matched filter; unsupervised learning; fully convolutional neural network; retina; blood vessels; segmentation; region growing; pathology.

DOI: 10.1504/IJBET.2020.110362

International Journal of Biomedical Engineering and Technology, 2020 Vol.34 No.1, pp.75 - 105

Received: 21 Oct 2019
Accepted: 31 Mar 2020
Published online: 15 Oct 2020 *

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