# STA-Risk: A Deep Dive of Spatio-Temporal Asymmetries for Breast Cancer Risk Prediction

arXiv: https://arxiv.org/abs/2505.21699 · HTML: https://mlsanity.com/paper/2505.21699/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 20 references that are in the map.
- First posted on arXiv 27 May 2025.

## Builds on (most cited first, 4 of 4)

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [COVID-19 Prognosis via Self-Supervised Representation Learning and Multi-Image Prediction](https://mlsanity.com/paper/2101.04909/) (2021)
- [Enhancing Breast Cancer Risk Prediction by Incorporating Prior Images](https://mlsanity.com/paper/2303.15699/) (2023)
- [RADIFUSION: A multi-radiomics deep learning based breast cancer risk prediction model using sequential mammographic images with image attention and bilateral asymmetry refinement](https://mlsanity.com/paper/2304.00257/) (2023)

## Built on by (most cited first, 1 of 1)

- [MamaDino: A Hybrid Vision Model for Breast Cancer 3-Year Risk Prediction](https://mlsanity.com/paper/2602.13930/) (2026)

## Abstract (arXiv)

Predicting the risk of developing breast cancer is an important clinical tool to guide early intervention and tailoring personalized screening strategies. Early risk models have limited performance and recently machine learning-based analysis of mammogram images showed encouraging risk prediction effects. These models however are limited to the use of a single exam or tend to overlook nuanced breast tissue evolvement in spatial and temporal details of longitudinal imaging exams that are indicative of breast cancer risk. In this paper, we propose STA-Risk (Spatial and Temporal Asymmetry-based Risk Prediction), a novel Transformer-based model that captures fine-grained mammographic imaging evolution simultaneously from bilateral and longitudinal asymmetries for breast cancer risk prediction. STA-Risk is innovative by the side encoding and temporal encoding to learn spatial-temporal asymmetries, regulated by a customized asymmetry loss. We performed extensive experiments with two independent mammogram datasets and achieved superior performance than four representative SOTA models for 1- to 5-year future risk prediction. Source codes will be released upon publishing of the paper.