Ordinal Learning: Longitudinal Attention Alignment Model for Predicting Time to Future Breast Cancer Events from Mammograms

TL;DR

This paper introduces OA-BreaCR, a novel ordinal learning model that improves breast cancer risk and time-to-event prediction from mammograms by modeling longitudinal tissue changes and event ordering, with enhanced interpretability.

Contribution

The paper presents OA-BreaCR, a new ordinal learning approach that explicitly models the timing and progression of breast cancer events using longitudinal mammogram data.

Findings

Outperforms existing risk prediction models on public and inhouse datasets.

Provides explainable attention maps over time.

Enhances clinical interpretability of breast cancer risk assessments.

Abstract

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.