A Segmentation Method of Coronary Angiograms Based on Multi-scale Filtering and Region-Growing
Shan Wang, Bonian Li, Shoujun Zhou · 2012
In this paper, we propose a simple and powerful method for segmentation of the coronary artery in angiograms, which combines Hessian matrix multi-scale filtering and region-growing. In this method, Hessian matrix multi-scale filtering is used to enhance vessel in angiographic images. The multi-seed region-growing algorithm is used to extract the coronary artery tree from the enhanced images. As considering the characteristics of the X-ray angiographic images and the advantages from both, the proposed method is sensitive to the vessel-like structures and robust to noise in the angiograms. Using this method, both the coronary artery trees and most of smaller distal vessels could be extracted clearly. The results show that the proposed method is suitable for the segmentation of coronary angiograms, and is available for further accurate quantitative analysis to coronary angiograms.