Deep Learning Model Uses Spatiotemporal Asymmetries in Sequential Mammograms for Breast Cancer Risk Prediction

A deep learning model was developed to predict breast cancer risk by capturing bilateral and longitudinal asymmetries on sequential screening mammograms. The retrospective study used 406 cancer patients and 6,053 controls from CSAW-CC, plus an independent set of 293 cancer patie…

• Retrospective case–control study design.
• Model trained on CSAW-CC (406 cancer patients, 6,053 controls) and an independent dataset (293 cancer patients).
• Model explicitly captures bilateral and longitudinal asymmetries between mammograms.

Automated summary

RadPigeon summaries are original and for information only. They are not clinical advice.