Table of Contents Author Guidelines Submit a Manuscript
BioMed Research International
Volume 2016, Article ID 3530251, 7 pages
http://dx.doi.org/10.1155/2016/3530251
Research Article

Automated Segmentation of Coronary Arteries Based on Statistical Region Growing and Heuristic Decision Method

1College of Information Science and Technology, Beijing Normal University, Beijing 100875, China
2Department of Radiology, Navy General Hospital, Beijing 100048, China
3Peking University Cancer Hospital & Institute, Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education), Beijing 100142, China

Received 17 July 2016; Accepted 26 September 2016

Academic Editor: Yong Xia

Copyright © 2016 Yun Tian et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Abstract

The segmentation of coronary arteries is a vital process that helps cardiovascular radiologists detect and quantify stenosis. In this paper, we propose a fully automated coronary artery segmentation from cardiac data volume. The method is built on a statistics region growing together with a heuristic decision. First, the heart region is extracted using a multi-atlas-based approach. Second, the vessel structures are enhanced via a 3D multiscale line filter. Next, seed points are detected automatically through a threshold preprocessing and a subsequent morphological operation. Based on the set of detected seed points, a statistics-based region growing is applied. Finally, results are obtained by setting conservative parameters. A heuristic decision method is then used to obtain the desired result automatically because parameters in region growing vary in different patients, and the segmentation requires full automation. The experiments are carried out on a dataset that includes eight-patient multivendor cardiac computed tomography angiography (CTA) volume data. The DICE similarity index, mean distance, and Hausdorff distance metrics are employed to compare the proposed algorithm with two state-of-the-art methods. Experimental results indicate that the proposed algorithm is capable of performing complete, robust, and accurate extraction of coronary arteries.