VM-UNET-V2：重新思考用于医学图像分割的Vision Mamba UNet
VM-UNET-V2 Rethinking Vision Mamba UNet for Medical Image Segmentation
AI总结：
针对医学图像分割中CNN和Transformer的局限，提出VM-UNetV2，引入VSS和SDI模块，在多个公共数据集上取得竞争性能。
摘要：
在医学图像分割领域，基于CNN和Transformer的模型已被深入研究。然而，CNN对长距离依赖的建模能力有限，难以充分利用图像中的语义信息。另一方面，二次方计算复杂度对Transformer构成了挑战。近年来，状态空间模型（SSM），如Mamba，被认为是一种有前景的方法。它们不仅在建模长距离交互方面表现出优越性能，而且保持了线性计算复杂度。受Mamba架构启发，我们提出了Vision Mamba-UNetV2，引入了视觉状态空间（VSS）模块来捕获广泛的上下文信息，并引入语义与细节注入（SDI）模块以增强低层和高层特征的融合。我们在ISIC17、ISIC18、CVC-300、CVC-ClinicDB、Kvasir、CVC-ColonDB和ETIS-LaribPolypDB公共数据集上进行了全面实验。结果表明，VM-UNetV2在医学图像分割任务中表现出具有竞争力的性能。我们的代码可在https://github.com/nobodyplayer1/VM-UNetV2获取。
英文摘要：
In the field of medical image segmentation, models based on both CNN and Transformer have been thoroughly investigated. However, CNNs have limited modeling capabilities for long-range dependencies, making it challenging to exploit the semantic information within images fully. On the other hand, the quadratic computational complexity poses a challenge for Transformers. Recently, State Space Models (SSMs), such as Mamba, have been recognized as a promising method. They not only demonstrate superior performance in modeling long-range interactions, but also preserve a linear computational complexity. Inspired by the Mamba architecture, We proposed Vison Mamba-UNetV2, the Visual State Space (VSS) Block is introduced to capture extensive contextual information, the Semantics and Detail Infusion (SDI) is introduced to augment the infusion of low-level and high-level features. We conduct comprehensive experiments on the ISIC17, ISIC18, CVC-300, CVC-ClinicDB, Kvasir, CVC-ColonDB and ETIS-LaribPolypDB public datasets. The results indicate that VM-UNetV2 exhibits competitive performance in medical image segmentation tasks. Our code is available at https://github.com/nobodyplayer1/VM-UNetV2.
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。
