Automatic segmentation of the left-ventricular cavity and atrium in 3D ultrasound using graph cuts and the radial symmetry transform

Radford Juang, Elliot R. McVeigh, Beatrice Hoffmann, David Yuh, Philippe Burlina

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

Abstract

In this paper, we propose a graph-based method for fullyautomatic segmentation of the left ventricle and atrium in 3D ultrasound (3DUS) volumes. Our method requires no user input and can segment volumes with open and closed mitral valves. We utilize the radial symmetry transform to determine a central axis along which the 3D volume is warped into a cylindrical coordinate space. A graph is constructed for the volume in this space and a min-cut algorithm is applied to segment the left ventricle and atrium from the background. Since segmentation in the cylindrical coordinate space is defined as finding a boundary between the left (interior) and right (exterior) sides, we obviate the need for user specified seeds. The segmented results are transformed back to the Cartesian coordinate space. Experiments using intraoperative 3D ultrasound data show promising results.

Original languageEnglish (US)
Title of host publicationProceedings - International Symposium on Biomedical Imaging
Pages606-609
Number of pages4
DOIs
StatePublished - 2011
Event2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11 - Chicago, IL, United States
Duration: Mar 30 2011Apr 2 2011

Other

Other2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11
CountryUnited States
CityChicago, IL
Period3/30/114/2/11

Fingerprint

Heart Atria
Heart Ventricles
Ultrasonics
Mitral Valve
Seed
Seeds
Experiments

Keywords

  • 3D Ultrasound
  • Graph cuts
  • Radial Symmetry Transform
  • Segmentation

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Cite this

Juang, R., McVeigh, E. R., Hoffmann, B., Yuh, D., & Burlina, P. (2011). Automatic segmentation of the left-ventricular cavity and atrium in 3D ultrasound using graph cuts and the radial symmetry transform. In Proceedings - International Symposium on Biomedical Imaging (pp. 606-609). [5872480] https://doi.org/10.1109/ISBI.2011.5872480

Automatic segmentation of the left-ventricular cavity and atrium in 3D ultrasound using graph cuts and the radial symmetry transform. / Juang, Radford; McVeigh, Elliot R.; Hoffmann, Beatrice; Yuh, David; Burlina, Philippe.

Proceedings - International Symposium on Biomedical Imaging. 2011. p. 606-609 5872480.

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

Juang, R, McVeigh, ER, Hoffmann, B, Yuh, D & Burlina, P 2011, Automatic segmentation of the left-ventricular cavity and atrium in 3D ultrasound using graph cuts and the radial symmetry transform. in Proceedings - International Symposium on Biomedical Imaging., 5872480, pp. 606-609, 2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11, Chicago, IL, United States, 3/30/11. https://doi.org/10.1109/ISBI.2011.5872480
Juang R, McVeigh ER, Hoffmann B, Yuh D, Burlina P. Automatic segmentation of the left-ventricular cavity and atrium in 3D ultrasound using graph cuts and the radial symmetry transform. In Proceedings - International Symposium on Biomedical Imaging. 2011. p. 606-609. 5872480 https://doi.org/10.1109/ISBI.2011.5872480
Juang, Radford ; McVeigh, Elliot R. ; Hoffmann, Beatrice ; Yuh, David ; Burlina, Philippe. / Automatic segmentation of the left-ventricular cavity and atrium in 3D ultrasound using graph cuts and the radial symmetry transform. Proceedings - International Symposium on Biomedical Imaging. 2011. pp. 606-609
@inproceedings{3c58b7d854f944b79f7799d931436bbc,
title = "Automatic segmentation of the left-ventricular cavity and atrium in 3D ultrasound using graph cuts and the radial symmetry transform",
abstract = "In this paper, we propose a graph-based method for fullyautomatic segmentation of the left ventricle and atrium in 3D ultrasound (3DUS) volumes. Our method requires no user input and can segment volumes with open and closed mitral valves. We utilize the radial symmetry transform to determine a central axis along which the 3D volume is warped into a cylindrical coordinate space. A graph is constructed for the volume in this space and a min-cut algorithm is applied to segment the left ventricle and atrium from the background. Since segmentation in the cylindrical coordinate space is defined as finding a boundary between the left (interior) and right (exterior) sides, we obviate the need for user specified seeds. The segmented results are transformed back to the Cartesian coordinate space. Experiments using intraoperative 3D ultrasound data show promising results.",
keywords = "3D Ultrasound, Graph cuts, Radial Symmetry Transform, Segmentation",
author = "Radford Juang and McVeigh, {Elliot R.} and Beatrice Hoffmann and David Yuh and Philippe Burlina",
year = "2011",
doi = "10.1109/ISBI.2011.5872480",
language = "English (US)",
isbn = "9781424441280",
pages = "606--609",
booktitle = "Proceedings - International Symposium on Biomedical Imaging",

}

TY - GEN

T1 - Automatic segmentation of the left-ventricular cavity and atrium in 3D ultrasound using graph cuts and the radial symmetry transform

AU - Juang, Radford

AU - McVeigh, Elliot R.

AU - Hoffmann, Beatrice

AU - Yuh, David

AU - Burlina, Philippe

PY - 2011

Y1 - 2011

N2 - In this paper, we propose a graph-based method for fullyautomatic segmentation of the left ventricle and atrium in 3D ultrasound (3DUS) volumes. Our method requires no user input and can segment volumes with open and closed mitral valves. We utilize the radial symmetry transform to determine a central axis along which the 3D volume is warped into a cylindrical coordinate space. A graph is constructed for the volume in this space and a min-cut algorithm is applied to segment the left ventricle and atrium from the background. Since segmentation in the cylindrical coordinate space is defined as finding a boundary between the left (interior) and right (exterior) sides, we obviate the need for user specified seeds. The segmented results are transformed back to the Cartesian coordinate space. Experiments using intraoperative 3D ultrasound data show promising results.

AB - In this paper, we propose a graph-based method for fullyautomatic segmentation of the left ventricle and atrium in 3D ultrasound (3DUS) volumes. Our method requires no user input and can segment volumes with open and closed mitral valves. We utilize the radial symmetry transform to determine a central axis along which the 3D volume is warped into a cylindrical coordinate space. A graph is constructed for the volume in this space and a min-cut algorithm is applied to segment the left ventricle and atrium from the background. Since segmentation in the cylindrical coordinate space is defined as finding a boundary between the left (interior) and right (exterior) sides, we obviate the need for user specified seeds. The segmented results are transformed back to the Cartesian coordinate space. Experiments using intraoperative 3D ultrasound data show promising results.

KW - 3D Ultrasound

KW - Graph cuts

KW - Radial Symmetry Transform

KW - Segmentation

UR - http://www.scopus.com/inward/record.url?scp=80055056272&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80055056272&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2011.5872480

DO - 10.1109/ISBI.2011.5872480

M3 - Conference contribution

AN - SCOPUS:80055056272

SN - 9781424441280

SP - 606

EP - 609

BT - Proceedings - International Symposium on Biomedical Imaging

ER -