Computer-aided tumor diagnosis using shear wave breast elastography

Woo Kyung Moon, Yao Sian Huang, Yan Wei Lee, Shao Chien Chang, Chung Ming Lo, Min Chun Yang, Min Sun Bae, Su Hyun Lee, Jung Min Chang, Chiun Sheng Huang, Yi Ting Lin, Ruey Feng Chang

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

The shear wave elastography (SWE) uses the acoustic radiation force to measure the stiffness of tissues and is less operator dependent in data acquisition compared to strain elastography. However, the reproducibility of the result is still interpreter dependent. The purpose of this study is to develop a computer-aided diagnosis (CAD) method to differentiate benign from malignant breast tumors using SWE images. After applying the level set method to automatically segment the tumor contour and hue-saturation-value color transformation, SWE features including average tissue elasticity, sectional stiffness ratio, and normalized minimum distance for grouped stiffer pixels are calculated. Finally, the performance of CAD based on SWE features are compared with those based on B-mode ultrasound (morphologic and textural) features, and a combination of both feature sets to differentiate benign from malignant tumors. In this study, we use 109 biopsy-proved breast tumors composed of 57 benign and 52 malignant cases. The experimental results show that the sensitivity, specificity, accuracy and the area under the receiver operating characteristic ROC curve (Az value) of CAD are 86.5%, 93.0%, 89.9%, and 0.905 for SWE features whereas they are 86.5%, 80.7%, 83.5% and 0.893 for B-mode features and 90.4%, 94.7%, 92.3% and 0.961 for the combined features. The Az value of combined feature set is significantly higher compared to the B-mode and SWE feature sets (p = 0.0296 and p = 0.0204, respectively). Our results suggest that the CAD based on SWE features has the potential to improve the performance of classifying breast tumors with US.

Original languageEnglish
Pages (from-to)125-133
Number of pages9
JournalUltrasonics
Volume78
DOIs
Publication statusPublished - Jul 1 2017

Fingerprint

Elasticity Imaging Techniques
breast
S waves
Breast
tumors
Neoplasms
Breast Neoplasms
ROC Curve
stiffness
classifying
sound waves
Elasticity
data acquisition
Acoustics
Reproducibility of Results
elastic properties
receivers
pixels
Color
saturation

Keywords

  • Breast
  • Computer-aided diagnosis
  • Elastography
  • Shear wave
  • Tumor segmentation

ASJC Scopus subject areas

  • Medicine(all)
  • Acoustics and Ultrasonics

Cite this

Moon, W. K., Huang, Y. S., Lee, Y. W., Chang, S. C., Lo, C. M., Yang, M. C., ... Chang, R. F. (2017). Computer-aided tumor diagnosis using shear wave breast elastography. Ultrasonics, 78, 125-133. https://doi.org/10.1016/j.ultras.2017.03.010

Computer-aided tumor diagnosis using shear wave breast elastography. / Moon, Woo Kyung; Huang, Yao Sian; Lee, Yan Wei; Chang, Shao Chien; Lo, Chung Ming; Yang, Min Chun; Bae, Min Sun; Lee, Su Hyun; Chang, Jung Min; Huang, Chiun Sheng; Lin, Yi Ting; Chang, Ruey Feng.

In: Ultrasonics, Vol. 78, 01.07.2017, p. 125-133.

Research output: Contribution to journalArticle

Moon, WK, Huang, YS, Lee, YW, Chang, SC, Lo, CM, Yang, MC, Bae, MS, Lee, SH, Chang, JM, Huang, CS, Lin, YT & Chang, RF 2017, 'Computer-aided tumor diagnosis using shear wave breast elastography', Ultrasonics, vol. 78, pp. 125-133. https://doi.org/10.1016/j.ultras.2017.03.010
Moon WK, Huang YS, Lee YW, Chang SC, Lo CM, Yang MC et al. Computer-aided tumor diagnosis using shear wave breast elastography. Ultrasonics. 2017 Jul 1;78:125-133. https://doi.org/10.1016/j.ultras.2017.03.010
Moon, Woo Kyung ; Huang, Yao Sian ; Lee, Yan Wei ; Chang, Shao Chien ; Lo, Chung Ming ; Yang, Min Chun ; Bae, Min Sun ; Lee, Su Hyun ; Chang, Jung Min ; Huang, Chiun Sheng ; Lin, Yi Ting ; Chang, Ruey Feng. / Computer-aided tumor diagnosis using shear wave breast elastography. In: Ultrasonics. 2017 ; Vol. 78. pp. 125-133.
@article{42457c9526f14464a868d790188b6c49,
title = "Computer-aided tumor diagnosis using shear wave breast elastography",
abstract = "The shear wave elastography (SWE) uses the acoustic radiation force to measure the stiffness of tissues and is less operator dependent in data acquisition compared to strain elastography. However, the reproducibility of the result is still interpreter dependent. The purpose of this study is to develop a computer-aided diagnosis (CAD) method to differentiate benign from malignant breast tumors using SWE images. After applying the level set method to automatically segment the tumor contour and hue-saturation-value color transformation, SWE features including average tissue elasticity, sectional stiffness ratio, and normalized minimum distance for grouped stiffer pixels are calculated. Finally, the performance of CAD based on SWE features are compared with those based on B-mode ultrasound (morphologic and textural) features, and a combination of both feature sets to differentiate benign from malignant tumors. In this study, we use 109 biopsy-proved breast tumors composed of 57 benign and 52 malignant cases. The experimental results show that the sensitivity, specificity, accuracy and the area under the receiver operating characteristic ROC curve (Az value) of CAD are 86.5{\%}, 93.0{\%}, 89.9{\%}, and 0.905 for SWE features whereas they are 86.5{\%}, 80.7{\%}, 83.5{\%} and 0.893 for B-mode features and 90.4{\%}, 94.7{\%}, 92.3{\%} and 0.961 for the combined features. The Az value of combined feature set is significantly higher compared to the B-mode and SWE feature sets (p = 0.0296 and p = 0.0204, respectively). Our results suggest that the CAD based on SWE features has the potential to improve the performance of classifying breast tumors with US.",
keywords = "Breast, Computer-aided diagnosis, Elastography, Shear wave, Tumor segmentation",
author = "Moon, {Woo Kyung} and Huang, {Yao Sian} and Lee, {Yan Wei} and Chang, {Shao Chien} and Lo, {Chung Ming} and Yang, {Min Chun} and Bae, {Min Sun} and Lee, {Su Hyun} and Chang, {Jung Min} and Huang, {Chiun Sheng} and Lin, {Yi Ting} and Chang, {Ruey Feng}",
year = "2017",
month = "7",
day = "1",
doi = "10.1016/j.ultras.2017.03.010",
language = "English",
volume = "78",
pages = "125--133",
journal = "Ultrasonics",
issn = "0041-624X",
publisher = "Elsevier",

}

TY - JOUR

T1 - Computer-aided tumor diagnosis using shear wave breast elastography

AU - Moon, Woo Kyung

AU - Huang, Yao Sian

AU - Lee, Yan Wei

AU - Chang, Shao Chien

AU - Lo, Chung Ming

AU - Yang, Min Chun

AU - Bae, Min Sun

AU - Lee, Su Hyun

AU - Chang, Jung Min

AU - Huang, Chiun Sheng

AU - Lin, Yi Ting

AU - Chang, Ruey Feng

PY - 2017/7/1

Y1 - 2017/7/1

N2 - The shear wave elastography (SWE) uses the acoustic radiation force to measure the stiffness of tissues and is less operator dependent in data acquisition compared to strain elastography. However, the reproducibility of the result is still interpreter dependent. The purpose of this study is to develop a computer-aided diagnosis (CAD) method to differentiate benign from malignant breast tumors using SWE images. After applying the level set method to automatically segment the tumor contour and hue-saturation-value color transformation, SWE features including average tissue elasticity, sectional stiffness ratio, and normalized minimum distance for grouped stiffer pixels are calculated. Finally, the performance of CAD based on SWE features are compared with those based on B-mode ultrasound (morphologic and textural) features, and a combination of both feature sets to differentiate benign from malignant tumors. In this study, we use 109 biopsy-proved breast tumors composed of 57 benign and 52 malignant cases. The experimental results show that the sensitivity, specificity, accuracy and the area under the receiver operating characteristic ROC curve (Az value) of CAD are 86.5%, 93.0%, 89.9%, and 0.905 for SWE features whereas they are 86.5%, 80.7%, 83.5% and 0.893 for B-mode features and 90.4%, 94.7%, 92.3% and 0.961 for the combined features. The Az value of combined feature set is significantly higher compared to the B-mode and SWE feature sets (p = 0.0296 and p = 0.0204, respectively). Our results suggest that the CAD based on SWE features has the potential to improve the performance of classifying breast tumors with US.

AB - The shear wave elastography (SWE) uses the acoustic radiation force to measure the stiffness of tissues and is less operator dependent in data acquisition compared to strain elastography. However, the reproducibility of the result is still interpreter dependent. The purpose of this study is to develop a computer-aided diagnosis (CAD) method to differentiate benign from malignant breast tumors using SWE images. After applying the level set method to automatically segment the tumor contour and hue-saturation-value color transformation, SWE features including average tissue elasticity, sectional stiffness ratio, and normalized minimum distance for grouped stiffer pixels are calculated. Finally, the performance of CAD based on SWE features are compared with those based on B-mode ultrasound (morphologic and textural) features, and a combination of both feature sets to differentiate benign from malignant tumors. In this study, we use 109 biopsy-proved breast tumors composed of 57 benign and 52 malignant cases. The experimental results show that the sensitivity, specificity, accuracy and the area under the receiver operating characteristic ROC curve (Az value) of CAD are 86.5%, 93.0%, 89.9%, and 0.905 for SWE features whereas they are 86.5%, 80.7%, 83.5% and 0.893 for B-mode features and 90.4%, 94.7%, 92.3% and 0.961 for the combined features. The Az value of combined feature set is significantly higher compared to the B-mode and SWE feature sets (p = 0.0296 and p = 0.0204, respectively). Our results suggest that the CAD based on SWE features has the potential to improve the performance of classifying breast tumors with US.

KW - Breast

KW - Computer-aided diagnosis

KW - Elastography

KW - Shear wave

KW - Tumor segmentation

UR - http://www.scopus.com/inward/record.url?scp=85015842644&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85015842644&partnerID=8YFLogxK

U2 - 10.1016/j.ultras.2017.03.010

DO - 10.1016/j.ultras.2017.03.010

M3 - Article

C2 - 28342323

AN - SCOPUS:85015842644

VL - 78

SP - 125

EP - 133

JO - Ultrasonics

JF - Ultrasonics

SN - 0041-624X

ER -