Skin lesion segmentation is a crucial method for identifying early skin cancer. In recent years, both convolutional neural network (CNN) and Transformer-based methods have been widely applied. Moreover, combining CNN and Transformer effectively integrates global and local relationships, but remains limited by the quadratic complexity of Transformer. To address this, we propose a hybrid architecture based on Mamba and CNN, called SkinMamba. It maintains linear complexity while offering powerful long-range dependency modeling and local feature extraction capabilities. Specifically, we introduce the Scale Residual State Space Block (SRSSB), which captures global contextual relationships and cross-scale information exchange at a macro level, enabling expert communication in a global state. This effectively addresses challenges in skin lesion segmentation related to varying lesion sizes and inconspicuous target areas. Additionally, to mitigate boundary blurring and information loss during model downsampling, we introduce the Frequency Boundary Guided Module (FBGM), providing sufficient boundary priors to guide precise boundary segmentation, while also using the retained information to assist the decoder in the decoding process. Finally, we conducted comparative and ablation experiments on two public lesion segmentation datasets (ISIC2017 and ISIC2018), and the results demonstrate the strong competitiveness of SkinMamba in skin lesion segmentation tasks. The code is available at https://github.com/zs1314/SkinMamba.

翻译：皮肤病变分割是识别早期皮肤癌的关键方法。近年来，基于卷积神经网络（CNN）和Transformer的方法均得到广泛应用。此外，结合CNN与Transformer能有效整合全局与局部关系，但仍受限于Transformer的二次复杂度。为此，我们提出了一种基于Mamba与CNN的混合架构，称为SkinMamba。它在保持线性复杂度的同时，提供了强大的长程依赖建模与局部特征提取能力。具体而言，我们引入了尺度残差状态空间块（SRSSB），该模块在宏观层面捕获全局上下文关系与跨尺度信息交换，实现在全局状态中的专家级通信。这有效应对了皮肤病变分割中病变尺寸多变与目标区域不显著的挑战。此外，为缓解模型下采样过程中的边界模糊与信息损失，我们引入了频率边界引导模块（FBGM），该模块提供充足的边界先验以引导精确的边界分割，同时利用保留的信息辅助解码器进行解码过程。最后，我们在两个公开的病变分割数据集（ISIC2017与ISIC2018）上进行了对比与消融实验，结果表明SkinMamba在皮肤病变分割任务中具有强大的竞争力。代码发布于https://github.com/zs1314/SkinMamba。