IVCVJun 20, 2025

VMRA-MaR: An Asymmetry-Aware Temporal Framework for Longitudinal Breast Cancer Risk Prediction

arXiv:2506.17412v12 citationsh-index: 2Has CodeMICCAI
Originality Incremental advance
AI Analysis

This work addresses the problem of improving early breast cancer detection through personalized screening strategies, representing an incremental advancement in longitudinal imaging analysis.

The paper tackles breast cancer risk prediction by developing a temporal framework that captures evolving trends in breast tissue using Vision Mamba RNN with state-space models and asymmetry modules, achieving superior performance in predicting cancer onset, especially for high-density breast cases and at extended time points (years four and five).

Breast cancer remains a leading cause of mortality worldwide and is typically detected via screening programs where healthy people are invited in regular intervals. Automated risk prediction approaches have the potential to improve this process by facilitating dynamically screening of high-risk groups. While most models focus solely on the most recent screening, there is growing interest in exploiting temporal information to capture evolving trends in breast tissue, as inspired by clinical practice. Early methods typically relied on two time steps, and although recent efforts have extended this to multiple time steps using Transformer architectures, challenges remain in fully harnessing the rich temporal dynamics inherent in longitudinal imaging data. In this work, we propose to instead leverage Vision Mamba RNN (VMRNN) with a state-space model (SSM) and LSTM-like memory mechanisms to effectively capture nuanced trends in breast tissue evolution. To further enhance our approach, we incorporate an asymmetry module that utilizes a Spatial Asymmetry Detector (SAD) and Longitudinal Asymmetry Tracker (LAT) to identify clinically relevant bilateral differences. This integrated framework demonstrates notable improvements in predicting cancer onset, especially for the more challenging high-density breast cases and achieves superior performance at extended time points (years four and five), highlighting its potential to advance early breast cancer recognition and enable more personalized screening strategies. Our code is available at https://github.com/Mortal-Suen/VMRA-MaR.git.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes