Semiautomated four-dimensional computed tomography segmentation using deformable models

Dustin Ragan, George Starkschall, Todd McNutt, Michael Kaus, Thomas Guerrero, Craig W. Stevens

Research output: Contribution to journalArticle

Abstract

The purpose of this work is to demonstrate a proof of feasibility of the application of a commercial prototype deformable model algorithm to the problem of delineation of anatomic structures on four-dimensional (4D) computed tomography (CT) image data sets. We acquired a 4D CT image data set of a patient's thorax that consisted of three-dimensional (3D) image data sets from eight phases in the respiratory cycle. The contours of the right and left lungs, cord, heart, and esophagus were manually delineated on the end inspiration data set. An interactive deformable model algorithm, originally intended for deforming an atlas-based model surface to a 3D CT image data set, was applied in an automated fashion. Triangulations based on the contours generated on each phase were deformed to the CT data set on the succeeding phase to generate the contours on that phase. Deformation was propagated through the eight phases, and the contours obtained on the end inspiration data set were compared with the original manually delineated contours. Structures defined by high-density gradients, such as lungs, cord, and heart, were accurately reproduced, except in regions where other gradient boundaries may have confused the algorithm, such as near bronchi. The algorithm failed to accurately contour the esophagus, a soft-tissue structure completely surrounded by tissue of similar density, without manual interaction. This technique has the potential to facilitate contour delineation in 4D CT image data sets; and future evolution of the software is expected to improve the process.

Original languageEnglish (US)
Pages (from-to)2254-2261
Number of pages8
JournalMedical Physics
Volume32
Issue number7
DOIs
StatePublished - Jul 2005
Externally publishedYes

Fingerprint

Four-Dimensional Computed Tomography
Esophagus
Tomography
Lung
Three-Dimensional Imaging
Datasets
Atlases
Bronchi
Thorax
Software

Keywords

  • 4D imaging
  • CT segmentation
  • Deformable models

ASJC Scopus subject areas

  • Biophysics

Cite this

Ragan, D., Starkschall, G., McNutt, T., Kaus, M., Guerrero, T., & Stevens, C. W. (2005). Semiautomated four-dimensional computed tomography segmentation using deformable models. Medical Physics, 32(7), 2254-2261. https://doi.org/10.1118/1.1929207

Semiautomated four-dimensional computed tomography segmentation using deformable models. / Ragan, Dustin; Starkschall, George; McNutt, Todd; Kaus, Michael; Guerrero, Thomas; Stevens, Craig W.

In: Medical Physics, Vol. 32, No. 7, 07.2005, p. 2254-2261.

Research output: Contribution to journalArticle

Ragan, D, Starkschall, G, McNutt, T, Kaus, M, Guerrero, T & Stevens, CW 2005, 'Semiautomated four-dimensional computed tomography segmentation using deformable models', Medical Physics, vol. 32, no. 7, pp. 2254-2261. https://doi.org/10.1118/1.1929207
Ragan, Dustin ; Starkschall, George ; McNutt, Todd ; Kaus, Michael ; Guerrero, Thomas ; Stevens, Craig W. / Semiautomated four-dimensional computed tomography segmentation using deformable models. In: Medical Physics. 2005 ; Vol. 32, No. 7. pp. 2254-2261.
@article{7077e5b51f4b438ca2382fe0a47c6e2e,
title = "Semiautomated four-dimensional computed tomography segmentation using deformable models",
abstract = "The purpose of this work is to demonstrate a proof of feasibility of the application of a commercial prototype deformable model algorithm to the problem of delineation of anatomic structures on four-dimensional (4D) computed tomography (CT) image data sets. We acquired a 4D CT image data set of a patient's thorax that consisted of three-dimensional (3D) image data sets from eight phases in the respiratory cycle. The contours of the right and left lungs, cord, heart, and esophagus were manually delineated on the end inspiration data set. An interactive deformable model algorithm, originally intended for deforming an atlas-based model surface to a 3D CT image data set, was applied in an automated fashion. Triangulations based on the contours generated on each phase were deformed to the CT data set on the succeeding phase to generate the contours on that phase. Deformation was propagated through the eight phases, and the contours obtained on the end inspiration data set were compared with the original manually delineated contours. Structures defined by high-density gradients, such as lungs, cord, and heart, were accurately reproduced, except in regions where other gradient boundaries may have confused the algorithm, such as near bronchi. The algorithm failed to accurately contour the esophagus, a soft-tissue structure completely surrounded by tissue of similar density, without manual interaction. This technique has the potential to facilitate contour delineation in 4D CT image data sets; and future evolution of the software is expected to improve the process.",
keywords = "4D imaging, CT segmentation, Deformable models",
author = "Dustin Ragan and George Starkschall and Todd McNutt and Michael Kaus and Thomas Guerrero and Stevens, {Craig W.}",
year = "2005",
month = "7",
doi = "10.1118/1.1929207",
language = "English (US)",
volume = "32",
pages = "2254--2261",
journal = "Medical Physics",
issn = "0094-2405",
publisher = "AAPM - American Association of Physicists in Medicine",
number = "7",

}

TY - JOUR

T1 - Semiautomated four-dimensional computed tomography segmentation using deformable models

AU - Ragan, Dustin

AU - Starkschall, George

AU - McNutt, Todd

AU - Kaus, Michael

AU - Guerrero, Thomas

AU - Stevens, Craig W.

PY - 2005/7

Y1 - 2005/7

N2 - The purpose of this work is to demonstrate a proof of feasibility of the application of a commercial prototype deformable model algorithm to the problem of delineation of anatomic structures on four-dimensional (4D) computed tomography (CT) image data sets. We acquired a 4D CT image data set of a patient's thorax that consisted of three-dimensional (3D) image data sets from eight phases in the respiratory cycle. The contours of the right and left lungs, cord, heart, and esophagus were manually delineated on the end inspiration data set. An interactive deformable model algorithm, originally intended for deforming an atlas-based model surface to a 3D CT image data set, was applied in an automated fashion. Triangulations based on the contours generated on each phase were deformed to the CT data set on the succeeding phase to generate the contours on that phase. Deformation was propagated through the eight phases, and the contours obtained on the end inspiration data set were compared with the original manually delineated contours. Structures defined by high-density gradients, such as lungs, cord, and heart, were accurately reproduced, except in regions where other gradient boundaries may have confused the algorithm, such as near bronchi. The algorithm failed to accurately contour the esophagus, a soft-tissue structure completely surrounded by tissue of similar density, without manual interaction. This technique has the potential to facilitate contour delineation in 4D CT image data sets; and future evolution of the software is expected to improve the process.

AB - The purpose of this work is to demonstrate a proof of feasibility of the application of a commercial prototype deformable model algorithm to the problem of delineation of anatomic structures on four-dimensional (4D) computed tomography (CT) image data sets. We acquired a 4D CT image data set of a patient's thorax that consisted of three-dimensional (3D) image data sets from eight phases in the respiratory cycle. The contours of the right and left lungs, cord, heart, and esophagus were manually delineated on the end inspiration data set. An interactive deformable model algorithm, originally intended for deforming an atlas-based model surface to a 3D CT image data set, was applied in an automated fashion. Triangulations based on the contours generated on each phase were deformed to the CT data set on the succeeding phase to generate the contours on that phase. Deformation was propagated through the eight phases, and the contours obtained on the end inspiration data set were compared with the original manually delineated contours. Structures defined by high-density gradients, such as lungs, cord, and heart, were accurately reproduced, except in regions where other gradient boundaries may have confused the algorithm, such as near bronchi. The algorithm failed to accurately contour the esophagus, a soft-tissue structure completely surrounded by tissue of similar density, without manual interaction. This technique has the potential to facilitate contour delineation in 4D CT image data sets; and future evolution of the software is expected to improve the process.

KW - 4D imaging

KW - CT segmentation

KW - Deformable models

UR - http://www.scopus.com/inward/record.url?scp=22544437829&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=22544437829&partnerID=8YFLogxK

U2 - 10.1118/1.1929207

DO - 10.1118/1.1929207

M3 - Article

C2 - 16121580

AN - SCOPUS:22544437829

VL - 32

SP - 2254

EP - 2261

JO - Medical Physics

JF - Medical Physics

SN - 0094-2405

IS - 7

ER -