标题： HCMA-UNet：一种具有轴向自注意力的混合CNN-Mamba UNet用于高效乳腺癌分割 显示英文标题

标题： HCMA-UNet: A Hybrid CNN-Mamba UNet with Axial Self-Attention for Efficient Breast Cancer Segmentation

摘要： 由于乳腺癌病灶在动态对比增强磁共振成像（DCE-MRI）中的异质性形态和边界模糊，其分割仍然具有挑战性。 为了解决这些难题，本研究提出了一种新颖的混合分割网络——HCMA-UNet，用于乳腺癌病灶分割。 我们的网络由一个轻量级的卷积神经网络（CNN）主干和一个多视图轴向自注意力模块（MISM）组成。 MISM 模块集成了视觉状态空间块（VSSB）和轴向自注意力（ASA）机制，并通过非对称分通道（ASC）策略有效减少参数，实现高效的三向特征提取。 我们的轻量级模型仅包含 287 万参数和 126.44 GFLOPs，却表现出色。 提出了一种基于特征引导的区域感知损失函数（FRLoss），以提高分割准确性。 在私有数据集和两个公共 DCE-MRI 乳腺癌数据集上的大量实验表明，我们的方法在保持计算效率的同时达到了最先进的性能。 FRLoss 还展示了良好的跨架构泛化能力。 源代码可在 https://github.com/Haoxuanli-Thu/HCMA-UNet 获取。 显示英文摘要

摘要： 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.