The DeepJoint Algorithm: An Innovative Approach for Studying the Longitudinal Evolution of Quantitative Mammographic Density and Its Association With Screen-Detected Breast Cancer Risk

DeepJoint算法:一种研究定量乳腺X线摄影密度纵向演变及其与筛查发现的乳腺癌风险之间关联的创新方法

阅读:1

Abstract

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.

特别声明

1、本页面内容包含部分的内容是基于公开信息的合理引用;引用内容仅为补充信息,不代表本站立场。

2、若认为本页面引用内容涉及侵权,请及时与本站联系,我们将第一时间处理。

3、其他媒体/个人如需使用本页面原创内容,需注明“来源:[生知库]”并获得授权;使用引用内容的,需自行联系原作者获得许可。

4、投稿及合作请联系:info@biocloudy.com。