Department of Radiology, Chinese PLA General Hospital, Beijing, China.
Key Laboratory of Magnetic Resonance in Biological Systems, State Key Laboratory of Magnetic Resonance and Atomic and Molecular Physics, National Center for Magnetic Resonance in Wuhan, Wuhan Institute of Physics and Mathematics, Innovation Academy for Precision Measurement Science and Technology, Chinese Academy of Sciences-Wuhan National Laboratory for Optoelectronics, Wuhan, China.
J Magn Reson Imaging. 2024 May;59(5):1620-1629. doi: 10.1002/jmri.28944. Epub 2023 Aug 9.
Ultra-high field 7T MRI can provide excellent tissue contrast and anatomical details, but is often cost prohibitive, and is not widely accessible in clinical practice.
To generate synthetic 7T images from widely acquired 3T images with deep learning and to evaluate the feasibility of this approach for brain imaging.
Prospective.
33 healthy volunteers and 89 patients with brain diseases, divided into training, and evaluation datasets in the ratio 4:1.
T1-weighted nonenhanced or contrast-enhanced magnetization-prepared rapid acquisition gradient-echo sequence at both 3T and 7T.
A generative adversarial network (SynGAN) was developed to produce synthetic 7T images from 3T images as input. SynGAN training and evaluation were performed separately for nonenhanced and contrast-enhanced paired acquisitions. Qualitative image quality of acquired 3T and 7T images and of synthesized 7T images was evaluated by three radiologists in terms of overall image quality, artifacts, sharpness, contrast, and visualization of vessel using 5-point Likert scales.
Wilcoxon signed rank tests to compare synthetic 7T images with acquired 7T and 3T images and intraclass correlation coefficients to evaluate interobserver variability. P < 0.05 was considered significant.
Of the 122 paired 3T and 7T MRI scans, 66 were acquired without contrast agent and 56 with contrast agent. The average time to generate synthetic images was ~11.4 msec per slice (2.95 sec per participant). The synthetic 7T images achieved significantly improved tissue contrast and sharpness in comparison to 3T images in both nonenhanced and contrast-enhanced subgroups. Meanwhile, there was no significant difference between acquired 7T and synthetic 7T images in terms of all the evaluation criteria for both nonenhanced and contrast-enhanced subgroups (P ≥ 0.180).
The deep learning model has potential to generate synthetic 7T images with similar image quality to acquired 7T images.
2 TECHNICAL EFFICACY: Stage 1.
超高场 7T MRI 可提供出色的组织对比度和解剖细节，但通常成本过高，并且在临床实践中无法广泛获得。
使用深度学习从广泛采集的 3T 图像生成合成 7T 图像，并评估该方法用于脑成像的可行性。
前瞻性。
33 名健康志愿者和 89 名脑部疾病患者，按 4:1 的比例分为训练和评估数据集。
3T 和 7T 时的 T1 加权非增强或增强对比磁化准备快速获取梯度回波序列。
开发了生成对抗网络（SynGAN），将 3T 图像作为输入生成合成 7T 图像。SynGAN 训练和评估分别针对非增强和增强配对采集进行。三位放射科医生使用 5 分李克特量表评估采集的 3T 和 7T 图像以及合成的 7T 图像的整体图像质量、伪影、锐度、对比度和血管可视化。
Wilcoxon 符号秩检验用于比较合成 7T 图像与采集的 7T 和 3T 图像，以及组内相关系数用于评估观察者间变异性。P<0.05 被认为具有统计学意义。
在 122 对 3T 和 7T MRI 扫描中，66 次无造影剂采集，56 次有造影剂采集。生成合成图像的平均时间约为每片 11.4 毫秒（每个参与者 2.95 秒）。与非增强和增强亚组的 3T 图像相比，合成的 7T 图像在组织对比度和锐度方面均有显著提高。同时，在非增强和增强亚组中，所有评估标准均无显著差异（P≥0.180）。
深度学习模型具有生成与采集的 7T 图像质量相似的合成 7T 图像的潜力。
2 技术功效：1 级。
