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, Lee Jane W.
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
C2 - 17671343
AN - SCOPUS:34547806215
SN - 0031-9155
VL - 52
SP - 4905
EP - 4921
JO - Physics in Medicine and Biology
JF - Physics in Medicine and Biology
IS - 16
M1 - 013
ER -