BiSegMamba: 用于3D医学图像分割的高效双向三向Mamba
BiSegMamba: Efficient Bidirectional Tri-Oriented Mamba for 3D Medical Image Segmentation
AI总结：
提出BiSegMamba，一种基于双向三向Mamba的高效3D医学图像分割网络，通过渐进压缩主干、多尺度空间混合器、双向正交Mamba块和自适应方向融合，在降低计算成本的同时提升分割精度。
摘要：
精确的3D医学图像分割需要长程体积上下文和精细边界保持。基于CNN的方法全局依赖建模有限，而基于Transformer的模型对于密集3D输入通常计算成本高昂。最近的基于Mamba的方法提供了一种高效替代方案，但现有的体积设计仍依赖于重复的高分辨率扫描、仅前向的顺序建模和固定的方向求和，导致高成本、扫描顺序偏差和次优的方向聚合。我们提出BiSegMamba，一种用于3D医学图像分割的高效双向三向Mamba网络。BiSegMamba遵循紧凑到细节的设计，其中渐进压缩主干（PCS）能够进行高效的潜在空间推理，同时保留浅层高分辨率特征用于重建。多尺度空间混合器（MSSM）在早期阶段捕获局部解剖模式，而提出的双向三向正交Mamba（Bi-ToOM）块使用联合处理的前向和后向扫描序列，从多个正交视图建模长程依赖。自适应方向融合（ADF）学习跨扫描方向的输入相关通道权重，用方向感知融合替代固定求和。在收集的颈动脉CTA数据集和三个公共基准BraTS2023、ACDC和AMOS-CT上的实验表明，BiSegMamba在血管、心脏、脑肿瘤和腹部多器官分割任务中具有良好的泛化能力。与SegMamba-V2相比，BiSegMamba在BraTS2023上性能略有提升，在ACDC和颈动脉数据集上显著改进，同时计算成本降低高达77.9% FLOPs，展示了在通用3D医学图像分割中强大的精度-效率平衡。
英文摘要：
Accurate 3D medical image segmentation requires both fine spatial detail and long-range volumetric context. Although Mamba provides efficient long-sequence modeling, volumetric formulations remain sensitive to spatial serialization order, repeated multi-orientation processing, and fixed aggregation of orientation-specific representations. We propose BiSegMamba, an efficient bidirectional tri-oriented Mamba framework that follows a compact-to-detail and local-to-global processing strategy. A progressive compacting stem shifts semantic reasoning to compact representations while retaining shallow high-resolution features for reconstruction, and a multi-scale spatial mixer captures local anatomical patterns. For global context modeling, volumetric features are serialized along three anatomical orientations and their reversed directions, the resulting six sequences are processed jointly by a shared Mamba operator, and reconciled using learned channel-wise forward-backward weighting. The restored orientation-specific features are subsequently integrated through input-dependent directional fusion. Experiments on an in-house carotid dataset and ACDC, BraTS2023, and AMOS-CT achieve Dice scores of 96.3%, 91.63%, 92.57%, and 89.03%, respectively. Compared with SegMamba-V2 under standardized $128^3$ profiling, BiSegMamba reduces the parameter count by 65.9% (138.77M$\rightarrow$47.38M) and inference latency by 53.6% (129.08$\rightarrow$59.86 ms), while increasing throughput by 115.7% (7.75$\rightarrow$16.71 samples/s). These results demonstrate a favorable accuracy--efficiency trade-off among volumetric Mamba-based segmentation models.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
