Quantitative analysis for breast density estimation in low dose chest CT scans

Woo Kyung Moon, Chung Ming Lo, Jin Mo Goo, Min Sun Bae, Jung Min Chang, Chiun Sheng Huang, Jeon Hor Chen, Violeta Ivanova, Ruey Feng Chang

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

A computational method was developed for the measurement of breast density using chest computed tomography (CT) images and the correlation between that and mammographic density. Sixty-nine asymptomatic Asian women (138 breasts) were studied. With the marked lung area and pectoralis muscle line in a template slice, demons algorithm was applied to the consecutive CT slices for automatically generating the defined breast area. The breast area was then analyzed using fuzzy c-mean clustering to separate fibroglandular tissue from fat tissues. The fibroglandular clusters obtained from all CT slices were summed then divided by the summation of the total breast area to calculate the percent density for CT. The results were compared with the density estimated from mammographic images. For CT breast density, the coefficient of variations of intraoperator and interoperator measurement were 3.00 % (0.59 %-8.52 %) and 3.09 % (0.20 %-6.98 %), respectively. Breast density measured from CT (22∈±∈0.6 %) was lower than that of mammography (34∈±∈1.9 %) with Pearson correlation coefficient of r∈=∈0.88. The results suggested that breast density measured from chest CT images correlated well with that from mammography. Reproducible 3D information on breast density can be obtained with the proposed CT-based quantification methods.

Original languageEnglish
Article number21
JournalJournal of Medical Systems
Volume38
Issue number3
DOIs
Publication statusPublished - 2014
Externally publishedYes

Fingerprint

Tomography
Thorax
Chemical analysis
Breast
Mammography
Tissue
Pectoralis Muscles
Breast Density
Computational methods
Oils and fats
Cluster Analysis
Muscle
Fats
Lung

Keywords

  • Breast density
  • CT
  • Fuzzy c-mean
  • Image registration
  • Mammography

ASJC Scopus subject areas

  • Medicine (miscellaneous)
  • Health Informatics
  • Health Information Management
  • Information Systems
  • Medicine(all)

Cite this

Moon, W. K., Lo, C. M., Goo, J. M., Bae, M. S., Chang, J. M., Huang, C. S., ... Chang, R. F. (2014). Quantitative analysis for breast density estimation in low dose chest CT scans. Journal of Medical Systems, 38(3), [21]. https://doi.org/10.1007/s10916-014-0021-5

Quantitative analysis for breast density estimation in low dose chest CT scans. / Moon, Woo Kyung; Lo, Chung Ming; Goo, Jin Mo; Bae, Min Sun; Chang, Jung Min; Huang, Chiun Sheng; Chen, Jeon Hor; Ivanova, Violeta; Chang, Ruey Feng.

In: Journal of Medical Systems, Vol. 38, No. 3, 21, 2014.

Research output: Contribution to journalArticle

Moon, WK, Lo, CM, Goo, JM, Bae, MS, Chang, JM, Huang, CS, Chen, JH, Ivanova, V & Chang, RF 2014, 'Quantitative analysis for breast density estimation in low dose chest CT scans', Journal of Medical Systems, vol. 38, no. 3, 21. https://doi.org/10.1007/s10916-014-0021-5
Moon, Woo Kyung ; Lo, Chung Ming ; Goo, Jin Mo ; Bae, Min Sun ; Chang, Jung Min ; Huang, Chiun Sheng ; Chen, Jeon Hor ; Ivanova, Violeta ; Chang, Ruey Feng. / Quantitative analysis for breast density estimation in low dose chest CT scans. In: Journal of Medical Systems. 2014 ; Vol. 38, No. 3.
@article{3a5707604aac4e00a1012f94c77d7d7d,
title = "Quantitative analysis for breast density estimation in low dose chest CT scans",
abstract = "A computational method was developed for the measurement of breast density using chest computed tomography (CT) images and the correlation between that and mammographic density. Sixty-nine asymptomatic Asian women (138 breasts) were studied. With the marked lung area and pectoralis muscle line in a template slice, demons algorithm was applied to the consecutive CT slices for automatically generating the defined breast area. The breast area was then analyzed using fuzzy c-mean clustering to separate fibroglandular tissue from fat tissues. The fibroglandular clusters obtained from all CT slices were summed then divided by the summation of the total breast area to calculate the percent density for CT. The results were compared with the density estimated from mammographic images. For CT breast density, the coefficient of variations of intraoperator and interoperator measurement were 3.00 {\%} (0.59 {\%}-8.52 {\%}) and 3.09 {\%} (0.20 {\%}-6.98 {\%}), respectively. Breast density measured from CT (22∈±∈0.6 {\%}) was lower than that of mammography (34∈±∈1.9 {\%}) with Pearson correlation coefficient of r∈=∈0.88. The results suggested that breast density measured from chest CT images correlated well with that from mammography. Reproducible 3D information on breast density can be obtained with the proposed CT-based quantification methods.",
keywords = "Breast density, CT, Fuzzy c-mean, Image registration, Mammography",
author = "Moon, {Woo Kyung} and Lo, {Chung Ming} and Goo, {Jin Mo} and Bae, {Min Sun} and Chang, {Jung Min} and Huang, {Chiun Sheng} and Chen, {Jeon Hor} and Violeta Ivanova and Chang, {Ruey Feng}",
year = "2014",
doi = "10.1007/s10916-014-0021-5",
language = "English",
volume = "38",
journal = "Journal of Medical Systems",
issn = "0148-5598",
publisher = "Springer New York",
number = "3",

}

TY - JOUR

T1 - Quantitative analysis for breast density estimation in low dose chest CT scans

AU - Moon, Woo Kyung

AU - Lo, Chung Ming

AU - Goo, Jin Mo

AU - Bae, Min Sun

AU - Chang, Jung Min

AU - Huang, Chiun Sheng

AU - Chen, Jeon Hor

AU - Ivanova, Violeta

AU - Chang, Ruey Feng

PY - 2014

Y1 - 2014

N2 - A computational method was developed for the measurement of breast density using chest computed tomography (CT) images and the correlation between that and mammographic density. Sixty-nine asymptomatic Asian women (138 breasts) were studied. With the marked lung area and pectoralis muscle line in a template slice, demons algorithm was applied to the consecutive CT slices for automatically generating the defined breast area. The breast area was then analyzed using fuzzy c-mean clustering to separate fibroglandular tissue from fat tissues. The fibroglandular clusters obtained from all CT slices were summed then divided by the summation of the total breast area to calculate the percent density for CT. The results were compared with the density estimated from mammographic images. For CT breast density, the coefficient of variations of intraoperator and interoperator measurement were 3.00 % (0.59 %-8.52 %) and 3.09 % (0.20 %-6.98 %), respectively. Breast density measured from CT (22∈±∈0.6 %) was lower than that of mammography (34∈±∈1.9 %) with Pearson correlation coefficient of r∈=∈0.88. The results suggested that breast density measured from chest CT images correlated well with that from mammography. Reproducible 3D information on breast density can be obtained with the proposed CT-based quantification methods.

AB - A computational method was developed for the measurement of breast density using chest computed tomography (CT) images and the correlation between that and mammographic density. Sixty-nine asymptomatic Asian women (138 breasts) were studied. With the marked lung area and pectoralis muscle line in a template slice, demons algorithm was applied to the consecutive CT slices for automatically generating the defined breast area. The breast area was then analyzed using fuzzy c-mean clustering to separate fibroglandular tissue from fat tissues. The fibroglandular clusters obtained from all CT slices were summed then divided by the summation of the total breast area to calculate the percent density for CT. The results were compared with the density estimated from mammographic images. For CT breast density, the coefficient of variations of intraoperator and interoperator measurement were 3.00 % (0.59 %-8.52 %) and 3.09 % (0.20 %-6.98 %), respectively. Breast density measured from CT (22∈±∈0.6 %) was lower than that of mammography (34∈±∈1.9 %) with Pearson correlation coefficient of r∈=∈0.88. The results suggested that breast density measured from chest CT images correlated well with that from mammography. Reproducible 3D information on breast density can be obtained with the proposed CT-based quantification methods.

KW - Breast density

KW - CT

KW - Fuzzy c-mean

KW - Image registration

KW - Mammography

UR - http://www.scopus.com/inward/record.url?scp=84898902039&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84898902039&partnerID=8YFLogxK

U2 - 10.1007/s10916-014-0021-5

DO - 10.1007/s10916-014-0021-5

M3 - Article

C2 - 24643751

AN - SCOPUS:84898902039

VL - 38

JO - Journal of Medical Systems

JF - Journal of Medical Systems

SN - 0148-5598

IS - 3

M1 - 21

ER -