A diffusion model based on multi-scale spatial Mamba for medical image segmentation

Medical image segmentation plays a key role in disease diagnosis, treatment planning, and monitoring disease progression. Recently, denoising diffusion models have shown significant promise in generating accurate pixel-level semantic representations. In this study, we introduce a diffusion model based on multi-scale spatial mamba (MSM-Diff) designed for precise medical image segmentation. MSM-Diff integrates the strengths of diffusion models, Mamba architecture, and convolutional neural networks to efficiently capture both global and local contextual information from complex volumetric data. The core of MSM-Diff is the Mamba-based U-shaped feature encoder (MUFE), which combines the three-dimensional multi-scale spatial Mamba model (MS-Mamba) with extracted features for enhanced multi-scale and global feature extraction. By using the mamba architecture, the model maintains linear computational complexity. Additionally, MSM-Diff incorporates a multi-scale gated spatial convolution (MS-GSC) module within MUFE to further refine spatial feature representations. Extensive evaluations of three public datasets demonstrate that MSM-Diff consistently outperforms current methods, achieving state-of-the-art performance in DSC and HD95. This model provides a robust solution for medical image segmentation by effectively capturing global context and accurately delineating boundaries, thereby improving diagnostic and treatment planning outcomes for radiologists and clinicians.