用轻量高效模型提升MRI图像分辨率，保留关键解剖细节。
Efficient Vision Mamba for MRI Super-Resolution via Hybrid Selective Scanning
- 结合多头选择性状态空间与轻量通道混合，实现长程依赖建模。
- 7T脑部数据SSIM达0.951，参数仅0.9M，计算量降低97.5%。
- 适合临床部署，兼顾精度与效率，尤其适用于资源受限场景。
高分辨率MRI对诊断至关重要，但采集时间长限制了临床应用。超分辨率（SR）可在扫描后提升图像分辨率，但现有深度学习方法存在保真度与效率的权衡。本文提出一种新型深度学习框架，结合多头选择性状态空间模型（MHSSM）与轻量通道MLP，采用2D块提取与混合扫描策略捕捉长程依赖。每个MambaFormer模块融合MHSSM、深度可分离卷积与门控通道混合。在7T脑部T1 MP2RAGE（n=142）和1.5T前列腺T2w MRI（n=334）数据集上评估，对比了双三次插值、GAN（CycleGAN、Pix2pix、SPSR）、Transformer（SwinIR）、Mamba（MambaIR）及扩散模型（I2SB、Res-SRDiff）。结果表明，本模型性能优越且极高效：7T脑部数据中SSIM=0.951±0.021，PSNR=26.90±1.41 dB，LPIPS=0.076±0.022，GMSD=0.083±0.017，显著优于所有基线（p<0.001）；前列腺数据中SSIM=0.770±0.049，PSNR=27.15±2.19 dB，LPIPS=0.190±0.095，GMSD=0.087±0.013。模型仅使用0.9M参数和57 GFLOPs，相比Res-SRDiff参数减少99.8%，计算量降低97.5%，同时在准确性和效率上超越SwinIR与MambaIR。结论表明，该框架提供了一种高效精准的MRI超分辨率解决方案，能有效增强跨数据集的解剖细节，具备良好的临床转化潜力。
原文摘要 · Abstract (English)
Background: High-resolution MRI is critical for diagnosis, but long acquisition times limit clinical use. Super-resolution (SR) can enhance resolution post-scan, yet existing deep learning methods face fidelity-efficiency trade-offs. Purpose: To develop a computationally efficient and accurate deep learning framework for MRI SR that preserves anatomical detail for clinical integration. Materials and Methods: We propose a novel SR framework combining multi-head selective state-space models (MHSSM) with a lightweight channel MLP. The model uses 2D patch extraction with hybrid scanning to capture long-range dependencies. Each MambaFormer block integrates MHSSM, depthwise convolutions, and gated channel mixing. Evaluation used 7T brain T1 MP2RAGE maps (n=142) and 1.5T prostate T2w MRI (n=334). Comparisons included Bicubic interpolation, GANs (CycleGAN, Pix2pix, SPSR), transformers (SwinIR), Mamba (MambaIR), and diffusion models (I2SB, Res-SRDiff). Results: Our model achieved superior performance with exceptional efficiency. For 7T brain data: SSIM=0.951+-0.021, PSNR=26.90+-1.41 dB, LPIPS=0.076+-0.022, GMSD=0.083+-0.017, significantly outperforming all baselines (p<0.001). For prostate data: SSIM=0.770+-0.049, PSNR=27.15+-2.19 dB, LPIPS=0.190+-0.095, GMSD=0.087+-0.013. The framework used only 0.9M parameters and 57 GFLOPs, reducing parameters by 99.8% and computation by 97.5% versus Res-SRDiff, while outperforming SwinIR and MambaIR in accuracy and efficiency. Conclusion: The proposed framework provides an efficient, accurate MRI SR solution, delivering enhanced anatomical detail across datasets. Its low computational demand and state-of-the-art performance show strong potential for clinical translation.
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。