Biomedical Imaging Research Institute, Cedars-Sinai Medical Center, Los Angeles, California, USA.
Department of Bioengineering, University of California, Los Angeles, California, USA.
Magn Reson Med. 2023 Dec;90(6):2362-2374. doi: 10.1002/mrm.29814. Epub 2023 Aug 14.
Deep learning superresolution (SR) is a promising approach to reduce MRI scan time without requiring custom sequences or iterative reconstruction. Previous deep learning SR approaches have generated low-resolution training images by simple k-space truncation, but this does not properly model in-plane turbo spin echo (TSE) MRI resolution degradation, which has variable T relaxation effects in different k-space regions. To fill this gap, we developed a T -deblurred deep learning SR method for the SR of 3D-TSE images.
A SR generative adversarial network was trained using physically realistic resolution degradation (asymmetric T weighting of raw high-resolution k-space data). For comparison, we trained the same network structure on previous degradation models without TSE physics modeling. We tested all models for both retrospective and prospective SR with 3 × 3 acceleration factor (in the two phase-encoding directions) of genetically engineered mouse embryo model TSE-MR images.
The proposed method can produce high-quality 3 × 3 SR images for a typical 500-slice volume with 6-7 mouse embryos. Because 3 × 3 SR was performed, the image acquisition time can be reduced from 15 h to 1.7 h. Compared to previous SR methods without TSE modeling, the proposed method achieved the best quantitative imaging metrics for both retrospective and prospective evaluations and achieved the best imaging-quality expert scores for prospective evaluation.
The proposed T -deblurring method improved accuracy and image quality of deep learning-based SR of TSE MRI. This method has the potential to accelerate TSE image acquisition by a factor of up to 9.
深度学习超分辨率（SR）是一种很有前途的方法，可以在不要求定制序列或迭代重建的情况下减少 MRI 扫描时间。以前的深度学习 SR 方法通过简单的 k 空间截断生成低分辨率训练图像，但这并没有正确模拟平面内涡轮自旋回波（TSE）MRI 分辨率下降，因为在不同的 k 空间区域有可变的 T 弛豫效应。为了填补这一空白，我们开发了一种用于 3D-TSE 图像 SR 的 T 去模糊深度学习 SR 方法。
使用物理上逼真的分辨率退化（对原始高分辨率 k 空间数据进行不对称 T 加权）来训练 SR 生成对抗网络。为了进行比较，我们在没有 TSE 物理建模的情况下，在以前的退化模型上训练了相同的网络结构。我们对所有模型进行了测试，包括对基因工程鼠胚胎模型 TSE-MR 图像进行的回顾性和前瞻性 SR，加速因子为 3×3（在两个相位编码方向上）。
该方法可以为典型的 500 层容积生成高质量的 3×3 SR 图像，其中包含 6-7 只老鼠胚胎。由于进行了 3×3 SR，图像采集时间可以从 15 小时减少到 1.7 小时。与以前没有 TSE 建模的 SR 方法相比，该方法在回顾性和前瞻性评估中都获得了最佳的定量成像指标，并且在前瞻性评估中获得了最佳的成像质量专家评分。
所提出的 T 去模糊方法提高了基于深度学习的 TSE MRI SR 的准确性和图像质量。该方法有望将 TSE 图像采集速度提高 9 倍。
