A Machine Learning-Based Method for Intracoronary OCT Segmentation and Vulnerable Coronary Plaque Cap Thickness Quantification

Xiaoya Guo; Dalin Tang; David Molony; Chun Yang; Habib Samady; Jie Zheng; Gary S. Mintz; Akiko Maehara; Liang Wang; Xuan Pei; Zhi Yong Li; Genshan Ma; Don P. Giddens

doi:10.1142/S0219876218420082

A Machine Learning-Based Method for Intracoronary OCT Segmentation and Vulnerable Coronary Plaque Cap Thickness Quantification

Xiaoya Guo, Dalin Tang, David Molony, Chun Yang, Habib Samady, Jie Zheng, Gary S. Mintz, Akiko Maehara, Liang Wang, Xuan Pei, Zhi Yong Li, Genshan Ma, Don P. Giddens

Research output: Contribution to journal › Article › peer-review

19 Scopus citations

Abstract

Accurate cap thickness quantification is of fundamental importance for vulnerable plaque detection in cardiovascular research. A segmentation method for intracoronary optical coherence tomography (OCT) image based on least squares support vector machine (LS-SVM) was performed to characterize plaque component borders and quantify fibrous cap thickness. Manual segmentation of OCT images were performed by experts based on combination of virtual-histology intravascular ultrasound (VH-IVUS) and OCT images and used as gold standard. The segmentation methods based on LS-SVM provided accurate plaque cap thickness (an 8.6% error by LS-SVM vs. 71% error by IVUS50) serving as solid basis for plaque modeling and assessment.

Original language	English
Article number	1842008
Journal	International Journal of Computational Methods
Volume	16
Issue number	3
DOIs	https://doi.org/10.1142/S0219876218420082
State	Published - May 1 2019

Keywords

LS-SVM
OCT
Vulnerable plaque
cap thickness
coronary
segmentation

Access to Document

10.1142/S0219876218420082

Cite this

Guo, X., Tang, D., Molony, D., Yang, C., Samady, H., Zheng, J., Mintz, G. S., Maehara, A., Wang, L., Pei, X., Li, Z. Y., Ma, G., & Giddens, D. P. (2019). A Machine Learning-Based Method for Intracoronary OCT Segmentation and Vulnerable Coronary Plaque Cap Thickness Quantification. International Journal of Computational Methods, 16(3), Article 1842008. https://doi.org/10.1142/S0219876218420082

@article{6d21bab2473b40aab1b745e5ae8c6e69,

title = "A Machine Learning-Based Method for Intracoronary OCT Segmentation and Vulnerable Coronary Plaque Cap Thickness Quantification",

abstract = "Accurate cap thickness quantification is of fundamental importance for vulnerable plaque detection in cardiovascular research. A segmentation method for intracoronary optical coherence tomography (OCT) image based on least squares support vector machine (LS-SVM) was performed to characterize plaque component borders and quantify fibrous cap thickness. Manual segmentation of OCT images were performed by experts based on combination of virtual-histology intravascular ultrasound (VH-IVUS) and OCT images and used as gold standard. The segmentation methods based on LS-SVM provided accurate plaque cap thickness (an 8.6% error by LS-SVM vs. 71% error by IVUS50) serving as solid basis for plaque modeling and assessment.",

keywords = "LS-SVM, OCT, Vulnerable plaque, cap thickness, coronary, segmentation",

author = "Xiaoya Guo and Dalin Tang and David Molony and Chun Yang and Habib Samady and Jie Zheng and Mintz, {Gary S.} and Akiko Maehara and Liang Wang and Xuan Pei and Li, {Zhi Yong} and Genshan Ma and Giddens, {Don P.}",

note = "Publisher Copyright: {\textcopyright} 2019 World Scientific Publishing Company.",

year = "2019",

month = may,

day = "1",

doi = "10.1142/S0219876218420082",

language = "English",

volume = "16",

journal = "International Journal of Computational Methods",

issn = "0219-8762",

number = "3",

}

Guo, X, Tang, D, Molony, D, Yang, C, Samady, H, Zheng, J, Mintz, GS, Maehara, A, Wang, L, Pei, X, Li, ZY, Ma, G & Giddens, DP 2019, 'A Machine Learning-Based Method for Intracoronary OCT Segmentation and Vulnerable Coronary Plaque Cap Thickness Quantification', International Journal of Computational Methods, vol. 16, no. 3, 1842008. https://doi.org/10.1142/S0219876218420082

TY - JOUR

T1 - A Machine Learning-Based Method for Intracoronary OCT Segmentation and Vulnerable Coronary Plaque Cap Thickness Quantification

AU - Guo, Xiaoya

AU - Tang, Dalin

AU - Molony, David

AU - Yang, Chun

AU - Samady, Habib

AU - Zheng, Jie

AU - Mintz, Gary S.

AU - Maehara, Akiko

AU - Wang, Liang

AU - Pei, Xuan

AU - Li, Zhi Yong

AU - Ma, Genshan

AU - Giddens, Don P.

PY - 2019/5/1

Y1 - 2019/5/1

N2 - Accurate cap thickness quantification is of fundamental importance for vulnerable plaque detection in cardiovascular research. A segmentation method for intracoronary optical coherence tomography (OCT) image based on least squares support vector machine (LS-SVM) was performed to characterize plaque component borders and quantify fibrous cap thickness. Manual segmentation of OCT images were performed by experts based on combination of virtual-histology intravascular ultrasound (VH-IVUS) and OCT images and used as gold standard. The segmentation methods based on LS-SVM provided accurate plaque cap thickness (an 8.6% error by LS-SVM vs. 71% error by IVUS50) serving as solid basis for plaque modeling and assessment.

AB - Accurate cap thickness quantification is of fundamental importance for vulnerable plaque detection in cardiovascular research. A segmentation method for intracoronary optical coherence tomography (OCT) image based on least squares support vector machine (LS-SVM) was performed to characterize plaque component borders and quantify fibrous cap thickness. Manual segmentation of OCT images were performed by experts based on combination of virtual-histology intravascular ultrasound (VH-IVUS) and OCT images and used as gold standard. The segmentation methods based on LS-SVM provided accurate plaque cap thickness (an 8.6% error by LS-SVM vs. 71% error by IVUS50) serving as solid basis for plaque modeling and assessment.

KW - LS-SVM

KW - OCT

KW - Vulnerable plaque

KW - cap thickness

KW - coronary

KW - segmentation

UR - http://www.scopus.com/inward/record.url?scp=85063060651&partnerID=8YFLogxK

U2 - 10.1142/S0219876218420082

DO - 10.1142/S0219876218420082

M3 - Article

AN - SCOPUS:85063060651

SN - 0219-8762

VL - 16

JO - International Journal of Computational Methods

JF - International Journal of Computational Methods

IS - 3

M1 - 1842008

ER -

A Machine Learning-Based Method for Intracoronary OCT Segmentation and Vulnerable Coronary Plaque Cap Thickness Quantification

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this