Development of an automated system to classify retinal vessels into arteries and veins

Authors:
Marc Saez;Sonia GonzáLez-VáZquez;Manuel GonzáLez-Penedo;Maria AntòNia Barceló;Marta Pena-Seijo;Gabriel Coll De Tuero;Antonio Pose-Reino
Affiliations:
Research Group on Statistics, Applied Economic and Health, GRECS,1 University of Girona, Spain and CIBER of Epidemiology and Public Health, CIBERESP, Spain;Artificial Vision and Pattern Recognition Group, VARPA, Department of Computing, University of A Coruña, Spain;Artificial Vision and Pattern Recognition Group, VARPA, Department of Computing, University of A Coruña, Spain;Research Group on Statistics, Applied Economic and Health, GRECS,1 University of Girona, Spain and CIBER of Epidemiology and Public Health, CIBERESP, Spain;Internal Medicine Service, Hospital de Conxo, Santiago de Compostela, Spain;CIBER of Epidemiology and Public Health, CIBERESP, Spain and Research Unit, Health Care Institute, Girona, Spain;Internal Medicine Service, Hospital de Conxo, Santiago de Compostela, Spain
Venue:
Computer Methods and Programs in Biomedicine
Year:
2012

Citing 6
Cited 0

Data Clustering: Theory, Algorithms, and Applications (ASA-SIAM Series on Statistics and Applied Probability)

Data Clustering: Theory, Algorithms, and Applications (ASA-SIAM Series on Statistics and Applied Probability)
Separation of the retinal vascular graph in arteries and veins based upon structural knowledge

Image and Vision Computing
Semi-automated evaluation tool for retinal vasculopathy

Computer Methods and Programs in Biomedicine
Graph-based methods for retinal mosaicing and vascular characterization

GbRPR'07 Proceedings of the 6th IAPR-TC-15 international conference on Graph-based representations in pattern recognition
Live-vessel: extending livewire for simultaneous extraction of optimal medial and boundary paths in vascular images

MICCAI'07 Proceedings of the 10th international conference on Medical image computing and computer-assisted intervention
Improvements in retinal vessel clustering techniques: towards the automatic computation of the arterio venous ratio

Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

There are some evidence of the association between the calibre of the retinal blood vessels and hypertension. Computer-assisted procedures have been proposed to measure the calibre of retinal blood vessels from high-resolution photopraphs. Most of them are in fact semi-automatic. Our objective in this paper is twofold, to develop a totally automated system to classify retinal vessels into arteries and veins and to compare the measurements of the arteriolar-to-venular diameter ratio (AVR) computed from the system with those computed from observers. Our classification method consists of four steps. First, we obtain the vascular tree structure using a segmentation algorithm. Then, we extract the profiles. After that, we select the best feature vectors to distinguish between veins and arteries. Finally, we use a clustering algorithm to classify each detected vessel as an artery or a vein. Our results show that compared with an observer-based method, our method achieves high sensitivity and specificity in the automated detection of retinal arteries and veins. In addition the system is robust enough independently of the radii finally chosen, which makes it more trustworthy in its clinical application. We conclude that the system represents an automatic method of detecting arteries and veins to measure the calibre of retinal microcirculation across digital pictures of the eye fundus.