MM-UNet：面向医学图像分割的Meta Mamba UNet
MM-UNet: Meta Mamba UNet for Medical Image Segmentation
AI总结：
针对状态空间模型（SSMs）直接应用于医学图像分割的局限，提出U形编解码架构MM-UNet，通过残差集成SSM的混合模块与双向扫描策略优化性能，在两个基准数据集上取得优于现有方法的结果。
摘要：
状态空间模型（SSMs）近期在长序列建模中展现出优异性能，尤其在自然语言处理领域。然而将其直接应用于医学图像分割存在诸多挑战：SSMs原本为一维序列设计，因扁平化带来的不连续性，难以处理医学图像中的三维空间结构；此外，SSMs难以拟合医学成像中常见的高方差数据。\n 本文分析了SSMs在医学图像分割中的固有局限，提出统一的U形编解码架构Meta Mamba UNet（MM-UNet），旨在发挥SSMs优势的同时弥补其不足。MM-UNet引入混合模块，将SSMs集成于残差连接中，降低方差并提升性能。此外，我们提出一种新颖的双向扫描顺序策略，以缓解处理医学图像时的不连续性问题。\n 在AMOS2022和Synapse数据集上的大量实验证明，MM-UNet优于现有最优方法。其在AMOS2022上取得91.0%的Dice分数，较nnUNet高出3.2%；在Synapse上取得87.1%的Dice分数。这些结果证实了通过架构设计优化将SSMs集成于医学图像分割的有效性。
英文摘要：
State Space Models (SSMs) have recently demonstrated outstanding performance in long-sequence modeling, particularly in natural language processing. However, their direct application to medical image segmentation poses several challenges. SSMs, originally designed for 1D sequences, struggle with 3D spatial structures in medical images due to discontinuities introduced by flattening. Additionally, SSMs have difficulty fitting high-variance data, which is common in medical imaging. In this paper, we analyze the intrinsic limitations of SSMs in medical image segmentation and propose a unified U-shaped encoder-decoder architecture, Meta Mamba UNet (MM-UNet), designed to leverage the advantages of SSMs while mitigating their drawbacks. MM-UNet incorporates hybrid modules that integrate SSMs within residual connections, reducing variance and improving performance. Furthermore, we introduce a novel bi-directional scan order strategy to alleviate discontinuities when processing medical images. Extensive experiments on the AMOS2022 and Synapse datasets demonstrate the superiority of MM-UNet over state-of-the-art methods. MM-UNet achieves a Dice score of 91.0% on AMOS2022, surpassing nnUNet by 3.2%, and a Dice score of 87.1% on Synapse. These results confirm the effectiveness of integrating SSMs in medical image segmentation through architectural design optimizations.
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。
