Retinal vessel segmentation using multi-scale textons derived from keypoints

Zhang, Lei, Fisher, Mark and Wang, Wenjia (2015) Retinal vessel segmentation using multi-scale textons derived from keypoints. Computerized Medical Imaging and Graphics, 45. pp. 47-56. ISSN 0895-6111

Preview

PDF (CMIG-D-14-00273R1 (revised submission)) - Accepted Version Available under License Creative Commons Attribution Non-commercial No Derivatives. Download (1MB) | Preview

Abstract

This paper presents a retinal vessel segmentation algorithm which uses a texton dictionary to classify vessel/non-vessel pixels. However, in contrast to previous work where filter parameters are learnt from manually labelled image pixels our filter parameters are derived from a smaller set of image features that we call keypoints. A Gabor filter bank, parameterised empirically by ROC analysis, is used to extract keypoints representing significant scale specific vessel features using an approach inspired by the SIFT algorithm. We first determine keypoints using a validation set and then derive seeds from these points to initialise a k-means clustering algorithm which builds a texton dictionary from another training set. During testing we use a simple 1-NN classifier to identify vessel/non-vessel pixels and evaluate our system using the DRIVE database. We achieve average values of sensitivity, specificity and accuracy of 78.12%, 96.68% and 95.05% respectively. We find that clusters of filter responses from keypoints are more robust than those derived from hand-labelled pixels. This, in turn yields textons more representative of vessel/non-vessel classes and mitigates problems arising due to intra and inter-observer variability.

Item Type:	Article
Uncontrolled Keywords:	retinal vessels,image segmentation,texton,keypoints
Faculty \ School:	Faculty of Science > School of Computing Sciences
UEA Research Groups:	Faculty of Science > Research Groups > Data Science and Statistics
Depositing User:	Pure Connector
Date Deposited:	02 Dec 2015 13:00
Last Modified:	21 Oct 2022 01:05
URI:	https://ueaeprints.uea.ac.uk/id/eprint/55632
DOI:	10.1016/j.compmedimag.2015.07.006

Downloads

Actions (login required)

View Item