Vessel Boundary Delineation on Fundus Images Using Graph-Based Approach

This paper proposes an algorithm to measure the width of retinal vessels in fundus photographs using graph-based algorithm to segment both vessel edges simultaneously. First, the simultaneous two-boundary segmentation problem is modeled as a two-slice, 3-D surface segmentation problem, which is further converted into the problem of computing a minimum closed set in a node-weighted graph. An initial segmentation is generated from a vessel probability image. We use the REVIEW database to evaluate diameter measurement performance. The algorithm is robust and estimates the vessel width with subpixel accuracy. The method is used to explore the relationship between the average vessel width and the distance from the optic disc in 600 subjects.

I. Introduction

Complications of cardiovascular disease, such as stroke and myocardial infarction, have high mortality and morbidity. The retinal blood vessels are the vessels that are the easiest to image noninvasively, and it has been shown that a decreased ratio of arterial to venous retinal vessel width (the AV ratio) forms an independent risk factor for stroke and myocardial infarct, as well as for eye disease [1]–[3]. In retinal images, the boundaries of the blood column form a reliable proxy for vessel diameter. Automated determination of the AV-ratio is therefore of high interest, but also complicated, because retinal vessel width and the contrast to the background vary greatly across retinal images. We have previously demonstrated a fully automated algorithm for determination of the AV ratio from fundus color photographs, by detecting the retinal blood vessels, determining whether these are arteries or veins, measuring their width, and determining the AV-ratio in an automatically determined region of interest [4]. In a previous study, we used a splat based technique to determine vessel width [5]. However, graph-based approaches to determine the location of the vessel boundary have the potential for greater speed and accuracy, as they are known to be globally optimal [6], [7]. In addition to AV-ratio analysis, automated determination of vessel width measurement based on segmentation of both vessel boundaries would also allow the geometry of the retinal vessels to be quantified, as the geometry is also affected by cardiovascular disease, diabetes, and retinal disease. Finally, accurate determination of the vessel boundary may allow local pathologic vascular changes such as tortuosity and vessel beading to be measured accurately [8].