Breast cancer risk prediction improves using aligned multi-view screening histories
Explicitly Aligned Multi-View Breast Cancer Risk Prediction from Variable-Length Screening Histories
Computer Vision and Pattern RecognitionArtificial Intelligence
Summary
Predicting breast cancer risk from mammograms can be better if we look at how breast tissue changes over time and use images taken from different angles. The authors created a method that matches the same breast areas across multiple past exams and combines the two key image views to get more accurate predictions. Their approach works even if the number of past exams varies and outperforms older methods in tests on real data. They also released software to fairly compare different breast cancer risk prediction techniques.
What this means in practice
- •For breast imaging software developers: Create risk prediction tools that use multiple mammogram views over time with better alignment for improved breast cancer screening decisions.$Commercial implications: Enables development of advanced commercial breast screening software offering enhanced personalized risk assessments from mammogram histories.
- •For hospital radiology departments: Integrate a risk prediction system that considers multiple past mammograms and views to assist radiologists in screening workflows.
Authors
Solveig Thrun, Zijun Sun, Suaiba A. Salahuddin, Kristoffer Wickstrøm, Elisabeth Wetzer, Stine Hansen, Robert Jenssen, Michael Kampffmeyer
Abstract
Accurate breast cancer risk prediction from screening mammography is essential for improved risk stratification and personalized screening. It can benefit from both temporal breast tissue changes across longitudinal examinations and complementary anatomical information from craniocaudal (CC) and mediolateral oblique (MLO) views. Leveraging longitudinal information requires identifying corresponding tissue regions across examinations, yet most approaches rely on implicit feature alignment without explicitly enforcing spatial consistency. Recent work has demonstrated the benefits of explicit temporal alignment; however, existing methods model each view independently, preventing them from exploiting complementary CC and MLO information. Furthermore, explicit approaches have been limited to a single prior examination. To fill these gaps, we propose (github.com/sot176/FlexLMV-Net), a breast-wise longitudinal multi-view framework that jointly models CC and MLO views across screening examinations while accommodating a variable number of prior examinations. FlexLMV-Net explicitly aligns longitudinal feature maps and integrates complementary views through cross-view temporal fusion and a dual-stream attention block. Evaluated on EMBED and CSAW-CC, FlexLMV-Net consistently outperforms existing approaches across breast density, cancer subtypes, and demographic subgroups, highlighting the benefits of explicit longitudinal alignment, multi-view modeling, and flexible use of available screening history. We further introduce (github.com/sot176/BCRBench), an open-source benchmark that unifies state-of-the-art single- and multi-timepoint breast cancer risk prediction models under standardized preprocessing, training, inference, and evaluation protocols, enabling fair and reproducible comparison of existing methods.