SkinMamba用Mamba+CNN架构实现精准皮肤病变分割，兼顾长程依赖与边界清晰度。
SkinMamba: A Precision Skin Lesion Segmentation Architecture with Cross-Scale Global State Modeling and Frequency Boundary Guidance
- 融合Mamba与CNN，线性复杂度下实现全局建模与局部特征提取。
- 在ISIC2017和ISIC2018数据集上达到先进性能，边界分割更精确。
- 适合医学图像分割任务，尤其对大小不一、边界模糊的病变有效。
皮肤病变分割是早期皮肤癌识别的关键方法。近年来，卷积神经网络（CNN）和基于Transformer的方法被广泛应用。尽管结合两者能有效融合全局与局部关系，但仍受限于Transformer的二次复杂度。为此，我们提出一种基于Mamba与CNN的混合架构——SkinMamba，其保持线性复杂度的同时具备强大的长距离依赖建模与局部特征提取能力。具体而言，我们引入尺度残差状态空间块（SRSSB），在宏观层面捕捉全局上下文关系与跨尺度信息交互，实现专家间全局状态通信，有效应对病变尺寸差异大及目标区域不明显的问题。此外，为缓解模型下采样过程中的边界模糊与信息丢失，我们设计了频率边界引导模块（FBGM），提供充分的边界先验以指导精确边界分割，并利用保留信息辅助解码器解码。最后，在两个公开皮肤病变分割数据集（ISIC2017和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竞争力。代码已开源：https://github.com/zs1314/SkinMamba。
原文摘要 · Abstract (English)
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.
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。