Statistical evaluation of a fully automated mammographic breast density algorithm

Visual assessments of mammographic breast density by radiologists are used in clinical practice; however, these assessments have shown weaker associations with breast cancer risk than area-based, quantitative methods. The purpose of this study is to present a statistical evaluation of a fully automated, area-based mammographic density measurement algorithm. Five radiologists estimated density in 5% increments for 138 "For Presentation" single MLO views; the median of the radiologists' estimates was used as the reference standard. Agreement amongst radiologists was excellent, ICC = 0.884, 95% CI (0.854, 0.910). Similarly, the agreement between the algorithm and the reference standard was excellent, ICC = 0.862, falling within the 95% CI of the radiologists' estimates. The Bland-Altman plot showed that the reference standard was slightly positively biased (+1.86%) compared to the algorithm-generated densities. A scatter plot showed that the algorithm moderately overestimated low densities and underestimated high densities. A box plot showed that 95% of the algorithm-generated assessments fell within one BI-RADS category of the reference standard. This study demonstrates the effective use of several statistical techniques that collectively produce a comprehensive evaluation of the algorithm and its potential to provide mammographic density measures that can be used to inform clinical practice.