Computing mammographic density from a multiple regression model constructed with image-acquisition parameters from a full-field digital mammographic unit

Leejane Lu, Thomas K. Nishino, Tuenchit Khamapirad, James J. Grady, Morton H. Leonard, Donald G. Brunder

Research output: Contribution to journalArticle

15 Citations (Scopus)

Abstract

Breast density (the percentage of fibroglandular tissue in the breast) has been suggested to be a useful surrogate marker for breast cancer risk. It is conventionally measured using screen-film mammographic images by a labor-intensive histogram segmentation method (HSM). We have adapted and modified the HSM for measuring breast density from raw digital mammograms acquired by full-field digital mammography. Multiple regression model analyses showed that many of the instrument parameters for acquiring the screening mammograms (e.g. breast compression thickness, radiological thickness, radiation dose, compression force, etc) and image pixel intensity statistics of the imaged breasts were strong predictors of the observed threshold values (model R2 = 0.93) and %-density (R2 = 0.84). The intra-class correlation coefficient of the %-density for duplicate images was estimated to be 0.80, using the regression model-derived threshold values, and 0.94 if estimated directly from the parameter estimates of the %-density prediction regression model. Therefore, with additional research, these mathematical models could be used to compute breast density objectively, automatically bypassing the HSM step, and could greatly facilitate breast cancer research studies.

Original languageEnglish (US)
Article number013
Pages (from-to)4905-4921
Number of pages17
JournalPhysics in Medicine and Biology
Volume52
Issue number16
DOIs
StatePublished - Aug 21 2007

Fingerprint

Image acquisition
breast
regression analysis
acquisition
Breast
Data Compression
Breast Neoplasms
histograms
Mammography
Research
Theoretical Models
Biomarkers
Regression Analysis
Radiation
Dosimetry
Screening
Pixels
cancer
Statistics
Personnel

ASJC Scopus subject areas

  • Biomedical Engineering
  • Physics and Astronomy (miscellaneous)
  • Radiology Nuclear Medicine and imaging
  • Radiological and Ultrasound Technology

Cite this

Computing mammographic density from a multiple regression model constructed with image-acquisition parameters from a full-field digital mammographic unit. / Lu, Leejane; Nishino, Thomas K.; Khamapirad, Tuenchit; Grady, James J.; Leonard, Morton H.; Brunder, Donald G.

In: Physics in Medicine and Biology, Vol. 52, No. 16, 013, 21.08.2007, p. 4905-4921.

Research output: Contribution to journalArticle

Lu, Leejane ; Nishino, Thomas K. ; Khamapirad, Tuenchit ; Grady, James J. ; Leonard, Morton H. ; Brunder, Donald G. / Computing mammographic density from a multiple regression model constructed with image-acquisition parameters from a full-field digital mammographic unit. In: Physics in Medicine and Biology. 2007 ; Vol. 52, No. 16. pp. 4905-4921.
@article{398127dd94e04a80ba64a391ec264cc5,
title = "Computing mammographic density from a multiple regression model constructed with image-acquisition parameters from a full-field digital mammographic unit",
abstract = "Breast density (the percentage of fibroglandular tissue in the breast) has been suggested to be a useful surrogate marker for breast cancer risk. It is conventionally measured using screen-film mammographic images by a labor-intensive histogram segmentation method (HSM). We have adapted and modified the HSM for measuring breast density from raw digital mammograms acquired by full-field digital mammography. Multiple regression model analyses showed that many of the instrument parameters for acquiring the screening mammograms (e.g. breast compression thickness, radiological thickness, radiation dose, compression force, etc) and image pixel intensity statistics of the imaged breasts were strong predictors of the observed threshold values (model R2 = 0.93) and {\%}-density (R2 = 0.84). The intra-class correlation coefficient of the {\%}-density for duplicate images was estimated to be 0.80, using the regression model-derived threshold values, and 0.94 if estimated directly from the parameter estimates of the {\%}-density prediction regression model. Therefore, with additional research, these mathematical models could be used to compute breast density objectively, automatically bypassing the HSM step, and could greatly facilitate breast cancer research studies.",
author = "Leejane Lu and Nishino, {Thomas K.} and Tuenchit Khamapirad and Grady, {James J.} and Leonard, {Morton H.} and Brunder, {Donald G.}",
year = "2007",
month = "8",
day = "21",
doi = "10.1088/0031-9155/52/16/013",
language = "English (US)",
volume = "52",
pages = "4905--4921",
journal = "Physics in Medicine and Biology",
issn = "0031-9155",
publisher = "IOP Publishing Ltd.",
number = "16",

}

TY - JOUR

T1 - Computing mammographic density from a multiple regression model constructed with image-acquisition parameters from a full-field digital mammographic unit

AU - Lu, Leejane

AU - Nishino, Thomas K.

AU - Khamapirad, Tuenchit

AU - Grady, James J.

AU - Leonard, Morton H.

AU - Brunder, Donald G.

PY - 2007/8/21

Y1 - 2007/8/21

N2 - Breast density (the percentage of fibroglandular tissue in the breast) has been suggested to be a useful surrogate marker for breast cancer risk. It is conventionally measured using screen-film mammographic images by a labor-intensive histogram segmentation method (HSM). We have adapted and modified the HSM for measuring breast density from raw digital mammograms acquired by full-field digital mammography. Multiple regression model analyses showed that many of the instrument parameters for acquiring the screening mammograms (e.g. breast compression thickness, radiological thickness, radiation dose, compression force, etc) and image pixel intensity statistics of the imaged breasts were strong predictors of the observed threshold values (model R2 = 0.93) and %-density (R2 = 0.84). The intra-class correlation coefficient of the %-density for duplicate images was estimated to be 0.80, using the regression model-derived threshold values, and 0.94 if estimated directly from the parameter estimates of the %-density prediction regression model. Therefore, with additional research, these mathematical models could be used to compute breast density objectively, automatically bypassing the HSM step, and could greatly facilitate breast cancer research studies.

AB - Breast density (the percentage of fibroglandular tissue in the breast) has been suggested to be a useful surrogate marker for breast cancer risk. It is conventionally measured using screen-film mammographic images by a labor-intensive histogram segmentation method (HSM). We have adapted and modified the HSM for measuring breast density from raw digital mammograms acquired by full-field digital mammography. Multiple regression model analyses showed that many of the instrument parameters for acquiring the screening mammograms (e.g. breast compression thickness, radiological thickness, radiation dose, compression force, etc) and image pixel intensity statistics of the imaged breasts were strong predictors of the observed threshold values (model R2 = 0.93) and %-density (R2 = 0.84). The intra-class correlation coefficient of the %-density for duplicate images was estimated to be 0.80, using the regression model-derived threshold values, and 0.94 if estimated directly from the parameter estimates of the %-density prediction regression model. Therefore, with additional research, these mathematical models could be used to compute breast density objectively, automatically bypassing the HSM step, and could greatly facilitate breast cancer research studies.

UR - http://www.scopus.com/inward/record.url?scp=34547806215&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34547806215&partnerID=8YFLogxK

U2 - 10.1088/0031-9155/52/16/013

DO - 10.1088/0031-9155/52/16/013

M3 - Article

VL - 52

SP - 4905

EP - 4921

JO - Physics in Medicine and Biology

JF - Physics in Medicine and Biology

SN - 0031-9155

IS - 16

M1 - 013

ER -