Segmentation of breast masses on dedicated breast computed tomography and three-dimensional breast ultrasound images

Hsien Chi Kuo, Maryellen L. Giger, Ingrid Reiser, Karen Drukker, John M Boone, Karen K Lindfors, Kai Yang, Alexandra Edwards, Charlene A. Sennett

Research output: Contribution to journalArticle

15 Citations (Scopus)

Abstract

We present and evaluate a method for the three-dimensional (3-D) segmentation of breast masses on dedicated breast computed tomography (bCT) and automated 3-D breast ultrasound images. The segmentation method, refined from our previous segmentation method for masses on contrast-enhanced bCT, includes two steps: (1) initial contour estimation and (2) active contour-based segmentation to further evolve and refine the initial contour by adding a local energy term to the level-set equation. Segmentation performance was assessed in terms of Dice coefficients (DICE) for 129 lesions on noncontrast bCT, 38 lesions on contrast-enhanced bCT, and 98 lesions on 3-D breast ultrasound (US) images. For bCT, DICE values of 0.82 and 0.80 were obtained on contrast-enhanced and noncontrast images, respectively. The improvement in segmentation performance with respect to that of our previous method was statistically significant (p=0.002). Moreover, segmentation appeared robust with respect to the presence of glandular tissue. For 3-D breast US, the DICE value was 0.71. Hence, our method obtained promising results for both 3-D imaging modalities, laying a solid foundation for further quantitative image analysis and potential future expansion to other 3-D imaging modalities.

Original languageEnglish (US)
Article number014501
JournalJournal of Medical Imaging
Volume1
Issue number1
DOIs
StatePublished - Apr 1 2014

Fingerprint

Tomography
Breast
Ultrasonics
Imaging techniques
Three-Dimensional Imaging
Image analysis
Tissue

Keywords

  • active contour model
  • breast computed tomography
  • computer-aided diagnosis
  • image analysis
  • segmentation
  • three-dimensional automated breast ultrasound

ASJC Scopus subject areas

  • Bioengineering
  • Radiology Nuclear Medicine and imaging

Cite this

Segmentation of breast masses on dedicated breast computed tomography and three-dimensional breast ultrasound images. / Kuo, Hsien Chi; Giger, Maryellen L.; Reiser, Ingrid; Drukker, Karen; Boone, John M; Lindfors, Karen K; Yang, Kai; Edwards, Alexandra; Sennett, Charlene A.

In: Journal of Medical Imaging, Vol. 1, No. 1, 014501, 01.04.2014.

Research output: Contribution to journalArticle

Kuo, Hsien Chi ; Giger, Maryellen L. ; Reiser, Ingrid ; Drukker, Karen ; Boone, John M ; Lindfors, Karen K ; Yang, Kai ; Edwards, Alexandra ; Sennett, Charlene A. / Segmentation of breast masses on dedicated breast computed tomography and three-dimensional breast ultrasound images. In: Journal of Medical Imaging. 2014 ; Vol. 1, No. 1.
@article{bb3fbeecae714cabaf7a2f76b79780b4,
title = "Segmentation of breast masses on dedicated breast computed tomography and three-dimensional breast ultrasound images",
abstract = "We present and evaluate a method for the three-dimensional (3-D) segmentation of breast masses on dedicated breast computed tomography (bCT) and automated 3-D breast ultrasound images. The segmentation method, refined from our previous segmentation method for masses on contrast-enhanced bCT, includes two steps: (1) initial contour estimation and (2) active contour-based segmentation to further evolve and refine the initial contour by adding a local energy term to the level-set equation. Segmentation performance was assessed in terms of Dice coefficients (DICE) for 129 lesions on noncontrast bCT, 38 lesions on contrast-enhanced bCT, and 98 lesions on 3-D breast ultrasound (US) images. For bCT, DICE values of 0.82 and 0.80 were obtained on contrast-enhanced and noncontrast images, respectively. The improvement in segmentation performance with respect to that of our previous method was statistically significant (p=0.002). Moreover, segmentation appeared robust with respect to the presence of glandular tissue. For 3-D breast US, the DICE value was 0.71. Hence, our method obtained promising results for both 3-D imaging modalities, laying a solid foundation for further quantitative image analysis and potential future expansion to other 3-D imaging modalities.",
keywords = "active contour model, breast computed tomography, computer-aided diagnosis, image analysis, segmentation, three-dimensional automated breast ultrasound",
author = "Kuo, {Hsien Chi} and Giger, {Maryellen L.} and Ingrid Reiser and Karen Drukker and Boone, {John M} and Lindfors, {Karen K} and Kai Yang and Alexandra Edwards and Sennett, {Charlene A.}",
year = "2014",
month = "4",
day = "1",
doi = "10.1117/1.JMI.1.1.014501",
language = "English (US)",
volume = "1",
journal = "Journal of Medical Imaging",
issn = "0720-048X",
publisher = "Elsevier Ireland Ltd",
number = "1",

}

TY - JOUR

T1 - Segmentation of breast masses on dedicated breast computed tomography and three-dimensional breast ultrasound images

AU - Kuo, Hsien Chi

AU - Giger, Maryellen L.

AU - Reiser, Ingrid

AU - Drukker, Karen

AU - Boone, John M

AU - Lindfors, Karen K

AU - Yang, Kai

AU - Edwards, Alexandra

AU - Sennett, Charlene A.

PY - 2014/4/1

Y1 - 2014/4/1

N2 - We present and evaluate a method for the three-dimensional (3-D) segmentation of breast masses on dedicated breast computed tomography (bCT) and automated 3-D breast ultrasound images. The segmentation method, refined from our previous segmentation method for masses on contrast-enhanced bCT, includes two steps: (1) initial contour estimation and (2) active contour-based segmentation to further evolve and refine the initial contour by adding a local energy term to the level-set equation. Segmentation performance was assessed in terms of Dice coefficients (DICE) for 129 lesions on noncontrast bCT, 38 lesions on contrast-enhanced bCT, and 98 lesions on 3-D breast ultrasound (US) images. For bCT, DICE values of 0.82 and 0.80 were obtained on contrast-enhanced and noncontrast images, respectively. The improvement in segmentation performance with respect to that of our previous method was statistically significant (p=0.002). Moreover, segmentation appeared robust with respect to the presence of glandular tissue. For 3-D breast US, the DICE value was 0.71. Hence, our method obtained promising results for both 3-D imaging modalities, laying a solid foundation for further quantitative image analysis and potential future expansion to other 3-D imaging modalities.

AB - We present and evaluate a method for the three-dimensional (3-D) segmentation of breast masses on dedicated breast computed tomography (bCT) and automated 3-D breast ultrasound images. The segmentation method, refined from our previous segmentation method for masses on contrast-enhanced bCT, includes two steps: (1) initial contour estimation and (2) active contour-based segmentation to further evolve and refine the initial contour by adding a local energy term to the level-set equation. Segmentation performance was assessed in terms of Dice coefficients (DICE) for 129 lesions on noncontrast bCT, 38 lesions on contrast-enhanced bCT, and 98 lesions on 3-D breast ultrasound (US) images. For bCT, DICE values of 0.82 and 0.80 were obtained on contrast-enhanced and noncontrast images, respectively. The improvement in segmentation performance with respect to that of our previous method was statistically significant (p=0.002). Moreover, segmentation appeared robust with respect to the presence of glandular tissue. For 3-D breast US, the DICE value was 0.71. Hence, our method obtained promising results for both 3-D imaging modalities, laying a solid foundation for further quantitative image analysis and potential future expansion to other 3-D imaging modalities.

KW - active contour model

KW - breast computed tomography

KW - computer-aided diagnosis

KW - image analysis

KW - segmentation

KW - three-dimensional automated breast ultrasound

UR - http://www.scopus.com/inward/record.url?scp=85015395940&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85015395940&partnerID=8YFLogxK

U2 - 10.1117/1.JMI.1.1.014501

DO - 10.1117/1.JMI.1.1.014501

M3 - Article

AN - SCOPUS:85015395940

VL - 1

JO - Journal of Medical Imaging

JF - Journal of Medical Imaging

SN - 0720-048X

IS - 1

M1 - 014501

ER -