Mammographic Breast Density: Comparison of Methods for Quantitative Evaluation

Purpose: To evaluate the results from two software tools for measurement of mammographic breast density and compare them with observer-based scores in a large cohort of women. Materials and Methods: Following written informed consent, a data set of 36 281 mammograms from 8867 women were collected from six United Kingdom centers in an ethically approved trial. Breast density was assessed by one of 26 readers on a visual analog scale and with two automated density tools. Mean differences were calculated as the mean of all the individual percentage differences between each measurement for each case (woman). Agreement in total breast volume, fibroglandular volume, and percentage density was assessed with the Bland-Altman method. Association with observer's scores was calculated by using the Pearson correlation coefficient (r). Results: Correlation between the Quantra and Volpara outputs for total breast volume was r = 0.97 (P < .001), with a mean difference of 43.5 cm(3) for all cases representing 5.0% of the mean total breast volume. Correlation of the two measures was lower for fibroglandular volume (r = 0.86, P < .001). The mean difference was 30.3 cm(3) for all cases representing 21.2% of the mean fibroglandular tissue volume result. Quantra gave the larger value and the difference tended to increase with volume. For the two measures of percentage volume density, the mean difference was 1.61 percentage points (r = 0.78, P < .001). Comparison of observer's scores with the area-based density given by Quantra yielded a low correlation (r = 0.55, P < .001). Correlations of observer's scores with the volumetric density results gave r values of 0.60 (P < .001) and 0.63 (P < .001) for Quantra and Volpara, respectively. Conclusion: Automated techniques for measuring breast density show good correlation, but these are poorly correlated with observer's scores. However automated techniques do give different results that should be considered when informing patient personalized imaging. (C) RSNA, 2015