Segmentation of the myocardium from myocardial contrast echocardiography

John E. Pickard, Rob L. Janiczek, Scott T. Acton, Jiri Sklenar, John A. Hossack, Sanjiv Kaul

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

2 Citations (Scopus)

Abstract

Myocardial contrast echocardiography (MCE) is a promising new technique that allows quantification of myocardium perfusion and therefore accurate diagnosis of coronary artery disease. MCE data, however, have previously required tedious and time-consuming off-line manual image processing. This paper presents results that demonstrate success of an automatic segmentation approach utilizing active shape models. A shape model was created from a training set of eleven manually drawn contours, which was then applied to twenty-two MCE images. Standard success metrics show that error from this automatic method is comparable to error found among manually drawn contours. Additionally, a more robust calculation of the key blood flow parameters was developed which can accommodate error in the segmentation, verified by high correlation between manually and automatically derived parameters.

Original languageEnglish (US)
Title of host publicationConference Record - Asilomar Conference on Signals, Systems and Computers
EditorsM.B. Matthews
Pages1616-1619
Number of pages4
Volume2
StatePublished - 2004
Externally publishedYes
EventConference Record of the Thirty-Eighth Asilomar Conference on Signals, Systems and Computers - Pacific Grove, CA, United States
Duration: Nov 7 2004Nov 10 2004

Other

OtherConference Record of the Thirty-Eighth Asilomar Conference on Signals, Systems and Computers
CountryUnited States
CityPacific Grove, CA
Period11/7/0411/10/04

Fingerprint

Echocardiography
Image processing
Blood

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Pickard, J. E., Janiczek, R. L., Acton, S. T., Sklenar, J., Hossack, J. A., & Kaul, S. (2004). Segmentation of the myocardium from myocardial contrast echocardiography. In M. B. Matthews (Ed.), Conference Record - Asilomar Conference on Signals, Systems and Computers (Vol. 2, pp. 1616-1619)

Segmentation of the myocardium from myocardial contrast echocardiography. / Pickard, John E.; Janiczek, Rob L.; Acton, Scott T.; Sklenar, Jiri; Hossack, John A.; Kaul, Sanjiv.

Conference Record - Asilomar Conference on Signals, Systems and Computers. ed. / M.B. Matthews. Vol. 2 2004. p. 1616-1619.

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

Pickard, JE, Janiczek, RL, Acton, ST, Sklenar, J, Hossack, JA & Kaul, S 2004, Segmentation of the myocardium from myocardial contrast echocardiography. in MB Matthews (ed.), Conference Record - Asilomar Conference on Signals, Systems and Computers. vol. 2, pp. 1616-1619, Conference Record of the Thirty-Eighth Asilomar Conference on Signals, Systems and Computers, Pacific Grove, CA, United States, 11/7/04.
Pickard JE, Janiczek RL, Acton ST, Sklenar J, Hossack JA, Kaul S. Segmentation of the myocardium from myocardial contrast echocardiography. In Matthews MB, editor, Conference Record - Asilomar Conference on Signals, Systems and Computers. Vol. 2. 2004. p. 1616-1619
Pickard, John E. ; Janiczek, Rob L. ; Acton, Scott T. ; Sklenar, Jiri ; Hossack, John A. ; Kaul, Sanjiv. / Segmentation of the myocardium from myocardial contrast echocardiography. Conference Record - Asilomar Conference on Signals, Systems and Computers. editor / M.B. Matthews. Vol. 2 2004. pp. 1616-1619
@inproceedings{5d8536fc8067467e87c58c52c657db03,
title = "Segmentation of the myocardium from myocardial contrast echocardiography",
abstract = "Myocardial contrast echocardiography (MCE) is a promising new technique that allows quantification of myocardium perfusion and therefore accurate diagnosis of coronary artery disease. MCE data, however, have previously required tedious and time-consuming off-line manual image processing. This paper presents results that demonstrate success of an automatic segmentation approach utilizing active shape models. A shape model was created from a training set of eleven manually drawn contours, which was then applied to twenty-two MCE images. Standard success metrics show that error from this automatic method is comparable to error found among manually drawn contours. Additionally, a more robust calculation of the key blood flow parameters was developed which can accommodate error in the segmentation, verified by high correlation between manually and automatically derived parameters.",
author = "Pickard, {John E.} and Janiczek, {Rob L.} and Acton, {Scott T.} and Jiri Sklenar and Hossack, {John A.} and Sanjiv Kaul",
year = "2004",
language = "English (US)",
volume = "2",
pages = "1616--1619",
editor = "M.B. Matthews",
booktitle = "Conference Record - Asilomar Conference on Signals, Systems and Computers",

}

TY - GEN

T1 - Segmentation of the myocardium from myocardial contrast echocardiography

AU - Pickard, John E.

AU - Janiczek, Rob L.

AU - Acton, Scott T.

AU - Sklenar, Jiri

AU - Hossack, John A.

AU - Kaul, Sanjiv

PY - 2004

Y1 - 2004

N2 - Myocardial contrast echocardiography (MCE) is a promising new technique that allows quantification of myocardium perfusion and therefore accurate diagnosis of coronary artery disease. MCE data, however, have previously required tedious and time-consuming off-line manual image processing. This paper presents results that demonstrate success of an automatic segmentation approach utilizing active shape models. A shape model was created from a training set of eleven manually drawn contours, which was then applied to twenty-two MCE images. Standard success metrics show that error from this automatic method is comparable to error found among manually drawn contours. Additionally, a more robust calculation of the key blood flow parameters was developed which can accommodate error in the segmentation, verified by high correlation between manually and automatically derived parameters.

AB - Myocardial contrast echocardiography (MCE) is a promising new technique that allows quantification of myocardium perfusion and therefore accurate diagnosis of coronary artery disease. MCE data, however, have previously required tedious and time-consuming off-line manual image processing. This paper presents results that demonstrate success of an automatic segmentation approach utilizing active shape models. A shape model was created from a training set of eleven manually drawn contours, which was then applied to twenty-two MCE images. Standard success metrics show that error from this automatic method is comparable to error found among manually drawn contours. Additionally, a more robust calculation of the key blood flow parameters was developed which can accommodate error in the segmentation, verified by high correlation between manually and automatically derived parameters.

UR - http://www.scopus.com/inward/record.url?scp=21644470169&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=21644470169&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:21644470169

VL - 2

SP - 1616

EP - 1619

BT - Conference Record - Asilomar Conference on Signals, Systems and Computers

A2 - Matthews, M.B.

ER -