期刊名称：Advanced Computing : an International Journal
印刷版ISSN：2229-726X
电子版ISSN：2229-6727
出版年度：2016
卷号：7
期号：1/2
页码：61
DOI：10.5121/acij.2016.7207
出版社：Academy & Industry Research Collaboration Center (AIRCC)
摘要：Measurements of retinal blood vessel morphology have been shown to be related to the risk ofcardiovascular diseases. The wrong identification of vessels may result in a large variation of thesemeasurements, leading to a wrong clinical diagnosis. In this paper, we address the problem ofautomatically identifying true vessels as a post processing step to vascular structure segmentation. Wemodel the segmented vascular structure as a vessel segment graph and formulate the problem of identifyingvessels as one of finding the optimal forest in the graph given a set of constraints. We design a method tosolve this optimization problem and evaluate it on a large real-world dataset of 2,446 retinal images.Experiment results are analyzed with respect to actual measurements of vessel morphology. The resultsshow that the proposed approach is able to achieve 98.9% pixel precision and 98.7% recall of the truevessels for clean segmented retinal images, and remains robust even when the segmented image is noisy.
