Computer-aided strain evaluation for acoustic radiation force impulse imaging of breast masses

Chung Ming Lo, Yen Po Chen, Yeun Chung Chang, Chiao Lo, Chiun Sheng Huang, Ruey Feng Chang

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

Acoustic radiation force impulse (ARFI) is a newly developed elastography technique that uses acoustic radiation force to provide additional stiffness information to conventional sonography. A computer-aided diagnosis (CAD) system was proposed to automatically specify the tumor boundaries in ARFI images and quantify the statistical stiffness information to reduce user dependence. The level-set segmentation was used to delineate tumor boundaries in B-mode images, and the segmented boundaries were then mapped to the corresponding area in ARFI images for a gray-scale calculation. A total of 61 benign and 51 malignant tumors were evaluated in the experiment. The CAD system based on the proposed ARFI features achieved an accuracy of 80% (90/112), a sensitivity of 80% (41/51), and a specificity of 80% (49/61), which is significantly better than that of the quantitative B-mode features (p <0.05). The ARFI features were further combined with the B-mode features, including shape and texture features, to further improve performance (area under the curve [AUC], 0.90 vs. 0.86). In conclusion, the CAD system based on the proposed ARFI features is a promising and efficient diagnostic method.

Original languageEnglish
Pages (from-to)151-166
Number of pages16
JournalUltrasonic Imaging
Volume36
Issue number3
DOIs
Publication statusPublished - 2014
Externally publishedYes

Fingerprint

Elasticity Imaging Techniques
Acoustics
Breast
Radiation
Neoplasms
Area Under Curve
Ultrasonography

Keywords

  • Acoustic radiation force impulse
  • Breast cancer
  • Computer-aided diagnosis
  • Ultrasound

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging
  • Radiological and Ultrasound Technology

Cite this

Lo, C. M., Chen, Y. P., Chang, Y. C., Lo, C., Huang, C. S., & Chang, R. F. (2014). Computer-aided strain evaluation for acoustic radiation force impulse imaging of breast masses. Ultrasonic Imaging, 36(3), 151-166. https://doi.org/10.1177/0161734613520599

Computer-aided strain evaluation for acoustic radiation force impulse imaging of breast masses. / Lo, Chung Ming; Chen, Yen Po; Chang, Yeun Chung; Lo, Chiao; Huang, Chiun Sheng; Chang, Ruey Feng.

In: Ultrasonic Imaging, Vol. 36, No. 3, 2014, p. 151-166.

Research output: Contribution to journalArticle

Lo, Chung Ming ; Chen, Yen Po ; Chang, Yeun Chung ; Lo, Chiao ; Huang, Chiun Sheng ; Chang, Ruey Feng. / Computer-aided strain evaluation for acoustic radiation force impulse imaging of breast masses. In: Ultrasonic Imaging. 2014 ; Vol. 36, No. 3. pp. 151-166.
@article{e9e3f933010d40b88b0e7aef0e52da7f,
title = "Computer-aided strain evaluation for acoustic radiation force impulse imaging of breast masses",
abstract = "Acoustic radiation force impulse (ARFI) is a newly developed elastography technique that uses acoustic radiation force to provide additional stiffness information to conventional sonography. A computer-aided diagnosis (CAD) system was proposed to automatically specify the tumor boundaries in ARFI images and quantify the statistical stiffness information to reduce user dependence. The level-set segmentation was used to delineate tumor boundaries in B-mode images, and the segmented boundaries were then mapped to the corresponding area in ARFI images for a gray-scale calculation. A total of 61 benign and 51 malignant tumors were evaluated in the experiment. The CAD system based on the proposed ARFI features achieved an accuracy of 80{\%} (90/112), a sensitivity of 80{\%} (41/51), and a specificity of 80{\%} (49/61), which is significantly better than that of the quantitative B-mode features (p <0.05). The ARFI features were further combined with the B-mode features, including shape and texture features, to further improve performance (area under the curve [AUC], 0.90 vs. 0.86). In conclusion, the CAD system based on the proposed ARFI features is a promising and efficient diagnostic method.",
keywords = "Acoustic radiation force impulse, Breast cancer, Computer-aided diagnosis, Ultrasound",
author = "Lo, {Chung Ming} and Chen, {Yen Po} and Chang, {Yeun Chung} and Chiao Lo and Huang, {Chiun Sheng} and Chang, {Ruey Feng}",
year = "2014",
doi = "10.1177/0161734613520599",
language = "English",
volume = "36",
pages = "151--166",
journal = "Ultrasonic Imaging",
issn = "0161-7346",
publisher = "Dynamedia Inc.",
number = "3",

}

TY - JOUR

T1 - Computer-aided strain evaluation for acoustic radiation force impulse imaging of breast masses

AU - Lo, Chung Ming

AU - Chen, Yen Po

AU - Chang, Yeun Chung

AU - Lo, Chiao

AU - Huang, Chiun Sheng

AU - Chang, Ruey Feng

PY - 2014

Y1 - 2014

N2 - Acoustic radiation force impulse (ARFI) is a newly developed elastography technique that uses acoustic radiation force to provide additional stiffness information to conventional sonography. A computer-aided diagnosis (CAD) system was proposed to automatically specify the tumor boundaries in ARFI images and quantify the statistical stiffness information to reduce user dependence. The level-set segmentation was used to delineate tumor boundaries in B-mode images, and the segmented boundaries were then mapped to the corresponding area in ARFI images for a gray-scale calculation. A total of 61 benign and 51 malignant tumors were evaluated in the experiment. The CAD system based on the proposed ARFI features achieved an accuracy of 80% (90/112), a sensitivity of 80% (41/51), and a specificity of 80% (49/61), which is significantly better than that of the quantitative B-mode features (p <0.05). The ARFI features were further combined with the B-mode features, including shape and texture features, to further improve performance (area under the curve [AUC], 0.90 vs. 0.86). In conclusion, the CAD system based on the proposed ARFI features is a promising and efficient diagnostic method.

AB - Acoustic radiation force impulse (ARFI) is a newly developed elastography technique that uses acoustic radiation force to provide additional stiffness information to conventional sonography. A computer-aided diagnosis (CAD) system was proposed to automatically specify the tumor boundaries in ARFI images and quantify the statistical stiffness information to reduce user dependence. The level-set segmentation was used to delineate tumor boundaries in B-mode images, and the segmented boundaries were then mapped to the corresponding area in ARFI images for a gray-scale calculation. A total of 61 benign and 51 malignant tumors were evaluated in the experiment. The CAD system based on the proposed ARFI features achieved an accuracy of 80% (90/112), a sensitivity of 80% (41/51), and a specificity of 80% (49/61), which is significantly better than that of the quantitative B-mode features (p <0.05). The ARFI features were further combined with the B-mode features, including shape and texture features, to further improve performance (area under the curve [AUC], 0.90 vs. 0.86). In conclusion, the CAD system based on the proposed ARFI features is a promising and efficient diagnostic method.

KW - Acoustic radiation force impulse

KW - Breast cancer

KW - Computer-aided diagnosis

KW - Ultrasound

UR - http://www.scopus.com/inward/record.url?scp=84903600749&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84903600749&partnerID=8YFLogxK

U2 - 10.1177/0161734613520599

DO - 10.1177/0161734613520599

M3 - Article

AN - SCOPUS:84903600749

VL - 36

SP - 151

EP - 166

JO - Ultrasonic Imaging

JF - Ultrasonic Imaging

SN - 0161-7346

IS - 3

ER -