Ordinal Learning: Longitudinal Attention Alignment Model for Predicting Time to Future Breast Cancer Events from Mammograms
This work addresses the need for more precise and interpretable breast cancer risk assessment to improve screening and prevention, though it appears incremental as it builds on existing deep learning models.
The paper tackles the problem of predicting time to future breast cancer events from mammograms by modeling ordinal relationships and longitudinal tissue changes, resulting in a method that outperforms existing approaches in both risk and time prediction tasks.
Precision breast cancer (BC) risk assessment is crucial for developing individualized screening and prevention. Despite the promising potential of recent mammogram (MG) based deep learning models in predicting BC risk, they mostly overlook the 'time-to-future-event' ordering among patients and exhibit limited explorations into how they track history changes in breast tissue, thereby limiting their clinical application. In this work, we propose a novel method, named OA-BreaCR, to precisely model the ordinal relationship of the time to and between BC events while incorporating longitudinal breast tissue changes in a more explainable manner. We validate our method on public EMBED and inhouse datasets, comparing with existing BC risk prediction and time prediction methods. Our ordinal learning method OA-BreaCR outperforms existing methods in both BC risk and time-to-future-event prediction tasks. Additionally, ordinal heatmap visualizations show the model's attention over time. Our findings underscore the importance of interpretable and precise risk assessment for enhancing BC screening and prevention efforts. The code will be accessible to the public.