Quantitative breast lesion classification based on multichannel distributions in shear-wave imaging

Chung Ming Lo, Yi Chen Lai, Yi Hong Chou, Ruey Feng Chang

Research output: Contribution to journalArticle

20 Citations (Scopus)

Abstract

Background and objectives: A computer-aided diagnosis (CAD) system based on the quantified color distributions in shear-wave elastography (SWE) was developed to evaluate the malignancies of breast tumors. Methods: For 57 benign and 31 malignant tumors, 18 SWE features were extracted from regions of interest (ROI), including the tumor and peritumoral areas. In the ROI, a histogram in each color channel was described using moments such as the mean, variance, skewness, and kurtosis. Moreover, three color channels were combined as a vector to evaluate tissue elasticity. The SWE features were then combined in a logistic regression classifier for breast tumor classification. Results: The performance of the CAD system achieved an accuracy of 81%. Combining the CAD system with a BI-RADS assessment obtained an Az improvement from 0.77 to 0.89 (p-value

Original languageEnglish
Pages (from-to)354-361
Number of pages8
JournalComputer Methods and Programs in Biomedicine
Volume122
Issue number3
DOIs
Publication statusPublished - Dec 1 2015

Fingerprint

Elasticity Imaging Techniques
Shear waves
Computer aided diagnosis
Tumors
Breast
Color
Imaging techniques
Breast Neoplasms
Neoplasms
Elasticity
Logistic Models
Logistics
Classifiers
Tissue

Keywords

  • Breast cancer
  • Computer-aided diagnosis
  • Histogram moment
  • Shear-wave elastography
  • Vector quantification

ASJC Scopus subject areas

  • Computer Science Applications
  • Software
  • Health Informatics

Cite this

Quantitative breast lesion classification based on multichannel distributions in shear-wave imaging. / Lo, Chung Ming; Lai, Yi Chen; Chou, Yi Hong; Chang, Ruey Feng.

In: Computer Methods and Programs in Biomedicine, Vol. 122, No. 3, 01.12.2015, p. 354-361.

Research output: Contribution to journalArticle

Lo, Chung Ming ; Lai, Yi Chen ; Chou, Yi Hong ; Chang, Ruey Feng. / Quantitative breast lesion classification based on multichannel distributions in shear-wave imaging. In: Computer Methods and Programs in Biomedicine. 2015 ; Vol. 122, No. 3. pp. 354-361.
@article{90271808848e48f2b60e5a17e0da5c4c,
title = "Quantitative breast lesion classification based on multichannel distributions in shear-wave imaging",
abstract = "Background and objectives: A computer-aided diagnosis (CAD) system based on the quantified color distributions in shear-wave elastography (SWE) was developed to evaluate the malignancies of breast tumors. Methods: For 57 benign and 31 malignant tumors, 18 SWE features were extracted from regions of interest (ROI), including the tumor and peritumoral areas. In the ROI, a histogram in each color channel was described using moments such as the mean, variance, skewness, and kurtosis. Moreover, three color channels were combined as a vector to evaluate tissue elasticity. The SWE features were then combined in a logistic regression classifier for breast tumor classification. Results: The performance of the CAD system achieved an accuracy of 81{\%}. Combining the CAD system with a BI-RADS assessment obtained an Az improvement from 0.77 to 0.89 (p-value",
keywords = "Breast cancer, Computer-aided diagnosis, Histogram moment, Shear-wave elastography, Vector quantification",
author = "Lo, {Chung Ming} and Lai, {Yi Chen} and Chou, {Yi Hong} and Chang, {Ruey Feng}",
year = "2015",
month = "12",
day = "1",
doi = "10.1016/j.cmpb.2015.09.004",
language = "English",
volume = "122",
pages = "354--361",
journal = "Computer Methods and Programs in Biomedicine",
issn = "0169-2607",
publisher = "Elsevier Ireland Ltd",
number = "3",

}

TY - JOUR

T1 - Quantitative breast lesion classification based on multichannel distributions in shear-wave imaging

AU - Lo, Chung Ming

AU - Lai, Yi Chen

AU - Chou, Yi Hong

AU - Chang, Ruey Feng

PY - 2015/12/1

Y1 - 2015/12/1

N2 - Background and objectives: A computer-aided diagnosis (CAD) system based on the quantified color distributions in shear-wave elastography (SWE) was developed to evaluate the malignancies of breast tumors. Methods: For 57 benign and 31 malignant tumors, 18 SWE features were extracted from regions of interest (ROI), including the tumor and peritumoral areas. In the ROI, a histogram in each color channel was described using moments such as the mean, variance, skewness, and kurtosis. Moreover, three color channels were combined as a vector to evaluate tissue elasticity. The SWE features were then combined in a logistic regression classifier for breast tumor classification. Results: The performance of the CAD system achieved an accuracy of 81%. Combining the CAD system with a BI-RADS assessment obtained an Az improvement from 0.77 to 0.89 (p-value

AB - Background and objectives: A computer-aided diagnosis (CAD) system based on the quantified color distributions in shear-wave elastography (SWE) was developed to evaluate the malignancies of breast tumors. Methods: For 57 benign and 31 malignant tumors, 18 SWE features were extracted from regions of interest (ROI), including the tumor and peritumoral areas. In the ROI, a histogram in each color channel was described using moments such as the mean, variance, skewness, and kurtosis. Moreover, three color channels were combined as a vector to evaluate tissue elasticity. The SWE features were then combined in a logistic regression classifier for breast tumor classification. Results: The performance of the CAD system achieved an accuracy of 81%. Combining the CAD system with a BI-RADS assessment obtained an Az improvement from 0.77 to 0.89 (p-value

KW - Breast cancer

KW - Computer-aided diagnosis

KW - Histogram moment

KW - Shear-wave elastography

KW - Vector quantification

UR - http://www.scopus.com/inward/record.url?scp=84947611836&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84947611836&partnerID=8YFLogxK

U2 - 10.1016/j.cmpb.2015.09.004

DO - 10.1016/j.cmpb.2015.09.004

M3 - Article

C2 - 26421696

AN - SCOPUS:84947611836

VL - 122

SP - 354

EP - 361

JO - Computer Methods and Programs in Biomedicine

JF - Computer Methods and Programs in Biomedicine

SN - 0169-2607

IS - 3

ER -