Detection and Classification of Bifurcation and Branch Points on Retinal Vascular Network

Abstract

Identifying the vascular bifurcation, branch and crossover points in the retinal image is helpful for predicting many cardiovascular diseases and can be used for image registration and biometric features. In this paper, we propose a novel method to detect and classify the vascular bifurcation, branch and crossover points (landmarks) based on the vessel geometrical features. We utilize the vessel's centerline and width information to detect and classify these landmarks, which can be used for image matching in medical diagnosis and biometric security applications. We segment the blood vessels and measure the width from the color retinal images. The geometrical properties of the blood vessels passing through the potential landmarks are obtained. Perceptual grouping and Support Vector Machine (SVM) are used to classify the landmarks into the vascular bifurcations, branchs and crossovers. We evaluate our results by comparing with manually measured bifurcation, branch and crossover points by an expert grader which shows that our automatic method achieved high detection accuracy of 91.84% for bifurcation, 92.23% for branch and 90.12% for crossover points.