Computer-Aided Diagnosis for the Classification of Breast Masses in Automated Whole Breast Ultrasound Images

Woo Kyung Moon, Yi Wei Shen, Chiun Sheng Huang, Li Ren Chiang, Ruey Feng Chang

Research output: Contribution to journalArticle

63 Citations (Scopus)

Abstract

New automated whole breast ultrasound (ABUS) machines have recently been developed and the ultrasound (US) volume dataset of the whole breast can be acquired in a standard manner. The purpose of this study was to develop a novel computer-aided diagnosis system for classification of breast masses in ABUS images. One hundred forty-seven cases (76 benign and 71 malignant breast masses) were obtained by a commercially available ABUS system. Because the distance of neighboring slices in ABUS images is fixed and small, these continuous slices were used for reconstruction as three-dimensional (3-D) US images. The 3-D tumor contour was segmented using the level-set segmentation method. Then, the 3-D features, including the texture, shape and ellipsoid fitting were extracted based on the segmented 3-D tumor contour to classify benign and malignant tumors based on the logistic regression model. The Student's t test, Mann-Whitney U test and receiver operating characteristic (ROC) curve analysis were used for statistical analysis. From the Az values of ROC curves, the shape features (0.9138) are better than the texture features (0.8603) and the ellipsoid fitting features (0.8496) for classification. The difference was significant between shape and ellipsoid fitting features (p = 0.0382). However, combination of ellipsoid fitting features and shape features can achieve a best performance with accuracy of 85.0% (125/147), sensitivity of 84.5% (60/71), specificity of 85.5% (65/76) and the area under the ROC curve Az of 0.9466. The results showed that ABUS images could be used for computer-aided feature extraction and classification of breast tumors. (E-mail: rfchang@csie.ntu.edu.tw).

Original languageEnglish
Pages (from-to)539-548
Number of pages10
JournalUltrasound in Medicine and Biology
Volume37
Issue number4
DOIs
StatePublished - 1 Apr 2011

Fingerprint

breast
Breast
ellipsoids
ROC Curve
tumors
receivers
Logistic Models
curves
textures
Neoplasms
Three-Dimensional Imaging
Nonparametric Statistics
logistics
pattern recognition
statistical analysis
students
regression analysis
Breast Neoplasms
Students
sensitivity

Keywords

  • Automated whole breast ultrasound
  • Breast cancer
  • Computer-aided diagnosis
  • Ellipsoid fitting
  • Logistic regression model

Cite this

Moon, Woo Kyung ; Shen, Yi Wei ; Huang, Chiun Sheng ; Chiang, Li Ren ; Chang, Ruey Feng. / Computer-Aided Diagnosis for the Classification of Breast Masses in Automated Whole Breast Ultrasound Images. In: Ultrasound in Medicine and Biology. 2011 ; Vol. 37, No. 4. pp. 539-548.
@article{50c7bf119cdb4de3bac9fe6d6aeb5bc9,
title = "Computer-Aided Diagnosis for the Classification of Breast Masses in Automated Whole Breast Ultrasound Images",
abstract = "New automated whole breast ultrasound (ABUS) machines have recently been developed and the ultrasound (US) volume dataset of the whole breast can be acquired in a standard manner. The purpose of this study was to develop a novel computer-aided diagnosis system for classification of breast masses in ABUS images. One hundred forty-seven cases (76 benign and 71 malignant breast masses) were obtained by a commercially available ABUS system. Because the distance of neighboring slices in ABUS images is fixed and small, these continuous slices were used for reconstruction as three-dimensional (3-D) US images. The 3-D tumor contour was segmented using the level-set segmentation method. Then, the 3-D features, including the texture, shape and ellipsoid fitting were extracted based on the segmented 3-D tumor contour to classify benign and malignant tumors based on the logistic regression model. The Student's t test, Mann-Whitney U test and receiver operating characteristic (ROC) curve analysis were used for statistical analysis. From the Az values of ROC curves, the shape features (0.9138) are better than the texture features (0.8603) and the ellipsoid fitting features (0.8496) for classification. The difference was significant between shape and ellipsoid fitting features (p = 0.0382). However, combination of ellipsoid fitting features and shape features can achieve a best performance with accuracy of 85.0{\%} (125/147), sensitivity of 84.5{\%} (60/71), specificity of 85.5{\%} (65/76) and the area under the ROC curve Az of 0.9466. The results showed that ABUS images could be used for computer-aided feature extraction and classification of breast tumors. (E-mail: rfchang@csie.ntu.edu.tw).",
keywords = "Automated whole breast ultrasound, Breast cancer, Computer-aided diagnosis, Ellipsoid fitting, Logistic regression model",
author = "Moon, {Woo Kyung} and Shen, {Yi Wei} and Huang, {Chiun Sheng} and Chiang, {Li Ren} and Chang, {Ruey Feng}",
year = "2011",
month = "4",
day = "1",
doi = "10.1016/j.ultrasmedbio.2011.01.006",
language = "English",
volume = "37",
pages = "539--548",
journal = "Ultrasound in Medicine and Biology",
issn = "0301-5629",
publisher = "Elsevier USA",
number = "4",

}

Computer-Aided Diagnosis for the Classification of Breast Masses in Automated Whole Breast Ultrasound Images. / Moon, Woo Kyung; Shen, Yi Wei; Huang, Chiun Sheng; Chiang, Li Ren; Chang, Ruey Feng.

In: Ultrasound in Medicine and Biology, Vol. 37, No. 4, 01.04.2011, p. 539-548.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Computer-Aided Diagnosis for the Classification of Breast Masses in Automated Whole Breast Ultrasound Images

AU - Moon, Woo Kyung

AU - Shen, Yi Wei

AU - Huang, Chiun Sheng

AU - Chiang, Li Ren

AU - Chang, Ruey Feng

PY - 2011/4/1

Y1 - 2011/4/1

N2 - New automated whole breast ultrasound (ABUS) machines have recently been developed and the ultrasound (US) volume dataset of the whole breast can be acquired in a standard manner. The purpose of this study was to develop a novel computer-aided diagnosis system for classification of breast masses in ABUS images. One hundred forty-seven cases (76 benign and 71 malignant breast masses) were obtained by a commercially available ABUS system. Because the distance of neighboring slices in ABUS images is fixed and small, these continuous slices were used for reconstruction as three-dimensional (3-D) US images. The 3-D tumor contour was segmented using the level-set segmentation method. Then, the 3-D features, including the texture, shape and ellipsoid fitting were extracted based on the segmented 3-D tumor contour to classify benign and malignant tumors based on the logistic regression model. The Student's t test, Mann-Whitney U test and receiver operating characteristic (ROC) curve analysis were used for statistical analysis. From the Az values of ROC curves, the shape features (0.9138) are better than the texture features (0.8603) and the ellipsoid fitting features (0.8496) for classification. The difference was significant between shape and ellipsoid fitting features (p = 0.0382). However, combination of ellipsoid fitting features and shape features can achieve a best performance with accuracy of 85.0% (125/147), sensitivity of 84.5% (60/71), specificity of 85.5% (65/76) and the area under the ROC curve Az of 0.9466. The results showed that ABUS images could be used for computer-aided feature extraction and classification of breast tumors. (E-mail: rfchang@csie.ntu.edu.tw).

AB - New automated whole breast ultrasound (ABUS) machines have recently been developed and the ultrasound (US) volume dataset of the whole breast can be acquired in a standard manner. The purpose of this study was to develop a novel computer-aided diagnosis system for classification of breast masses in ABUS images. One hundred forty-seven cases (76 benign and 71 malignant breast masses) were obtained by a commercially available ABUS system. Because the distance of neighboring slices in ABUS images is fixed and small, these continuous slices were used for reconstruction as three-dimensional (3-D) US images. The 3-D tumor contour was segmented using the level-set segmentation method. Then, the 3-D features, including the texture, shape and ellipsoid fitting were extracted based on the segmented 3-D tumor contour to classify benign and malignant tumors based on the logistic regression model. The Student's t test, Mann-Whitney U test and receiver operating characteristic (ROC) curve analysis were used for statistical analysis. From the Az values of ROC curves, the shape features (0.9138) are better than the texture features (0.8603) and the ellipsoid fitting features (0.8496) for classification. The difference was significant between shape and ellipsoid fitting features (p = 0.0382). However, combination of ellipsoid fitting features and shape features can achieve a best performance with accuracy of 85.0% (125/147), sensitivity of 84.5% (60/71), specificity of 85.5% (65/76) and the area under the ROC curve Az of 0.9466. The results showed that ABUS images could be used for computer-aided feature extraction and classification of breast tumors. (E-mail: rfchang@csie.ntu.edu.tw).

KW - Automated whole breast ultrasound

KW - Breast cancer

KW - Computer-aided diagnosis

KW - Ellipsoid fitting

KW - Logistic regression model

UR - http://www.scopus.com/inward/record.url?scp=79952713737&partnerID=8YFLogxK

U2 - 10.1016/j.ultrasmedbio.2011.01.006

DO - 10.1016/j.ultrasmedbio.2011.01.006

M3 - Article

C2 - 21420580

AN - SCOPUS:79952713737

VL - 37

SP - 539

EP - 548

JO - Ultrasound in Medicine and Biology

JF - Ultrasound in Medicine and Biology

SN - 0301-5629

IS - 4

ER -