Quantitative analysis of breast echotexture patterns in automated breast ultrasound images

Ruey Feng Chang, Yu Ling Hou, Chung Ming Lo, Chiun Sheng Huang, Jeon Hor Chen, Won Hwa Kim, Jung Min Chang, Min Sun Bae, Woo Kyung Moon

研究成果: 雜誌貢獻文章

4 引文 (Scopus)

摘要

Purpose: Breast tissue composition is considered to be associated with breast cancer risk. This study aimed to develop a computer-aided classification (CAC) system to automatically classify echotexture patterns as heterogeneous or homogeneous using automated breast ultrasound (ABUS) images. Methods: A CAC system was proposed that can recognize breast echotexture patterns in ABUS images. For each case, the echotexture pattern was assessed by two expert radiologists and classified as heterogeneous or homogeneous. After neutrosophic image transformation and fuzzy c-mean clusterings, the lower and upper boundaries of the fibroglandular tissues were defined. Then, the number of hypoechoic regions and histogram features were extracted from the fibroglandular tissues, and the support vector machine model with the leave-one-out cross-validation method was utilized as the classifier. The authors' database included a total of 208 ABUS images of the breasts of 104 females. Results: The accuracies of the proposed system for the classification of heterogeneous and homogeneous echotexture patterns were 93.48% (43/46) and 92.59% (150/162), respectively, with an overall Az (area under the receiver operating characteristic curve) of 0.9786. The agreement between the radiologists and the proposed system was almost perfect, with a kappa value of 0.814. Conclusions: The use of ABUS and the proposed method can provide quantitative information on the echotexture patterns of the breast and can be used to evaluate whether breast echotexture patterns are associated with breast cancer risk in the future.
原文英語
頁(從 - 到)4566-4578
頁數13
期刊Medical Physics
42
發行號8
DOIs
出版狀態已發佈 - 八月 1 2015
對外發佈Yes

指紋

Breast
Breast Neoplasms
ROC Curve
Cluster Analysis
Databases

ASJC Scopus subject areas

  • Biophysics
  • Radiology Nuclear Medicine and imaging

引用此文

Chang, R. F., Hou, Y. L., Lo, C. M., Huang, C. S., Chen, J. H., Kim, W. H., ... Moon, W. K. (2015). Quantitative analysis of breast echotexture patterns in automated breast ultrasound images. Medical Physics, 42(8), 4566-4578. https://doi.org/10.1118/1.4923754

Quantitative analysis of breast echotexture patterns in automated breast ultrasound images. / Chang, Ruey Feng; Hou, Yu Ling; Lo, Chung Ming; Huang, Chiun Sheng; Chen, Jeon Hor; Kim, Won Hwa; Chang, Jung Min; Bae, Min Sun; Moon, Woo Kyung.

於: Medical Physics, 卷 42, 編號 8, 01.08.2015, p. 4566-4578.

研究成果: 雜誌貢獻文章

Chang, RF, Hou, YL, Lo, CM, Huang, CS, Chen, JH, Kim, WH, Chang, JM, Bae, MS & Moon, WK 2015, 'Quantitative analysis of breast echotexture patterns in automated breast ultrasound images', Medical Physics, 卷 42, 編號 8, 頁 4566-4578. https://doi.org/10.1118/1.4923754
Chang, Ruey Feng ; Hou, Yu Ling ; Lo, Chung Ming ; Huang, Chiun Sheng ; Chen, Jeon Hor ; Kim, Won Hwa ; Chang, Jung Min ; Bae, Min Sun ; Moon, Woo Kyung. / Quantitative analysis of breast echotexture patterns in automated breast ultrasound images. 於: Medical Physics. 2015 ; 卷 42, 編號 8. 頁 4566-4578.
@article{9f967bb038c543ccbb17cffabcff13a2,
title = "Quantitative analysis of breast echotexture patterns in automated breast ultrasound images",
abstract = "Purpose: Breast tissue composition is considered to be associated with breast cancer risk. This study aimed to develop a computer-aided classification (CAC) system to automatically classify echotexture patterns as heterogeneous or homogeneous using automated breast ultrasound (ABUS) images. Methods: A CAC system was proposed that can recognize breast echotexture patterns in ABUS images. For each case, the echotexture pattern was assessed by two expert radiologists and classified as heterogeneous or homogeneous. After neutrosophic image transformation and fuzzy c-mean clusterings, the lower and upper boundaries of the fibroglandular tissues were defined. Then, the number of hypoechoic regions and histogram features were extracted from the fibroglandular tissues, and the support vector machine model with the leave-one-out cross-validation method was utilized as the classifier. The authors' database included a total of 208 ABUS images of the breasts of 104 females. Results: The accuracies of the proposed system for the classification of heterogeneous and homogeneous echotexture patterns were 93.48{\%} (43/46) and 92.59{\%} (150/162), respectively, with an overall Az (area under the receiver operating characteristic curve) of 0.9786. The agreement between the radiologists and the proposed system was almost perfect, with a kappa value of 0.814. Conclusions: The use of ABUS and the proposed method can provide quantitative information on the echotexture patterns of the breast and can be used to evaluate whether breast echotexture patterns are associated with breast cancer risk in the future.",
keywords = "automated breast ultrasound, breast cancer, computer-aided classification, echotexture, mammographic density",
author = "Chang, {Ruey Feng} and Hou, {Yu Ling} and Lo, {Chung Ming} and Huang, {Chiun Sheng} and Chen, {Jeon Hor} and Kim, {Won Hwa} and Chang, {Jung Min} and Bae, {Min Sun} and Moon, {Woo Kyung}",
year = "2015",
month = "8",
day = "1",
doi = "10.1118/1.4923754",
language = "English",
volume = "42",
pages = "4566--4578",
journal = "Medical Physics",
issn = "0094-2405",
publisher = "AAPM - American Association of Physicists in Medicine",
number = "8",

}

TY - JOUR

T1 - Quantitative analysis of breast echotexture patterns in automated breast ultrasound images

AU - Chang, Ruey Feng

AU - Hou, Yu Ling

AU - Lo, Chung Ming

AU - Huang, Chiun Sheng

AU - Chen, Jeon Hor

AU - Kim, Won Hwa

AU - Chang, Jung Min

AU - Bae, Min Sun

AU - Moon, Woo Kyung

PY - 2015/8/1

Y1 - 2015/8/1

N2 - Purpose: Breast tissue composition is considered to be associated with breast cancer risk. This study aimed to develop a computer-aided classification (CAC) system to automatically classify echotexture patterns as heterogeneous or homogeneous using automated breast ultrasound (ABUS) images. Methods: A CAC system was proposed that can recognize breast echotexture patterns in ABUS images. For each case, the echotexture pattern was assessed by two expert radiologists and classified as heterogeneous or homogeneous. After neutrosophic image transformation and fuzzy c-mean clusterings, the lower and upper boundaries of the fibroglandular tissues were defined. Then, the number of hypoechoic regions and histogram features were extracted from the fibroglandular tissues, and the support vector machine model with the leave-one-out cross-validation method was utilized as the classifier. The authors' database included a total of 208 ABUS images of the breasts of 104 females. Results: The accuracies of the proposed system for the classification of heterogeneous and homogeneous echotexture patterns were 93.48% (43/46) and 92.59% (150/162), respectively, with an overall Az (area under the receiver operating characteristic curve) of 0.9786. The agreement between the radiologists and the proposed system was almost perfect, with a kappa value of 0.814. Conclusions: The use of ABUS and the proposed method can provide quantitative information on the echotexture patterns of the breast and can be used to evaluate whether breast echotexture patterns are associated with breast cancer risk in the future.

AB - Purpose: Breast tissue composition is considered to be associated with breast cancer risk. This study aimed to develop a computer-aided classification (CAC) system to automatically classify echotexture patterns as heterogeneous or homogeneous using automated breast ultrasound (ABUS) images. Methods: A CAC system was proposed that can recognize breast echotexture patterns in ABUS images. For each case, the echotexture pattern was assessed by two expert radiologists and classified as heterogeneous or homogeneous. After neutrosophic image transformation and fuzzy c-mean clusterings, the lower and upper boundaries of the fibroglandular tissues were defined. Then, the number of hypoechoic regions and histogram features were extracted from the fibroglandular tissues, and the support vector machine model with the leave-one-out cross-validation method was utilized as the classifier. The authors' database included a total of 208 ABUS images of the breasts of 104 females. Results: The accuracies of the proposed system for the classification of heterogeneous and homogeneous echotexture patterns were 93.48% (43/46) and 92.59% (150/162), respectively, with an overall Az (area under the receiver operating characteristic curve) of 0.9786. The agreement between the radiologists and the proposed system was almost perfect, with a kappa value of 0.814. Conclusions: The use of ABUS and the proposed method can provide quantitative information on the echotexture patterns of the breast and can be used to evaluate whether breast echotexture patterns are associated with breast cancer risk in the future.

KW - automated breast ultrasound

KW - breast cancer

KW - computer-aided classification

KW - echotexture

KW - mammographic density

UR - http://www.scopus.com/inward/record.url?scp=84937047005&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84937047005&partnerID=8YFLogxK

U2 - 10.1118/1.4923754

DO - 10.1118/1.4923754

M3 - Article

C2 - 26233185

AN - SCOPUS:84937047005

VL - 42

SP - 4566

EP - 4578

JO - Medical Physics

JF - Medical Physics

SN - 0094-2405

IS - 8

ER -