发表机构
The University of Chicago; University of North Carolina at Chapel Hill; Emory University; Georgia Institute of Technology; Mayo Clinic（芝加哥大学; 北卡罗来纳大学教堂山分校; 埃默里大学; 佐治亚理工学院; 梅奥诊所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对MRI扫描时间与分辨率的权衡问题，提出仅需十步采样的超分辨率扩散桥模型SR-DBM，在7T脑和前列腺MRI数据集上的量化指标与视觉效果均优于九种对比方法。
AI 中文摘要
目的：MRI具备优异的软组织对比度，但过长的采集时间会引发患者不适并导致运动伪影，迫使在空间分辨率与扫描时间之间进行权衡。基于扩散的超分辨率（SR）可从低分辨率（LR）输入重建高分辨率（HR）图像，但通常需要大量采样步骤，且其从高斯先验初始化的方式并不适配图像修复任务。我们开发了一种高效的扩散框架，可直接从LR数据重建HR MRI。方法：我们提出超分辨率扩散桥模型（SR-DBM），将SR问题建模为LR与HR图像分布之间的随机传输过程。通过对均值回复随机微分方程进行Doob h变换，SR-DBM将该过程固定在配对的HR与LR图像端点，使重建从实测解剖结构而非高斯噪声初始化。HR图像通过确定性反向轨迹恢复，其中网络仅在十个采样步骤中的每一步预测清晰图像。我们在超高场7T脑T1 MP2RAGE图谱和盆腔T2加权前列腺图像上，使用PSNR、SSIM、GMSD和LPIPS四个指标，将SR-DBM与九种对比方法进行评估。主要结果：SR-DBM在两个数据集上均取得最高的PSNR和SSIM，以及最低的GMSD（脑数据集：27.66±1.52 dB、0.96±0.02、7.96±1.86；前列腺数据集：27.87±2.29 dB、0.80±0.05、8.38±1.44），相较于所有对比方法均具有统计学显著提升（双侧Wilcoxon符号秩检验结合Holm校正，p<0.05）。最强基线方法SR-EMamba排名第二。定性来看，SR-DBM产生的残差误差最小，且能最佳保留精细结构与病灶。
英文摘要
Objective. MRI provides excellent soft-tissue contrast, but long acquisition times can cause patient discomfort and lead to motion artifacts, forcing a trade-off between spatial resolution and scan time. Diffusion-based super-resolution (SR) reconstructs high-resolution (HR) images from low-resolution (LR) inputs, but typically needs many sampling steps and initializes from a Gaussian prior ill-suited to image restoration. We developed an efficient diffusion framework that reconstructs HR MRI directly from LR data. Approach. We propose super-resolution diffusion bridge model (SR-DBM), a super-resolution diffusion bridge model that casts SR as a stochastic transport between the LR and HR image distributions. Through a Doob's h-transform of a mean-reverting stochastic differential equation, SR-DBM pins the process to the paired HR and LR images at its endpoints, initializing reconstruction from the measured anatomy rather than from Gaussian noise. The HR image is recovered by a deterministic reverse trajectory in which a network predicts the clean image at each of only ten sampling steps. We evaluated SR-DBM on ultra-high-field 7T brain T1 MP2RAGE maps and pelvic T2-weighted prostate images against nine comparison methods using PSNR, SSIM, GMSD, and LPIPS. Main results. SR-DBM attained the highest PSNR and SSIM and the lowest GMSD on both datasets (brain: 27.66+-1.52 dB, 0.96+-0.02, 7.96+-1.86$; prostate: 27.87+-2.29 dB, 0.80+-0.05, 8.38+- 1.44), with statistically significant gains over every comparison method (two-sided Wilcoxon signed-rank test with Holm correction, p<0.05). The strongest baseline, SR-EMamba, ranked second. Qualitatively, SR-DBM produced the smallest residual errors and best preserved fine structures and lesions.
