Region Growing Segmentation Method for Extracting Vessel Structures from Coronary Cine-angiograms

Abstract

The coronary cine-angiogram (CCA) is an invasive medical image modality which is used to determine the luminal obstructions or stenosis in the Coronary Arteries (CA). CCA based quantitative assessment of vascular morphology is a demanding area in medical diagnosis and segmentation of blood vessels in CCAs is one of the mandatory step in this endeavor. The accurate segmentation of CAs in Angiogram is a challenging task due to various reported reasons. In order to overcome this challenge, we proposed a region growing segmentation method which implements using morphological image processing operations and flood fill method. It can extract the boundary of main CA visualized in the processed CCA completely. The result of the proposed method reveals that this proposed segmentation method possesses 90.89% accuracy to segment the CAs related to the selected Angiography views. This segmentation results can be further enhanced to determine the functional severity of the CA and this study laid the foundation to improve the Angiography based diagnosis technique.