用新型混合结构提升皮肤病变分割精度，兼顾效率与细节。
ASP-VMUNet: Atrous Shifted Parallel Vision Mamba U-Net for Skin Lesion Segmentation
- 引入空洞扫描与并行视觉马尔可夫层，扩大感受野并增强特征提取。
- 在四个数据集上达到最佳性能，平均DSC超90%，显著优于传统CNN和Transformer。
- 适合医学图像分割研究者，尤其关注高效高精度模型设计的团队。
皮肤病变分割是计算机视觉中的关键挑战，准确分离病灶与健康皮肤对诊断至关重要。传统卷积神经网络（CNN）受限于感受野狭窄，而变换器（Transformers）则面临巨大计算负担。本文提出一种新型皮肤病变分割框架——空洞移位并行视觉马尔可夫U-Net（ASP-VMUNet），融合高效可扩展的Mamba架构，克服传统CNN与计算密集型Transformer的局限。该框架引入空洞扫描技术，减少背景干扰并扩大感受野，增强Mamba的扫描能力；同时加入并行视觉马尔可夫（PVM）层与移位循环操作，优化特征分割并促进段间信息交互。此外，附加一个含选择性核（SK）模块的CNN分支，融合局部与全局上下文信息以进一步精炼分割结果。在ISIC16/17/18与PH2四个基准数据集上的测试表明，ASP-VMUNet表现出色，经全面消融实验验证。该方法不仅推动了医学图像分割进展，也凸显了混合架构在医学影像中的优势。代码已开源：https://github.com/BaoBao0926/ASP-VMUNet/tree/main。
原文摘要 · Abstract (English)
Skin lesion segmentation is a critical challenge in computer vision, and it is essential to separate pathological features from healthy skin for diagnostics accurately. Traditional Convolutional Neural Networks (CNNs) are limited by narrow receptive fields, and Transformers face significant computational burdens. This paper presents a novel skin lesion segmentation framework, the Atrous Shifted Parallel Vision Mamba UNet (ASP-VMUNet), which integrates the efficient and scalable Mamba architecture to overcome limitations in traditional CNNs and computationally demanding Transformers. The framework introduces an atrous scan technique that minimizes background interference and expands the receptive field, enhancing Mamba's scanning capabilities. Additionally, the inclusion of a Parallel Vision Mamba (PVM) layer and a shift round operation optimizes feature segmentation and fosters rich inter-segment information exchange. A supplementary CNN branch with a Selective-Kernel (SK) Block further refines the segmentation by blending local and global contextual information. Tested on four benchmark datasets (ISIC16/17/18 and PH2), ASP-VMUNet demonstrates superior performance in skin lesion segmentation, validated by comprehensive ablation studies. This approach not only advances medical image segmentation but also highlights the benefits of hybrid architectures in medical imaging technology. Our code is available at https://github.com/BaoBao0926/ASP-VMUNet/tree/main.
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。