90 97

Cited 3 times in

Automatic Coronary Artery Segmentation Using Active Search for Branches and Seemingly Disconnected Vessel Segments from Coronary CT Angiography

 Dongjin Han  ;  Hackjoon Shim  ;  Byunghwan Jeon  ;  Yeonggul Jang  ;  Youngtaek Hong  ;  Sunghee Jung  ;  Seongmin Ha  ;  Hyuk-Jae Chang 
 PLoS One, Vol.11(8) : e0156837, 2016 
Journal Title
 PLoS One 
Issue Date
Bayes Theorem ; Computed Tomography Angiography/methods* ; Coronary Angiography/methods* ; Coronary Vessels/anatomy & histology ; Coronary Vessels/diagnostic imaging* ; Humans ; Models, Theoretical ; Stochastic Processes
We propose a Bayesian tracking and segmentation method of coronary arteries on coronary computed tomographic angiography (CCTA). The geometry of coronary arteries including lumen boundary is estimated in Maximum A Posteriori (MAP) framework. Three consecutive sphere based filtering is combined with a stochastic process that is based on the similarity of the consecutive local neighborhood voxels and the geometric constraint of a vessel. It is also founded on the prior knowledge that an artery can be seen locally disconnected and consist of branches which may be seemingly disconnected due to plaque build up. For such problem, an active search method is proposed to find branches and seemingly disconnected but actually connected vessel segments. Several new measures have been developed for branch detection, disconnection check and planar vesselness measure. Using public domain Rotterdam CT dataset, the accuracy of extracted centerline is demonstrated and automatic reconstruction of coronary artery mesh is shown.
Files in This Item:
T201603009.pdf Download
Appears in Collections:
1. Journal Papers (연구논문) > 5. Research Institutes (연구소) > Yonsei Cardiovascular Research Institute (심혈관연구소)
1. Journal Papers (연구논문) > 1. College of Medicine (의과대학) > Dept. of Internal Medicine (내과학교실)
Yonsei Authors
심학준(Shim, Hack Joon)
장혁재(Chang, Hyuck Jae) ORCID logo https://orcid.org/0000-0002-6139-7545
한동진(Han, Dong Jin)
RIS (EndNote)
XLS (Excel)
사서에게 알리기


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.