轻量级网络高效分割乳腺癌病灶，精度与速度兼备
HCMA-UNet: A Hybrid CNN-Mamba UNet with Axial Self-Attention for Efficient Breast Cancer Segmentation
- 融合CNN与Mamba结构，用轴向自注意力实现三向特征提取
- 仅287万参数、126.44 GFLOPs，分割精度达当前最优
- 新损失函数跨架构泛化强，适合临床辅助诊断应用
动态增强MRI中乳腺癌病灶分割因肿瘤形态异质性和边界模糊而具挑战性。本文提出新型混合分割网络HCMA-UNet，包含轻量级CNN主干和多视角轴向自注意力Mamba（MISM）模块。MISM结合视觉状态空间块（VSSB）与轴向自注意力（ASA）机制，通过非对称分通道（ASC）策略显著减少参数量，实现高效的三向特征提取。所提轻量模型仅含287万参数、126.44 GFLOPs，性能优异。此外，设计了特征引导的区域感知损失（FRLoss），提升分割精度。在1个私有及2个公开DCE-MRI数据集上实验表明，本方法在保持计算效率的同时达到最先进水平。FRLoss亦展现良好跨架构泛化能力。源代码已开源：https://github.com/Haoxuanli-Thu/HCMA-UNet。
原文摘要 · Abstract (English)
Breast cancer lesion segmentation in DCE-MRI remains challenging due to heterogeneous tumor morphology and indistinct boundaries. To address these challenges, this study proposes a novel hybrid segmentation network, HCMA-UNet, for lesion segmentation of breast cancer. Our network consists of a lightweight CNN backbone and a Multi-view Axial Self-Attention Mamba (MISM) module. The MISM module integrates Visual State Space Block (VSSB) and Axial Self-Attention (ASA) mechanism, effectively reducing parameters through Asymmetric Split Channel (ASC) strategy to achieve efficient tri-directional feature extraction. Our lightweight model achieves superior performance with 2.87M parameters and 126.44 GFLOPs. A Feature-guided Region-aware loss function (FRLoss) is proposed to enhance segmentation accuracy. Extensive experiments on one private and two public DCE-MRI breast cancer datasets demonstrate that our approach achieves state-of-the-art performance while maintaining computational efficiency. FRLoss also exhibits good cross-architecture generalization capabilities. The source code is available at https://github.com/Haoxuanli-Thu/HCMA-UNet.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。