Deriving a mammogram-based risk score from screening digital breast tomosynthesis for 5-year breast cancer risk prediction.

Abstract

Screening digital breast tomosynthesis (DBT) aims to identify breast cancer early when treatment is most effective leading to reduced mortality. In addition to early detection, the information contained within DBT images may also inform subsequent risk stratification and guide risk-reducing management. Using transfer learning we refined a model in the WashU cohort of 5,066 women with DBT screening (mean age 54.6) among whom 105 were diagnosed with breast cancer (26 DCIS). We applied the model to external data from the EMBED cohort of 7,017 women free from cancer (mean age 55.4) among whom 111 pathology confirmed breast cancer cases were diagnosed more than 6 months after initial DBT (17 DCIS). We obtained a 5-year area under the curve (AUC) = 0.75 (95% confidence interval (CI) = 0.73 - 0.78) in the internal validation. The model validated in external data gave an AUC = 0.72 (95% CI, 0.69 - 0.75). The AUC was unchanged when age and BI-RADS density are added to the model with synthetic DBT image. The model significantly outperforms the Tyrer-Cuzick model 5-year AUC 0.56 (95%CI 0.54, 0.58) (p<0.01). Our model extends risk prediction applications to synthetic DBT, provides 5-year risk estimates, and is readily calibrated to national risk strata for clinical translation and guideline driven risk management. The model could be implemented within any digital mammography program.