Tracking the Endocardial Border in Artifact-Prone 3D Images

K.Y. Esther Leung, Mikhail G. Danilouchkine, Marijn van Stralen, Nico de Jong, Antonius F.W. van der Steen, J.G. Bosch

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Abstract

Echocardiography is a commonly-used, safe, and noninvasive method for assessing cardiac dysfunction and related coronary artery disease. The analysis of echocardiograms, whether visual or automated, has traditionally been hampered by the presence of ultrasound artifacts, which obscure the moving myocardial wall. In this study, a novel method is proposed for tracking the endocardial surface in 3D ultrasound images. Artifacts which obscure the myocardium are detected in order to improve the quality of cardiac boundary segmentation. The expectation-maximization algorithm is applied in a stationary and dynamic, cardiac-motion frame-of-reference, and weights are derived accordingly. The weights are integrated with an optical-flow based contour tracking method, which incorporates prior knowledge via a statistical model of cardiac motion. Evaluation on 35 three-dimensional echocardiographic sequences shows that this weighed tracking method significantly improves the tracking results. In conclusion, the proposed weights are able to reduce the influence of artifacts, resulting in a more accurate quantitative analysis.
Original languageEnglish
Title of host publication2009 IEEE International Ultrasonics Symposium
Place of PublicationPiscataway, NJ
PublisherIEEE
Number of pages4
ISBN (Electronic)978-1-4244-4390-1
ISBN (Print)978-1-4244-4389-5
DOIs
Publication statusPublished - 20 Sep 2009
EventIEEE International Ultrasonics Symposium, IUS 2009 - Rome, Italy
Duration: 20 Sep 200923 Sep 2009

Conference

ConferenceIEEE International Ultrasonics Symposium, IUS 2009
Abbreviated titleIUS
CountryItaly
CityRome
Period20/09/0923/09/09

Fingerprint

Ultrasonics
Echocardiography
Optical flows
Chemical analysis
Statistical Models

Cite this

Leung, K. Y. E., Danilouchkine, M. G., van Stralen, M., de Jong, N., van der Steen, A. F. W., & Bosch, J. G. (2009). Tracking the Endocardial Border in Artifact-Prone 3D Images. In 2009 IEEE International Ultrasonics Symposium Piscataway, NJ: IEEE. https://doi.org/10.1109/ULTSYM.2009.5442017
Leung, K.Y. Esther ; Danilouchkine, Mikhail G. ; van Stralen, Marijn ; de Jong, Nico ; van der Steen, Antonius F.W. ; Bosch, J.G. / Tracking the Endocardial Border in Artifact-Prone 3D Images. 2009 IEEE International Ultrasonics Symposium. Piscataway, NJ : IEEE, 2009.
@inproceedings{c3750d092a74488bb0d30c86a9760fb5,
title = "Tracking the Endocardial Border in Artifact-Prone 3D Images",
abstract = "Echocardiography is a commonly-used, safe, and noninvasive method for assessing cardiac dysfunction and related coronary artery disease. The analysis of echocardiograms, whether visual or automated, has traditionally been hampered by the presence of ultrasound artifacts, which obscure the moving myocardial wall. In this study, a novel method is proposed for tracking the endocardial surface in 3D ultrasound images. Artifacts which obscure the myocardium are detected in order to improve the quality of cardiac boundary segmentation. The expectation-maximization algorithm is applied in a stationary and dynamic, cardiac-motion frame-of-reference, and weights are derived accordingly. The weights are integrated with an optical-flow based contour tracking method, which incorporates prior knowledge via a statistical model of cardiac motion. Evaluation on 35 three-dimensional echocardiographic sequences shows that this weighed tracking method significantly improves the tracking results. In conclusion, the proposed weights are able to reduce the influence of artifacts, resulting in a more accurate quantitative analysis.",
author = "Leung, {K.Y. Esther} and Danilouchkine, {Mikhail G.} and {van Stralen}, Marijn and {de Jong}, Nico and {van der Steen}, {Antonius F.W.} and J.G. Bosch",
year = "2009",
month = "9",
day = "20",
doi = "10.1109/ULTSYM.2009.5442017",
language = "English",
isbn = "978-1-4244-4389-5",
booktitle = "2009 IEEE International Ultrasonics Symposium",
publisher = "IEEE",
address = "United States",

}

Leung, KYE, Danilouchkine, MG, van Stralen, M, de Jong, N, van der Steen, AFW & Bosch, JG 2009, Tracking the Endocardial Border in Artifact-Prone 3D Images. in 2009 IEEE International Ultrasonics Symposium. IEEE, Piscataway, NJ, IEEE International Ultrasonics Symposium, IUS 2009, Rome, Italy, 20/09/09. https://doi.org/10.1109/ULTSYM.2009.5442017

Tracking the Endocardial Border in Artifact-Prone 3D Images. / Leung, K.Y. Esther; Danilouchkine, Mikhail G.; van Stralen, Marijn; de Jong, Nico; van der Steen, Antonius F.W.; Bosch, J.G.

2009 IEEE International Ultrasonics Symposium. Piscataway, NJ : IEEE, 2009.

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Tracking the Endocardial Border in Artifact-Prone 3D Images

AU - Leung, K.Y. Esther

AU - Danilouchkine, Mikhail G.

AU - van Stralen, Marijn

AU - de Jong, Nico

AU - van der Steen, Antonius F.W.

AU - Bosch, J.G.

PY - 2009/9/20

Y1 - 2009/9/20

N2 - Echocardiography is a commonly-used, safe, and noninvasive method for assessing cardiac dysfunction and related coronary artery disease. The analysis of echocardiograms, whether visual or automated, has traditionally been hampered by the presence of ultrasound artifacts, which obscure the moving myocardial wall. In this study, a novel method is proposed for tracking the endocardial surface in 3D ultrasound images. Artifacts which obscure the myocardium are detected in order to improve the quality of cardiac boundary segmentation. The expectation-maximization algorithm is applied in a stationary and dynamic, cardiac-motion frame-of-reference, and weights are derived accordingly. The weights are integrated with an optical-flow based contour tracking method, which incorporates prior knowledge via a statistical model of cardiac motion. Evaluation on 35 three-dimensional echocardiographic sequences shows that this weighed tracking method significantly improves the tracking results. In conclusion, the proposed weights are able to reduce the influence of artifacts, resulting in a more accurate quantitative analysis.

AB - Echocardiography is a commonly-used, safe, and noninvasive method for assessing cardiac dysfunction and related coronary artery disease. The analysis of echocardiograms, whether visual or automated, has traditionally been hampered by the presence of ultrasound artifacts, which obscure the moving myocardial wall. In this study, a novel method is proposed for tracking the endocardial surface in 3D ultrasound images. Artifacts which obscure the myocardium are detected in order to improve the quality of cardiac boundary segmentation. The expectation-maximization algorithm is applied in a stationary and dynamic, cardiac-motion frame-of-reference, and weights are derived accordingly. The weights are integrated with an optical-flow based contour tracking method, which incorporates prior knowledge via a statistical model of cardiac motion. Evaluation on 35 three-dimensional echocardiographic sequences shows that this weighed tracking method significantly improves the tracking results. In conclusion, the proposed weights are able to reduce the influence of artifacts, resulting in a more accurate quantitative analysis.

U2 - 10.1109/ULTSYM.2009.5442017

DO - 10.1109/ULTSYM.2009.5442017

M3 - Conference contribution

SN - 978-1-4244-4389-5

BT - 2009 IEEE International Ultrasonics Symposium

PB - IEEE

CY - Piscataway, NJ

ER -

Leung KYE, Danilouchkine MG, van Stralen M, de Jong N, van der Steen AFW, Bosch JG. Tracking the Endocardial Border in Artifact-Prone 3D Images. In 2009 IEEE International Ultrasonics Symposium. Piscataway, NJ: IEEE. 2009 https://doi.org/10.1109/ULTSYM.2009.5442017