Quantitative analysis of vascular dimension and plaque composition in coronary multidetector computed tomography images

Mark E. Olszewski, Andreas Wahle, Mani Vembar, Les Ciancibello, Arthur Kerner, Rafael Beyar, Eduard Ghersin, Krishna Subramanyan, Milan Sonka

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The noninvasive assessment of coronary atherosclerosis holds great promise for the future of cardiovascular medicine, and multidetector computed tomography (MDCT) has recently taken the lead in this area. Earlier studies have shown the ability of MDCT to visualize the coronary lumen and various types of atherosclerotic plaque. The aims of this project are to design, implement, and validate a complete system for the automated, quantitative analysis of coronary MDCT images. The developed system uses graph algorithms and knowledge-based cost functions to automatically segment the lumen and wall, and then uses pattern classification techniques to identify and quantify the tissue types found within the detected vascular wall. The system has been validated in comparison with expert tracings and labels, as well as in comparison with intravascular ultrasound (IVUS). In the former, the radial position of the lumen and adventitia were compared at 360 corresponding angular locations in 299 vascular cross sections (from 13 vessels in 5 patients: 5 RCA, 4 LAD, 4 LCX). Results show a border positioning error of 0.150 ± 0.090 mm unsigned / 0.007 ± 0.001 mm signed for the lumen, and 0.210 ± 0.120 mm unsigned / 0.020 ± 0.030 mm signed for the vessel wall. In the comparison with IVUS, the luminal and vascular cross sectional areas were compared in 7 vessels; good correlation was shown for both the lumen (R=0.83) and the vessel wall (R=0.76). The plaque characterization algorithm correctly classified 92% of calcified plaques and 87% of non-calcified plaques.

Original languageEnglish
Title of host publicationProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume6143 I
DOIs
StatePublished - Jun 30 2006
Externally publishedYes
EventMedical Imaging 2006: Physiology, Function, and Structure from Medical Images - San Diego, CA, United States
Duration: Feb 12 2006Feb 14 2006

Other

OtherMedical Imaging 2006: Physiology, Function, and Structure from Medical Images
CountryUnited States
CitySan Diego, CA
Period2/12/062/14/06

Fingerprint

Multidetector computed tomography
Ultrasonics
Chemical analysis
Cost functions
Medicine
Pattern recognition
Labels
Lead
Tissue

Keywords

  • Coronary heart disease
  • Multidetector computed tomography
  • Plaque
  • Segmentation

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Olszewski, M. E., Wahle, A., Vembar, M., Ciancibello, L., Kerner, A., Beyar, R., ... Sonka, M. (2006). Quantitative analysis of vascular dimension and plaque composition in coronary multidetector computed tomography images. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE (Vol. 6143 I). [614308] https://doi.org/10.1117/12.657992

Quantitative analysis of vascular dimension and plaque composition in coronary multidetector computed tomography images. / Olszewski, Mark E.; Wahle, Andreas; Vembar, Mani; Ciancibello, Les; Kerner, Arthur; Beyar, Rafael; Ghersin, Eduard; Subramanyan, Krishna; Sonka, Milan.

Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 6143 I 2006. 614308.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Olszewski, ME, Wahle, A, Vembar, M, Ciancibello, L, Kerner, A, Beyar, R, Ghersin, E, Subramanyan, K & Sonka, M 2006, Quantitative analysis of vascular dimension and plaque composition in coronary multidetector computed tomography images. in Progress in Biomedical Optics and Imaging - Proceedings of SPIE. vol. 6143 I, 614308, Medical Imaging 2006: Physiology, Function, and Structure from Medical Images, San Diego, CA, United States, 2/12/06. https://doi.org/10.1117/12.657992
Olszewski ME, Wahle A, Vembar M, Ciancibello L, Kerner A, Beyar R et al. Quantitative analysis of vascular dimension and plaque composition in coronary multidetector computed tomography images. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 6143 I. 2006. 614308 https://doi.org/10.1117/12.657992
Olszewski, Mark E. ; Wahle, Andreas ; Vembar, Mani ; Ciancibello, Les ; Kerner, Arthur ; Beyar, Rafael ; Ghersin, Eduard ; Subramanyan, Krishna ; Sonka, Milan. / Quantitative analysis of vascular dimension and plaque composition in coronary multidetector computed tomography images. Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 6143 I 2006.
@inproceedings{30c60c2a93c84c408c4389fc573757d1,
title = "Quantitative analysis of vascular dimension and plaque composition in coronary multidetector computed tomography images",
abstract = "The noninvasive assessment of coronary atherosclerosis holds great promise for the future of cardiovascular medicine, and multidetector computed tomography (MDCT) has recently taken the lead in this area. Earlier studies have shown the ability of MDCT to visualize the coronary lumen and various types of atherosclerotic plaque. The aims of this project are to design, implement, and validate a complete system for the automated, quantitative analysis of coronary MDCT images. The developed system uses graph algorithms and knowledge-based cost functions to automatically segment the lumen and wall, and then uses pattern classification techniques to identify and quantify the tissue types found within the detected vascular wall. The system has been validated in comparison with expert tracings and labels, as well as in comparison with intravascular ultrasound (IVUS). In the former, the radial position of the lumen and adventitia were compared at 360 corresponding angular locations in 299 vascular cross sections (from 13 vessels in 5 patients: 5 RCA, 4 LAD, 4 LCX). Results show a border positioning error of 0.150 ± 0.090 mm unsigned / 0.007 ± 0.001 mm signed for the lumen, and 0.210 ± 0.120 mm unsigned / 0.020 ± 0.030 mm signed for the vessel wall. In the comparison with IVUS, the luminal and vascular cross sectional areas were compared in 7 vessels; good correlation was shown for both the lumen (R=0.83) and the vessel wall (R=0.76). The plaque characterization algorithm correctly classified 92{\%} of calcified plaques and 87{\%} of non-calcified plaques.",
keywords = "Coronary heart disease, Multidetector computed tomography, Plaque, Segmentation",
author = "Olszewski, {Mark E.} and Andreas Wahle and Mani Vembar and Les Ciancibello and Arthur Kerner and Rafael Beyar and Eduard Ghersin and Krishna Subramanyan and Milan Sonka",
year = "2006",
month = "6",
day = "30",
doi = "10.1117/12.657992",
language = "English",
isbn = "0819461865",
volume = "6143 I",
booktitle = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",

}

TY - GEN

T1 - Quantitative analysis of vascular dimension and plaque composition in coronary multidetector computed tomography images

AU - Olszewski, Mark E.

AU - Wahle, Andreas

AU - Vembar, Mani

AU - Ciancibello, Les

AU - Kerner, Arthur

AU - Beyar, Rafael

AU - Ghersin, Eduard

AU - Subramanyan, Krishna

AU - Sonka, Milan

PY - 2006/6/30

Y1 - 2006/6/30

N2 - The noninvasive assessment of coronary atherosclerosis holds great promise for the future of cardiovascular medicine, and multidetector computed tomography (MDCT) has recently taken the lead in this area. Earlier studies have shown the ability of MDCT to visualize the coronary lumen and various types of atherosclerotic plaque. The aims of this project are to design, implement, and validate a complete system for the automated, quantitative analysis of coronary MDCT images. The developed system uses graph algorithms and knowledge-based cost functions to automatically segment the lumen and wall, and then uses pattern classification techniques to identify and quantify the tissue types found within the detected vascular wall. The system has been validated in comparison with expert tracings and labels, as well as in comparison with intravascular ultrasound (IVUS). In the former, the radial position of the lumen and adventitia were compared at 360 corresponding angular locations in 299 vascular cross sections (from 13 vessels in 5 patients: 5 RCA, 4 LAD, 4 LCX). Results show a border positioning error of 0.150 ± 0.090 mm unsigned / 0.007 ± 0.001 mm signed for the lumen, and 0.210 ± 0.120 mm unsigned / 0.020 ± 0.030 mm signed for the vessel wall. In the comparison with IVUS, the luminal and vascular cross sectional areas were compared in 7 vessels; good correlation was shown for both the lumen (R=0.83) and the vessel wall (R=0.76). The plaque characterization algorithm correctly classified 92% of calcified plaques and 87% of non-calcified plaques.

AB - The noninvasive assessment of coronary atherosclerosis holds great promise for the future of cardiovascular medicine, and multidetector computed tomography (MDCT) has recently taken the lead in this area. Earlier studies have shown the ability of MDCT to visualize the coronary lumen and various types of atherosclerotic plaque. The aims of this project are to design, implement, and validate a complete system for the automated, quantitative analysis of coronary MDCT images. The developed system uses graph algorithms and knowledge-based cost functions to automatically segment the lumen and wall, and then uses pattern classification techniques to identify and quantify the tissue types found within the detected vascular wall. The system has been validated in comparison with expert tracings and labels, as well as in comparison with intravascular ultrasound (IVUS). In the former, the radial position of the lumen and adventitia were compared at 360 corresponding angular locations in 299 vascular cross sections (from 13 vessels in 5 patients: 5 RCA, 4 LAD, 4 LCX). Results show a border positioning error of 0.150 ± 0.090 mm unsigned / 0.007 ± 0.001 mm signed for the lumen, and 0.210 ± 0.120 mm unsigned / 0.020 ± 0.030 mm signed for the vessel wall. In the comparison with IVUS, the luminal and vascular cross sectional areas were compared in 7 vessels; good correlation was shown for both the lumen (R=0.83) and the vessel wall (R=0.76). The plaque characterization algorithm correctly classified 92% of calcified plaques and 87% of non-calcified plaques.

KW - Coronary heart disease

KW - Multidetector computed tomography

KW - Plaque

KW - Segmentation

UR - http://www.scopus.com/inward/record.url?scp=33745383786&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33745383786&partnerID=8YFLogxK

U2 - 10.1117/12.657992

DO - 10.1117/12.657992

M3 - Conference contribution

SN - 0819461865

SN - 9780819461865

VL - 6143 I

BT - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

ER -