Validation of a new fully automated software for 2D digital mammographic breast density evaluation in predicting breast cancer risk

We compared accuracy for breast cancer (BC) risk stratification of a new fully automated system (DenSeeMammo—DSM) for breast density (BD) assessment to a non-inferiority threshold based on radiologists’ visual assessment. Pooled analysis was performed on 14,267 2D mammograms collected from women aged 48–55 years who underwent BC screening within three studies: RETomo, Florence study and PROCAS. BD was expressed through clinical Breast Imaging Reporting and Data System (BI-RADS) density classification. Women in BI-RADS D category had a 2.6 (95% CI 1.5–4.4) and a 3.6 (95% CI 1.4–9.3) times higher risk of incident and interval cancer, respectively, than women in the two lowest BD categories. The ability of DSM to predict risk of incident cancer was non-inferior to radiologists’ visual assessment as both point estimate and lower bound of 95% CI (AUC 0.589; 95% CI 0.580–0.597) were above the predefined visual assessment threshold (AUC 0.571). AUC for interval (AUC 0.631; 95% CI 0.623–0.639) cancers was even higher. BD assessed with new fully automated method is positively associated with BC risk and is not inferior to radiologists’ visual assessment. It is an even stronger marker of interval cancer, confirming an appreciable masking effect of BD that reduces mammography sensitivity.