High mammographic density is a well-known risk factor for breast cancer and reduces the sensitivity of mammography-based screening. While automated machine and deep learning-based methods provide more consistent and precise measurements compared to subjective Breast Imaging Reporting and Data System (BI-RADS) assessments, they often fail to account for the longitudinal evolution of density. Many of these methods assess mammographic density in a cross-sectional manner, overlooking correlations in repeated measures, irregular visit intervals, missing data, and informative dropouts. Joint models address these limitations by simultaneously modeling the relationship between longitudinal biomarkers and time-to-event outcomes. We introduce the DeepJoint algorithm, an open-source method combining deep learning-based mammographic density estimation with joint modeling to assess its longitudinal relationship with breast cancer risk. Our approach adequately analyzes processed mammograms from various manufacturers, estimating both dense area and percent density, two established risk factors for breast cancer. We utilize a joint model to explore their association with breast cancer risk and provide individualized risk predictions. Bayesian inference and the consensus Monte Carlo algorithm make the approach reliable for large screening datasets. By integrating deep learning with joint modeling, our new method provides a robust, comprehensive framework for evaluating breast cancer risk based on longitudinal density profiles. The complete pipeline is publicly available, promoting broader application and comparison with other methods.
Rakez et al. (Fri,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: