Quantitative breast mass classification based on the integration of B-mode features and strain features in elastography

Chung Ming Lo, Yeun Chung Chang, Ya Wen Yang, Chiun Sheng Huang, Ruey Feng Chang

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

Background: Elastography is a new sonographic imaging technique to acquire the strain information of tissues and transform the information into images. Radiologists have to observe the gray-scale distribution of tissues on the elastographic image interpreted as the reciprocal of Young[U+05F3]s modulus to evaluate the pathological changes such as scirrhous carcinoma. In this study, a computer-aided diagnosis (CAD) system was developed to extract quantitative strain features from elastographic images to reduce operator-dependence and provide an automatic procedure for breast mass classification. Method: The collected image database was composed of 45 malignant and 45 benign breast masses. For each case, tumor segmentation was performed on the B-mode image to obtain tumor contour which was then mapped to the elastographic images to define the corresponding tumor area. The gray-scale pixels around tumor area were classified into white, gray, and black by fuzzy c-means clustering to highlight stiff tissues with darker values. Quantitative strain features were then extracted from the black cluster and compared with the B-mode features in the classification of breast masses. Results: The performance of the proposed strain features achieved an accuracy of 80% (72/90), a sensitivity of 80% (36/45), a specificity of 80% (36/45), and a normalized area under the receiver operating characteristic curve, Az=0.84. Combining the strain features with the B-mode features obtained a significantly better Az=0.93, p-value

Original languageEnglish
Pages (from-to)91-100
Number of pages10
JournalComputers in Biology and Medicine
Volume64
DOIs
Publication statusPublished - Sep 1 2015

Fingerprint

Elasticity Imaging Techniques
Breast
Tumors
Neoplasms
Tissue
Scirrhous Adenocarcinoma
Tissue Distribution
Computer aided diagnosis
ROC Curve
Cluster Analysis
Databases
Pixels
Imaging techniques

Keywords

  • B-mode
  • Breast cancer
  • Computer-aided diagnosis
  • Elastography
  • Fuzzy c-means clustering

ASJC Scopus subject areas

  • Computer Science Applications
  • Health Informatics

Cite this

Quantitative breast mass classification based on the integration of B-mode features and strain features in elastography. / Lo, Chung Ming; Chang, Yeun Chung; Yang, Ya Wen; Huang, Chiun Sheng; Chang, Ruey Feng.

In: Computers in Biology and Medicine, Vol. 64, 01.09.2015, p. 91-100.

Research output: Contribution to journalArticle

Lo, Chung Ming ; Chang, Yeun Chung ; Yang, Ya Wen ; Huang, Chiun Sheng ; Chang, Ruey Feng. / Quantitative breast mass classification based on the integration of B-mode features and strain features in elastography. In: Computers in Biology and Medicine. 2015 ; Vol. 64. pp. 91-100.
@article{219d4b23618c4a2ab7d486cda8d8e8a1,
title = "Quantitative breast mass classification based on the integration of B-mode features and strain features in elastography",
abstract = "Background: Elastography is a new sonographic imaging technique to acquire the strain information of tissues and transform the information into images. Radiologists have to observe the gray-scale distribution of tissues on the elastographic image interpreted as the reciprocal of Young[U+05F3]s modulus to evaluate the pathological changes such as scirrhous carcinoma. In this study, a computer-aided diagnosis (CAD) system was developed to extract quantitative strain features from elastographic images to reduce operator-dependence and provide an automatic procedure for breast mass classification. Method: The collected image database was composed of 45 malignant and 45 benign breast masses. For each case, tumor segmentation was performed on the B-mode image to obtain tumor contour which was then mapped to the elastographic images to define the corresponding tumor area. The gray-scale pixels around tumor area were classified into white, gray, and black by fuzzy c-means clustering to highlight stiff tissues with darker values. Quantitative strain features were then extracted from the black cluster and compared with the B-mode features in the classification of breast masses. Results: The performance of the proposed strain features achieved an accuracy of 80{\%} (72/90), a sensitivity of 80{\%} (36/45), a specificity of 80{\%} (36/45), and a normalized area under the receiver operating characteristic curve, Az=0.84. Combining the strain features with the B-mode features obtained a significantly better Az=0.93, p-value",
keywords = "B-mode, Breast cancer, Computer-aided diagnosis, Elastography, Fuzzy c-means clustering",
author = "Lo, {Chung Ming} and Chang, {Yeun Chung} and Yang, {Ya Wen} and Huang, {Chiun Sheng} and Chang, {Ruey Feng}",
year = "2015",
month = "9",
day = "1",
doi = "10.1016/j.compbiomed.2015.06.013",
language = "English",
volume = "64",
pages = "91--100",
journal = "Computers in Biology and Medicine",
issn = "0010-4825",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Quantitative breast mass classification based on the integration of B-mode features and strain features in elastography

AU - Lo, Chung Ming

AU - Chang, Yeun Chung

AU - Yang, Ya Wen

AU - Huang, Chiun Sheng

AU - Chang, Ruey Feng

PY - 2015/9/1

Y1 - 2015/9/1

N2 - Background: Elastography is a new sonographic imaging technique to acquire the strain information of tissues and transform the information into images. Radiologists have to observe the gray-scale distribution of tissues on the elastographic image interpreted as the reciprocal of Young[U+05F3]s modulus to evaluate the pathological changes such as scirrhous carcinoma. In this study, a computer-aided diagnosis (CAD) system was developed to extract quantitative strain features from elastographic images to reduce operator-dependence and provide an automatic procedure for breast mass classification. Method: The collected image database was composed of 45 malignant and 45 benign breast masses. For each case, tumor segmentation was performed on the B-mode image to obtain tumor contour which was then mapped to the elastographic images to define the corresponding tumor area. The gray-scale pixels around tumor area were classified into white, gray, and black by fuzzy c-means clustering to highlight stiff tissues with darker values. Quantitative strain features were then extracted from the black cluster and compared with the B-mode features in the classification of breast masses. Results: The performance of the proposed strain features achieved an accuracy of 80% (72/90), a sensitivity of 80% (36/45), a specificity of 80% (36/45), and a normalized area under the receiver operating characteristic curve, Az=0.84. Combining the strain features with the B-mode features obtained a significantly better Az=0.93, p-value

AB - Background: Elastography is a new sonographic imaging technique to acquire the strain information of tissues and transform the information into images. Radiologists have to observe the gray-scale distribution of tissues on the elastographic image interpreted as the reciprocal of Young[U+05F3]s modulus to evaluate the pathological changes such as scirrhous carcinoma. In this study, a computer-aided diagnosis (CAD) system was developed to extract quantitative strain features from elastographic images to reduce operator-dependence and provide an automatic procedure for breast mass classification. Method: The collected image database was composed of 45 malignant and 45 benign breast masses. For each case, tumor segmentation was performed on the B-mode image to obtain tumor contour which was then mapped to the elastographic images to define the corresponding tumor area. The gray-scale pixels around tumor area were classified into white, gray, and black by fuzzy c-means clustering to highlight stiff tissues with darker values. Quantitative strain features were then extracted from the black cluster and compared with the B-mode features in the classification of breast masses. Results: The performance of the proposed strain features achieved an accuracy of 80% (72/90), a sensitivity of 80% (36/45), a specificity of 80% (36/45), and a normalized area under the receiver operating characteristic curve, Az=0.84. Combining the strain features with the B-mode features obtained a significantly better Az=0.93, p-value

KW - B-mode

KW - Breast cancer

KW - Computer-aided diagnosis

KW - Elastography

KW - Fuzzy c-means clustering

UR - http://www.scopus.com/inward/record.url?scp=84936856193&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84936856193&partnerID=8YFLogxK

U2 - 10.1016/j.compbiomed.2015.06.013

DO - 10.1016/j.compbiomed.2015.06.013

M3 - Article

C2 - 26159906

AN - SCOPUS:84936856193

VL - 64

SP - 91

EP - 100

JO - Computers in Biology and Medicine

JF - Computers in Biology and Medicine

SN - 0010-4825

ER -