Predicting 5-Year Breast Cancer Risk From Longitudinal Digital Breast Tomosynthesis: A Single-Center Retrospective Study.
Longitudinal AI model beats single-timepoint scans predicting 5-year breast cancer risk
Predicting 5-Year Breast Cancer Risk From Longitudinal Digital Breast Tomosynthesis: A Single-Center Retrospective Study.
Imaging-based breast cancer risk prediction models primarily use full-field digital mammography (full-field digital mammography).
The aim of this study was to develop and evaluate a deep learning model that uses longitudinal digital breast tomosynthesis examinations to predict long-term breast cancer risk.
This retrospective study included 313,335 digital breast tomosynthesis examinations from 161,077 women (mean age, 58.5 ± 11.7 years) between January 2016 and August 2020 at a single health institution.
AUROC; 1.0 is perfect, and the longitudinal model outperformed single-scan and Mirai models
In a matched case-control cohort (n = 432), the DRP model achieved a 5-year AUC of 0.676 (95% CI, 0.626-0.726), compared with 0.563 (95% CI, 0.509-0.619; p < .001) for the Tyrer-Cuzick model.
Among examinations of women with extremely dense breasts, the model classified 39.7% (746/1877) as average risk, with an observed 5-year cancer incidence of 0.8% (6/746).
Among examinations of women with fatty breasts, the model classified 14.8% (386/2605) as high risk, with an observed 5-year cancer incidence of 2.6% (10/386).
A deep learning model using longitudinal digital breast tomosynthesis examinations improved long-term breast cancer risk prediction compared with full-field digital mammography-based and clinical risk models.
Clinical Impact: Longitudinal digital breast tomosynthesis-based risk prediction has the potential to inform dynamic risk assessment using screening images and to support future personalized screening strategies.