Breast Density Evaluation Using Spectral Mammography, Radiologist Reader Assessment, and Segmentation Techniques: A Retrospective Study Based on Left and Right Breast Comparison

Abstract

The purpose of this study was to compare the precision of mammographic breast density measurement using radiologist reader assessment, histogram threshold segmentation, fuzzy C-mean segmentation, and spectral material decomposition. Spectral mammography images from a total of 92 consecutive asymptomatic women (aged 50-69years) who presented for annual screening mammography were retrospectively analyzed for this study. Breast density was estimated using 10 radiologist reader assessment, standard histogram thresholding, fuzzy C-mean algorithm, and spectral material decomposition. The breast density correlation between left and right breasts was used to assess the precision of these techniques to measure breast composition relative to dual-energy material decomposition. In comparison to the other techniques, the results of breast density measurements using dual-energy material decomposition showed the highest correlation. The relative standard error of estimate for breast density measurements from left and right breasts using radiologist reader assessment, standard histogram thresholding, fuzzy C-mean algorithm, and dual-energy material decomposition was calculated to be 1.95, 2.87, 2.07, and 1.00, respectively. The results indicate that the precision of dual-energy material decomposition was approximately factor of two higher than the other techniques with regard to better correlation of breast density measurements from right and left breasts.