Boundary-aware geometric Mamba network for breast tumor segmentation in 3D MRI
- 1College of Computer Science and Technology, Changchun University , , ,
Abstract
Introduction: Accurate breast tumor segmentation in Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) is important for reliable diagnosis and treatment planning. However, complex tumor morphology, diverse spatial structures, and indistinct boundaries remain challenging for existing segmentation methods. Convolutional neural network-based methods have limited ability to model long-range dependencies, while Transformer-based methods often introduce substantial computational overhead. Although Mamba-based approaches provide an efficient alternative, conventional scanning strategies may suffer from directional bias and insufficiently capture three-dimensional structural variations.
Methods: We propose a Boundary-Aware Geometric Mamba Network (BAGMNet) for three-dimensional breast tumor segmentation. BAGMNet establishes a structural representation learning framework that combines geometric modeling, multi-directional state-space propagation, and boundary-aware feature refinement. The Geometric Mamba Encoder constructs complementary spatial representations through multiple geometric transformations, while the Multi-directional Selective State Space module enhances three-dimensional dependency modeling and alleviates the directional bias of conventional Mamba scanning. The Gated State-space Fusion and Adaptive Skip Recalibration modules further integrate local structural details with global contextual information and enhance boundary-related representations during feature propagation.
Results: Extensive experiments were conducted on the ISPY1 and Yunnan breast MRI datasets. BAGMNet achieved Dice scores of 70.34% and 79.14%, with average surface distances of 9.79 mm and 8.96 mm on the ISPY1 and Yunnan datasets, respectively. Compared with representative convolutional neural network-, Transformer-, and Mamba-based methods, BAGMNet achieved competitive performance in both regional segmentation accuracy and boundary localization.
Related
- UGB-SegNet: Uncertainty-Guided Multi-Scale Attention and Boundary-Aware Learning for Breast Ultrasound Lesion Segmentation
- Evaluation of boundary-aware UNet++ for low-grade glioma segmentation
- Boundary-aware multi-scale residual learning with hybrid radiomic–deep fusion for lung tumor segmentation and classification
- AMF-U-Net: an adaptive multimodal fusion residual attention 3D U-Net for boundary-aware brain tumour segmentation
- AdaSwitch3D: Reliability-Aware Human-in-the-Loop Artificial Intelligence for Breast Tumor Segmentation in Dynamic Contrast-Enhanced MRI Across Unseen Centers
BibTeX
@article{kuang2026boundaryaware,
title = {{Boundary-aware geometric Mamba network for breast tumor segmentation in 3D MRI}},
author = {Zhejun Kuang and Yuxuan Zhu and Dawen Sun and Jian Zhao},
journal = {Frontiers in oncology},
year = {2026},
month = oct,
doi = {10.3389/fonc.2026.1972153},
url = {https://europepmc.org/article/PMC/PMC13690640},
note = {CC BY},
}
RIS
TY - JOUR
TI - Boundary-aware geometric Mamba network for breast tumor segmentation in 3D MRI
AU - Zhejun Kuang
AU - Yuxuan Zhu
AU - Dawen Sun
AU - Jian Zhao
PY - 2026
DA - 2026/10/09
JO - Frontiers in oncology
DO - 10.3389/fonc.2026.1972153
UR - https://europepmc.org/article/PMC/PMC13690640
AB - Introduction: Accurate breast tumor segmentation in Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) is important for reliable diagnosis and treatment planning. However, complex tumor morphology, diverse spatial structures, and indistinct boundaries remain challenging for existing segmentation methods. Convolutional neural network-based methods have limited ability to model long-range dependencies, while Transformer-based methods often introduce substantial computational overhead. Although Mamba-based approaches provide an efficient alternative, conventional scanning strategies may suffer from directional bias and insufficiently capture three-dimensional structural variations. Methods: We propose a Boundary-Aware Geometric Mamba Network (BAGMNet) for three-dimensional breast tumor segmentation. BAGMNet establishes a structural representation learning framework that combines geometric modeling, multi-directional state-space propagation, and boundary-aware feature refinement. The Geometric Mamba Encoder constructs complementary spatial representations through multiple geometric transformations, while the Multi-directional Selective State Space module enhances three-dimensional dependency modeling and alleviates the directional bias of conventional Mamba scanning. The Gated State-space Fusion and Adaptive Skip Recalibration modules further integrate local structural details with global contextual information and enhance boundary-related representations during feature propagation. Results: Extensive experiments were conducted on the ISPY1 and Yunnan breast MRI datasets. BAGMNet achieved Dice scores of 70.34% and 79.14%, with average surface distances of 9.79 mm and 8.96 mm on the ISPY1 and Yunnan datasets, respectively. Compared with representative convolutional neural network-, Transformer-, and Mamba-based methods, BAGMNet achieved competitive performance in both regional segmentation accuracy and boundary localization.
SN - 2234-943X
ER -