Misclassification of Breast Imaging Reporting and Data System (BI-RADS) Mammographic Density and Implications for Breast Density Reporting Legislation

Abstract

USA states have begun legislating mammographic breast density reporting to women, requiring that women undergoing screening mammography who have dense breast tissue (Breast Imaging Reporting and Data System [BI-RADS] density c or d) receive written notification of their breast density; however, the impact that misclassification of breast density will have on this reporting remains unclear. The aim of this study was to assess reproducibility of the four-category BI-RADS density measure and examine its relationship with a continuous measure of percent density. We enrolled 19 radiologists, experienced in breast imaging, from a single integrated health care system. Radiologists interpreted 341 screening mammograms at two points in time 6 months apart. We assessed intra- and interobserver agreement in radiologists'; interpretations of BI-RADS density and explored whether agreement depended upon radiologist characteristics. We examined the relationship between BI-RADS density and percent density in a subset of 282 examinations. Intraradiologist agreement was moderate to substantial, with kappa varying across radiologists from 0.50 to 0.81 (mean = 0.69, 95% CI [0.63, 0.73]). Intraradiologist agreement was higher for radiologists with ≥10 years experience interpreting mammograms (difference in mean kappa = 0.10, 95% CI [0.01, 0.24]). Interradiologist agreement varied widely across radiologist pairs from slight to substantial, with kappa ranging from 0.02 to 0.72 (mean = 0.46, 95% CI [0.36, 0.55]). Of 145 examinations interpreted as "nondense" (BI-RADS density a or b) by the majority of radiologists, 82.8% were interpreted as "dense" (BI-RADS density c or d) by at least one radiologist. Of 187 examinations interpreted as "dense" by the majority of radiologists, 47.1% were interpreted as "nondense" by at least one radiologist. While the examinations of almost half of the women in our study were interpreted clinically as having BI-RADS density c or d, only about 10% of examinations had percent density >50%. Our results suggest that breast density reporting based on a single BI-RADS density interpretation may be misleading due to high interradiologist variability and a lack of correspondence between BI-RADS density and percent density.

Keywords: BI-RADS density; breast density reporting legislation; intra- and interradiologist agreement; misclassification; percent density.

Figure 1

Distributions of BI-RADS density interpretations from the test setting^* by radiologist, clinical BI-RADS density interpretations, and majority report from the test setting^*ƚ. ^*Unassisted interpretations ^ƚMajority report was determined for each examination as the mode of BI-RADS density interpretations from the test setting for that examination.

Figure 2

Distributions of percent density within each category of clinical BI-RADS density. The dashed horizontal lines provide the ranges of percent density that would be expected within each BI-RADS density category based on the BI-RADS 4^th edition density definition. The thick horizontal line provides the median and the box provides the interquartile range for each category of clinical BI-RADS density. Whiskers extend 1.5 times the interquartile range. Outliers are also plotted.

Figure 3

Distributions of percent density for (top to bottom) BI-RADS density category a, b, c, and d interpretations^* from the test setting, by radiologist. ^*Unassisted interpretations The dashed vertical lines provide the ranges of percent density that would be expected within each BI-RADS density category based on the BI-RADS 4^th edition density definition. The solid vertical lines provide, for each BI-RADS density category, the overall median of percent density measurements for that category. For a given BI-RADS density category, the overall median was calculated as the median of the median of percent density measurements for each radiologist. Curves based on majority report are overlaid in thick black.