用改进的Mamba结构提升医学图像分割精度
MM-UNet: Meta Mamba UNet for Medical Image Segmentation
- 设计融合Mamba的双分支UNet架构，缓解空间结构断裂问题
- 在AMOS2022上达91.0% Dice，比nnUNet高3.2%
- 适合需要高精度分割的医学影像研究者
状态空间模型（SSMs）在长序列建模中表现优异，尤其在自然语言处理领域。然而，其直接应用于医学图像分割面临挑战：原为一维序列设计的SSMs难以处理医学图像中的三维空间结构，因扁平化引入不连续性；同时对高方差数据拟合能力弱，而医学图像正普遍存在此特性。本文分析了SSMs在医学图像分割中的内在局限，提出统一的U型编码器-解码器架构——Meta Mamba UNet（MM-UNet），旨在发挥SSMs优势的同时克服其缺陷。该架构通过在残差连接中嵌入混合模块整合SSMs，降低数据方差并提升性能；进一步提出新型双向扫描策略，减轻图像处理时的不连续性。在AMOS2022与Synapse数据集上的大量实验表明，MM-UNet优于现有先进方法，在AMOS2022上取得91.0%的Dice分数，较nnUNet提升3.2%；在Synapse数据集上达87.1%。结果验证了通过架构优化集成SSMs在医学图像分割中的有效性。
原文摘要 · Abstract (English)
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.
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。