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

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

Research output: Contribution to journalArticle

15 Scopus citations

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

ASJC Scopus subject areas

  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging

Fingerprint Dive into the research topics of 'Computing mammographic density from a multiple regression model constructed with image-acquisition parameters from a full-field digital mammographic unit'. Together they form a unique fingerprint.

  • Cite this