TY - JOUR
T1 - Automated framework for detecting lumen and media-adventitia borders in intravascular ultrasound images
AU - Gao, Zhifan
AU - Hau, William Kongto
AU - Lu, Minhua
AU - Huang, Wenhua
AU - Zhang, Heye
AU - Wu, Wanqing
AU - Liu, Xin
AU - Zhang, Yuan-Ting
PY - 2015/7
Y1 - 2015/7
N2 - An automated framework for detecting lumen and media-adventitia borders in intravascular ultrasound images was developed on the basis of an adaptive region-growing method and an unsupervised clustering method. To demonstrate the capability of the framework, linear regression, Bland-Altman analysis and distance analysis were used to quantitatively investigate the correlation, agreement and spatial distance, respectively, between our detected borders and manually traced borders in 337 intravascular ultrasound images in vivo acquired from six patients. The results of these investigations revealed good correlation (r 5 0.99), good agreement (.96.82% of results within the 95% confidence interval) and small average distance errors (lumen border: 0.08 mm, media-adventitia border: 0.10 mm) between the borders generated by the automated framework and the manual tracing method. The proposed framework was found to be effective in detecting lumen and media- adventitia borders in intravascular ultrasound images, indicating its potential for use in routine studies of vascular disease.
AB - An automated framework for detecting lumen and media-adventitia borders in intravascular ultrasound images was developed on the basis of an adaptive region-growing method and an unsupervised clustering method. To demonstrate the capability of the framework, linear regression, Bland-Altman analysis and distance analysis were used to quantitatively investigate the correlation, agreement and spatial distance, respectively, between our detected borders and manually traced borders in 337 intravascular ultrasound images in vivo acquired from six patients. The results of these investigations revealed good correlation (r 5 0.99), good agreement (.96.82% of results within the 95% confidence interval) and small average distance errors (lumen border: 0.08 mm, media-adventitia border: 0.10 mm) between the borders generated by the automated framework and the manual tracing method. The proposed framework was found to be effective in detecting lumen and media- adventitia borders in intravascular ultrasound images, indicating its potential for use in routine studies of vascular disease.
KW - Intravascular
KW - Region growing
KW - Ultrasound
KW - Unsupervised clustering
UR - http://www.scopus.com/inward/record.url?scp=84942986731&partnerID=8YFLogxK
UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-84942986731&origin=recordpage
U2 - 10.1016/j.ultrasmedbio.2015.03.022
DO - 10.1016/j.ultrasmedbio.2015.03.022
M3 - RGC 21 - Publication in refereed journal
C2 - 25922134
SN - 0301-5629
VL - 41
SP - 2001
EP - 2021
JO - Ultrasound in Medicine and Biology
JF - Ultrasound in Medicine and Biology
IS - 7
ER -