Cardiac MR image segmentation using deformable models

A. Gupta, L. von Kurowski, A. Singh, Davi Geiger, C. C. Liang, M. Y. Chiu, L. P. Adler, M. Haacke, D. L. Wilson

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

Abstract

We describe efficient and robust deformable model based techniques for segmentation of ventricular boundaries in cardiac MR images. Starting with a user specified approximate boundary or an interior point of the left ventricle for one ED slice, our algorithms generate contours for inner and outer walls, and automatically propagate them to other slices in the ED phase (spatial propagation) and to slices in all the phases (temporal propagation) of the cardiac study. The algorithms are based on steepest descent as well as dynamic programming strategies integrated via multiscale analysis. The ventricular boundaries are used to construct a 3-D model for visualization and to compute volume based diagnostic quantities. The algorithms have been incorporated into a user interface which can load, sort, visualize, and analyze a cardiac study in less than 10 minutes. The system has been tested on a dozen volunteers and patients (1000+ images) with excellent results.

Original languageEnglish (US)
Title of host publicationComputers in Cardiology
PublisherPubl by IEEE
Pages747-750
Number of pages4
ISBN (Print)0818654708
StatePublished - 1993
EventProceedings of the 1993 Conference on Computers in Cardiology - London, UK
Duration: Sep 5 1993Sep 8 1993

Other

OtherProceedings of the 1993 Conference on Computers in Cardiology
CityLondon, UK
Period9/5/939/8/93

Fingerprint

Image segmentation
Dynamic programming
User interfaces
Heart Ventricles
Volunteers
Visualization

ASJC Scopus subject areas

  • Software
  • Cardiology and Cardiovascular Medicine

Cite this

Gupta, A., von Kurowski, L., Singh, A., Geiger, D., Liang, C. C., Chiu, M. Y., ... Wilson, D. L. (1993). Cardiac MR image segmentation using deformable models. In Computers in Cardiology (pp. 747-750). Publ by IEEE.

Cardiac MR image segmentation using deformable models. / Gupta, A.; von Kurowski, L.; Singh, A.; Geiger, Davi; Liang, C. C.; Chiu, M. Y.; Adler, L. P.; Haacke, M.; Wilson, D. L.

Computers in Cardiology. Publ by IEEE, 1993. p. 747-750.

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

Gupta, A, von Kurowski, L, Singh, A, Geiger, D, Liang, CC, Chiu, MY, Adler, LP, Haacke, M & Wilson, DL 1993, Cardiac MR image segmentation using deformable models. in Computers in Cardiology. Publ by IEEE, pp. 747-750, Proceedings of the 1993 Conference on Computers in Cardiology, London, UK, 9/5/93.
Gupta A, von Kurowski L, Singh A, Geiger D, Liang CC, Chiu MY et al. Cardiac MR image segmentation using deformable models. In Computers in Cardiology. Publ by IEEE. 1993. p. 747-750
Gupta, A. ; von Kurowski, L. ; Singh, A. ; Geiger, Davi ; Liang, C. C. ; Chiu, M. Y. ; Adler, L. P. ; Haacke, M. ; Wilson, D. L. / Cardiac MR image segmentation using deformable models. Computers in Cardiology. Publ by IEEE, 1993. pp. 747-750
@inproceedings{01f86965b6c84048851793cb752a01c3,
title = "Cardiac MR image segmentation using deformable models",
abstract = "We describe efficient and robust deformable model based techniques for segmentation of ventricular boundaries in cardiac MR images. Starting with a user specified approximate boundary or an interior point of the left ventricle for one ED slice, our algorithms generate contours for inner and outer walls, and automatically propagate them to other slices in the ED phase (spatial propagation) and to slices in all the phases (temporal propagation) of the cardiac study. The algorithms are based on steepest descent as well as dynamic programming strategies integrated via multiscale analysis. The ventricular boundaries are used to construct a 3-D model for visualization and to compute volume based diagnostic quantities. The algorithms have been incorporated into a user interface which can load, sort, visualize, and analyze a cardiac study in less than 10 minutes. The system has been tested on a dozen volunteers and patients (1000+ images) with excellent results.",
author = "A. Gupta and {von Kurowski}, L. and A. Singh and Davi Geiger and Liang, {C. C.} and Chiu, {M. Y.} and Adler, {L. P.} and M. Haacke and Wilson, {D. L.}",
year = "1993",
language = "English (US)",
isbn = "0818654708",
pages = "747--750",
booktitle = "Computers in Cardiology",
publisher = "Publ by IEEE",

}

TY - GEN

T1 - Cardiac MR image segmentation using deformable models

AU - Gupta, A.

AU - von Kurowski, L.

AU - Singh, A.

AU - Geiger, Davi

AU - Liang, C. C.

AU - Chiu, M. Y.

AU - Adler, L. P.

AU - Haacke, M.

AU - Wilson, D. L.

PY - 1993

Y1 - 1993

N2 - We describe efficient and robust deformable model based techniques for segmentation of ventricular boundaries in cardiac MR images. Starting with a user specified approximate boundary or an interior point of the left ventricle for one ED slice, our algorithms generate contours for inner and outer walls, and automatically propagate them to other slices in the ED phase (spatial propagation) and to slices in all the phases (temporal propagation) of the cardiac study. The algorithms are based on steepest descent as well as dynamic programming strategies integrated via multiscale analysis. The ventricular boundaries are used to construct a 3-D model for visualization and to compute volume based diagnostic quantities. The algorithms have been incorporated into a user interface which can load, sort, visualize, and analyze a cardiac study in less than 10 minutes. The system has been tested on a dozen volunteers and patients (1000+ images) with excellent results.

AB - We describe efficient and robust deformable model based techniques for segmentation of ventricular boundaries in cardiac MR images. Starting with a user specified approximate boundary or an interior point of the left ventricle for one ED slice, our algorithms generate contours for inner and outer walls, and automatically propagate them to other slices in the ED phase (spatial propagation) and to slices in all the phases (temporal propagation) of the cardiac study. The algorithms are based on steepest descent as well as dynamic programming strategies integrated via multiscale analysis. The ventricular boundaries are used to construct a 3-D model for visualization and to compute volume based diagnostic quantities. The algorithms have been incorporated into a user interface which can load, sort, visualize, and analyze a cardiac study in less than 10 minutes. The system has been tested on a dozen volunteers and patients (1000+ images) with excellent results.

UR - http://www.scopus.com/inward/record.url?scp=0027851976&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0027851976&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0027851976

SN - 0818654708

SP - 747

EP - 750

BT - Computers in Cardiology

PB - Publ by IEEE

ER -