Despite the progress made in Mamba-based medical image segmentation models, current methods utilizing unidirectional or multi-directional feature scanning mechanisms fail to well model dependencies between neighboring positions in the image, hindering the effective modeling of local features. However, local features are crucial for medical image segmentation as they provide vital information about lesions and tissue structures. To address this limitation, we propose a simple yet effective method named SliceMamba, a locally sensitive pure Mamba medical image segmentation model. The proposed SliceMamba includes an efffcient Bidirectional Slice Scan module (BSS), which performs bidirectional feature segmentation while employing varied scanning mechanisms for distinct features. This ensures that spatially adjacent features maintain proximity in the scanning sequence, thereby enhancing segmentation performance. Extensive experiments on skin lesion and polyp segmentation datasets validate the effectiveness of our method.

翻译：尽管基于Mamba的医学图像分割模型已取得进展，但当前采用单向或多向特征扫描机制的方法未能充分建模图像中相邻位置间的依赖关系，这阻碍了对局部特征的有效建模。然而，局部特征对于医学图像分割至关重要，因为它们能提供关于病灶和组织结构的关键信息。为应对这一局限，我们提出了一种简单而有效的方法，命名为SliceMamba，这是一种局部敏感的纯Mamba医学图像分割模型。所提出的SliceMamba包含一个高效的双向切片扫描模块（BSS），该模块在执行双向特征分割的同时，针对不同特征采用差异化的扫描机制。这确保了空间上相邻的特征在扫描序列中保持邻近性，从而提升了分割性能。在皮肤病灶和息肉分割数据集上进行的大量实验验证了我们方法的有效性。