Automatic segmentation of coronary artery tree based on multiscale Gabor filtering and transition region extraction

2011 ◽  
Author(s):  
Fang Wang ◽  
Guozhu Wang ◽  
Lie Kang ◽  
Juan Wang
2012 ◽  
Vol 217-219 ◽  
pp. 1964-1967
Author(s):  
Tong Tong ◽  
Yan Cai ◽  
Da Wei Sun ◽  
Peng Liu

In allusion to the complex images of weld defects, weak contrast between the target and the background, a new segmentation method based on gray level difference transition region extraction is proposed. The paper analyzes the characteristic of weld defects, and then low-pass filtering and contrast enhanced are used to enhance the clarity. Finally, we extract the transition region and confirm a threshold for defects segmentation. The experimental results show that the method can extract the transition region more accurate, and segment the image much better in complex environment.


2017 ◽  
Vol 3 (1) ◽  
pp. 9-17 ◽  
Author(s):  
Sándor Miklós Szilágyi ◽  
Monica Marton Popovici ◽  
László Szilágyi

AbstractCoronary artery disease represents one of the leading reasons of death worldwide, and acute coronary syndromes are their most devastating consequences. It is extremely important to identify the patients at risk for developing an acute myocardial infarction, and this goal can be achieved using noninvasive imaging techniques. Coronary computed tomography angiography (CCTA) is currently one of the most reliable methods used for assessing the coronary arteries; however, its use in emergency settings is sometimes limited due to time constraints. This paper presents the main characteristics of plaque vulnerability, the role of CCTA in the assessment of vulnerable plaques, and automatic segmentation techniques of the coronary artery tree based on CT angiography images. A detailed inventory of existing methods is given, representing the state-of-the-art of computational methods applied in vascular system segmentation, focusing on the current applications in acute coronary syndromes.


2008 ◽  
Author(s):  
Carlos Castro ◽  
Miguel �ngel Luengo-Oroz ◽  
Andr� Santos ◽  
Mar�a J. Ledesma-Carbayo

Automatic segmentation and tracking of the coronary artery tree from Cardiac Multislice-CT images is an important goal to improve the diagnosis and treatment of coronary artery disease. This paper presents a semi-automatic algorithm (one input point per vessel) based on morphological grayscale local reconstructions in 3D images devoted to the extraction of the coronary artery tree. The algorithm has been evaluated in the framework of the Coronary Artery Tracking Challenge 2008 [1], obtaining consistent results in overlapping measurements (a mean of 70% of the vessel well tracked). Poor results in accuracy measurements suggest that future work should refine the centerline extraction. The algorithm can be efficiently implemented and its general strategy can be easily extrapolated to a completely automated centerline extraction or to a user interactive vessel extraction.


2013 ◽  
Vol 2013 ◽  
pp. 1-9 ◽  
Author(s):  
Ying Li ◽  
Wei Chen ◽  
Kaijun Liu ◽  
Yi Wu ◽  
Yonglin Chen ◽  
...  

Noncalcified plaques (NCPs) are associated with the presence of lipid-core plaques that are prone to rupture. Thus, it is important to detect and monitor the development of NCPs. Contrast-enhanced coronary Computed Tomography Angiography (CTA) is a potential imaging technique to identify atherosclerotic plaques in the whole coronary tree, but it fails to provide information about vessel walls. In order to overcome the limitations of coronary CTA and provide more meaningful quantitative information for percutaneous coronary intervention (PCI), we proposed a Voxel-Map based on mathematical morphology to quantitatively analyze the noncalcified plaques on a three-dimensional coronary artery wall model (3D-CAWM). This approach is a combination of Voxel-Map analysis techniques, plaque locating, and anatomical location related labeling, which show more detailed and comprehensive coronary tree wall visualization.


Sign in / Sign up

Export Citation Format

Share Document