The Impact of Longitudinal Mammogram Alignment on Breast Cancer Risk Assessment

TL;DR

This study evaluates various alignment strategies for longitudinal mammogram analysis, demonstrating that image-based registration significantly improves breast cancer risk prediction accuracy and robustness over other methods.

Contribution

It provides a comprehensive comparison of alignment methods, highlighting the superiority of image-based registration for deep learning-based risk modeling in mammography.

Findings

Image-based registration outperforms feature-based and implicit methods across metrics.

Regularizing deformation fields improves deformation quality but can reduce prediction performance.

Applying image-based deformation fields within feature space yields the best risk prediction results.

Abstract

Regular mammography screening is crucial for early breast cancer detection. By leveraging deep learning-based risk models, screening intervals can be personalized, especially for high-risk individuals. While recent methods increasingly incorporate longitudinal information from prior mammograms, accurate spatial alignment across time points remains a key challenge. Misalignment can obscure meaningful tissue changes and degrade model performance. In this study, we provide insights into various alignment strategies, image-based registration, feature-level (representation space) alignment with and without regularization, and implicit alignment methods, for their effectiveness in longitudinal deep learning-based risk modeling. Using two large-scale mammography datasets, we assess each method across key metrics, including predictive accuracy, precision, recall, and deformation field quality. Our results show that image-based registration consistently outperforms the more recently favored feature-based and implicit approaches across all metrics, enabling more accurate, temporally consistent predictions and generating smooth, anatomically plausible deformation fields. Although regularizing the deformation field improves deformation quality, it reduces the risk prediction performance of feature-level alignment. Applying image-based deformation fields within the feature space yields the best risk prediction performance. These findings underscore the importance of image-based deformation fields for spatial alignment in longitudinal risk modeling, offering improved prediction accuracy and robustness. This approach has strong potential to enhance personalized screening and enable earlier interventions for high-risk individuals. The code is available at https://github.com/sot176/Mammogram_Alignment_Study_Risk_Prediction.git, allowing full reproducibility of the results.