Point-guided modeling and segmentation of myocardium for low dose cardiac CT images

Yixun Liu, Marcelo Souto Nacif, Songtao Liu, Christopher Sibley, David A. Bluemke, Ronald M. Summers, Jianhua Yao

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

2 Citations (Scopus)

Abstract

Cardiac CT is emerging as a preferable modality to detect myocardial stress/rest perfusion; however the insufficient contrast of myocardium on CT image makes its segmentation difficult. In this paper, we present a point-guided modeling and deformable model-based segmentation method. This method first builds a triangular surface model of myocardium through Bézier contour fitting based on a few points selected by clinicians. Then, a deformable model-based segmentation method is developed to refine the segmentation result. The experiments on 8 cases show the accuracy of the segmentation in terms of true positive volume fraction, false positive volume fractions, and average surface distance can reach 91.0%, 0.3%, and 0.6mm, respectively. The comparison between the proposed method and a graph cut-based method is performed. The results demonstrate that this method is effective in improving the accuracy further.

Original languageEnglish (US)
Title of host publicationProceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
Pages5327-5330
Number of pages4
DOIs
StatePublished - 2012
Externally publishedYes
Event34th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2012 - San Diego, CA, United States
Duration: Aug 28 2012Sep 1 2012

Other

Other34th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2012
CountryUnited States
CitySan Diego, CA
Period8/28/129/1/12

Fingerprint

Myocardium
Volume fraction
Perfusion
Experiments

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Biomedical Engineering
  • Health Informatics

Cite this

Liu, Y., Nacif, M. S., Liu, S., Sibley, C., Bluemke, D. A., Summers, R. M., & Yao, J. (2012). Point-guided modeling and segmentation of myocardium for low dose cardiac CT images. In Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS (pp. 5327-5330). [6347197] https://doi.org/10.1109/EMBC.2012.6347197

Point-guided modeling and segmentation of myocardium for low dose cardiac CT images. / Liu, Yixun; Nacif, Marcelo Souto; Liu, Songtao; Sibley, Christopher; Bluemke, David A.; Summers, Ronald M.; Yao, Jianhua.

Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS. 2012. p. 5327-5330 6347197.

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

Liu, Y, Nacif, MS, Liu, S, Sibley, C, Bluemke, DA, Summers, RM & Yao, J 2012, Point-guided modeling and segmentation of myocardium for low dose cardiac CT images. in Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS., 6347197, pp. 5327-5330, 34th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2012, San Diego, CA, United States, 8/28/12. https://doi.org/10.1109/EMBC.2012.6347197
Liu Y, Nacif MS, Liu S, Sibley C, Bluemke DA, Summers RM et al. Point-guided modeling and segmentation of myocardium for low dose cardiac CT images. In Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS. 2012. p. 5327-5330. 6347197 https://doi.org/10.1109/EMBC.2012.6347197
Liu, Yixun ; Nacif, Marcelo Souto ; Liu, Songtao ; Sibley, Christopher ; Bluemke, David A. ; Summers, Ronald M. ; Yao, Jianhua. / Point-guided modeling and segmentation of myocardium for low dose cardiac CT images. Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS. 2012. pp. 5327-5330
@inproceedings{2f3630612c0c46af9af2fd11c20c06b4,
title = "Point-guided modeling and segmentation of myocardium for low dose cardiac CT images",
abstract = "Cardiac CT is emerging as a preferable modality to detect myocardial stress/rest perfusion; however the insufficient contrast of myocardium on CT image makes its segmentation difficult. In this paper, we present a point-guided modeling and deformable model-based segmentation method. This method first builds a triangular surface model of myocardium through B{\'e}zier contour fitting based on a few points selected by clinicians. Then, a deformable model-based segmentation method is developed to refine the segmentation result. The experiments on 8 cases show the accuracy of the segmentation in terms of true positive volume fraction, false positive volume fractions, and average surface distance can reach 91.0{\%}, 0.3{\%}, and 0.6mm, respectively. The comparison between the proposed method and a graph cut-based method is performed. The results demonstrate that this method is effective in improving the accuracy further.",
author = "Yixun Liu and Nacif, {Marcelo Souto} and Songtao Liu and Christopher Sibley and Bluemke, {David A.} and Summers, {Ronald M.} and Jianhua Yao",
year = "2012",
doi = "10.1109/EMBC.2012.6347197",
language = "English (US)",
isbn = "9781424441198",
pages = "5327--5330",
booktitle = "Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS",

}

TY - GEN

T1 - Point-guided modeling and segmentation of myocardium for low dose cardiac CT images

AU - Liu, Yixun

AU - Nacif, Marcelo Souto

AU - Liu, Songtao

AU - Sibley, Christopher

AU - Bluemke, David A.

AU - Summers, Ronald M.

AU - Yao, Jianhua

PY - 2012

Y1 - 2012

N2 - Cardiac CT is emerging as a preferable modality to detect myocardial stress/rest perfusion; however the insufficient contrast of myocardium on CT image makes its segmentation difficult. In this paper, we present a point-guided modeling and deformable model-based segmentation method. This method first builds a triangular surface model of myocardium through Bézier contour fitting based on a few points selected by clinicians. Then, a deformable model-based segmentation method is developed to refine the segmentation result. The experiments on 8 cases show the accuracy of the segmentation in terms of true positive volume fraction, false positive volume fractions, and average surface distance can reach 91.0%, 0.3%, and 0.6mm, respectively. The comparison between the proposed method and a graph cut-based method is performed. The results demonstrate that this method is effective in improving the accuracy further.

AB - Cardiac CT is emerging as a preferable modality to detect myocardial stress/rest perfusion; however the insufficient contrast of myocardium on CT image makes its segmentation difficult. In this paper, we present a point-guided modeling and deformable model-based segmentation method. This method first builds a triangular surface model of myocardium through Bézier contour fitting based on a few points selected by clinicians. Then, a deformable model-based segmentation method is developed to refine the segmentation result. The experiments on 8 cases show the accuracy of the segmentation in terms of true positive volume fraction, false positive volume fractions, and average surface distance can reach 91.0%, 0.3%, and 0.6mm, respectively. The comparison between the proposed method and a graph cut-based method is performed. The results demonstrate that this method is effective in improving the accuracy further.

UR - http://www.scopus.com/inward/record.url?scp=84870801932&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84870801932&partnerID=8YFLogxK

U2 - 10.1109/EMBC.2012.6347197

DO - 10.1109/EMBC.2012.6347197

M3 - Conference contribution

SN - 9781424441198

SP - 5327

EP - 5330

BT - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS

ER -