Spatial-Temporal Mamba Network for Accurate Breast Tumor Segmentation in DCE-MRI

Motivation: Breast tumor segmentation with DCE-MRI facilitates downstream characterization, diagnosis, and prognostication. However, current methods often overlook the temporal hemodynamic information inherent in DCE-MRI, limiting segmentation accuracy. This study addresses this gap by integrating spatial and temporal data to enhance tumor segmentation. Goal(s): To develop a model that captures both spatial and temporal features in DCE-MRI to enhance accuracy. Approach: We propose a Spatial-Temporal Mamba Network, integrating 3D spatial structures and multi-phase hemodynamic features using a 4D encoder and specialized modules for both spatial and temporal feature extraction. Results: Our model achieved superior performance in DSC and HD metrics compared to state-of-the-art methods. Impact: Our results show that the proposed model can significantly improve tumor segmentation accuracy in DCE-MRI by utilizing both spatial and temporal features. This advancement holds promise for more accurate breast cancer diagnosis and better-informed treatment planning.