Division of Diagnostics and Specialist Medicine, Department of Health Medicine and Caring Sciences, Linköping University, Linköping, Sweden.
Center for Medical Image Science and Visualization (CMIV), Linköping University, Linköping, Sweden.
J Magn Reson Imaging. 2021 Sep;54(3):777-786. doi: 10.1002/jmri.27578. Epub 2021 Feb 25.
Although contrast agents would be beneficial, they are seldom used in four-dimensional (4D) flow magnetic resonance imaging (MRI) due to potential side effects and contraindications.
To develop and evaluate a deep learning architecture to generate high blood-tissue contrast in noncontrast 4D flow MRI by emulating the use of an external contrast agent.
Retrospective.
Of 222 data sets, 141 were used for neural network (NN) training (69 with and 72 without contrast agent). Evaluation was performed on the remaining 81 noncontrast data sets.
FIELD STRENGTH/SEQUENCES: Gradient echo or echo-planar 4D flow MRI at 1.5 T and 3 T.
A cyclic generative adversarial NN was trained to perform image translation between noncontrast and contrast data. Evaluation was performed quantitatively using contrast-to-noise ratio (CNR), signal-to-noise ratio (SNR), structural similarity index (SSIM), mean squared error (MSE) of edges, and Dice coefficient of segmentations. Three observers performed a qualitative assessment of blood-tissue contrast, noise, presence of artifacts, and image structure visualization.
The Wilcoxon rank-sum test evaluated statistical significance. Kendall's concordance coefficient assessed interobserver agreement.
Contrast in the regions of interest (ROIs) in the NN enhanced images increased by 88%, CNR increased by 63%, and SNR improved by 48% (all P < 0.001). The SSIM was 0.82 ± 0.01, and the MSE of edges was 0.09 ± 0.01 (range [0,1]). Segmentations based on the generated images resulted in a Dice similarity increase of 15.25%. The observers managed to differentiate between contrast MR images and our results; however, they preferred the NN enhanced images in 76.7% of cases. This percentage increased to 93.3% for phase-contrast MR angiograms created from the NN enhanced data. Visual grading scores were blood-tissue contrast = 4.30 ± 0.74, noise = 3.12 ± 0.98, and presence of artifacts = 3.63 ± 0.76. Image structures within and without the ROIs resulted in scores of 3.42 ± 0.59 and 3.07 ± 0.71, respectively (P < 0.001).
The proposed approach improves blood-tissue contrast in MR images and could be used to improve data quality, visualization, and postprocessing of cardiovascular 4D flow data. EVIDENCE LEVEL: 3 TECHNICAL EFFICACY: Stage 1.
尽管对比剂会很有帮助，但由于潜在的副作用和禁忌症，它们在四维（4D）流动磁共振成像（MRI）中很少使用。
开发和评估一种深度学习架构，通过模拟使用外部对比剂在非对比 4D 流动 MRI 中产生高血液-组织对比度。
回顾性。
在 222 个数据集，141 个用于神经网络（NN）训练（69 个有和 72 个没有对比剂）。其余 81 个非对比数据集进行了评估。
磁场强度/序列：1.5T 和 3T 的梯度回波或回波平面 4D 流动 MRI。
训练一个循环生成对抗网络（GAN），以执行非对比和对比数据之间的图像翻译。使用对比噪声比（CNR）、信噪比（SNR）、结构相似性指数（SSIM）、边缘均方误差（MSE）和分割的 Dice 系数进行定量评估。三名观察者对血液-组织对比度、噪声、伪影存在和图像结构可视化进行了定性评估。
Wilcoxon 秩和检验评估统计显著性。Kendall 一致性系数评估观察者间一致性。
感兴趣区域（ROI）的 NN 增强图像对比度增加了 88%，CNR 增加了 63%，SNR 提高了 48%（均 P<0.001）。SSIM 为 0.82±0.01，边缘 MSE 为 0.09±0.01（范围[0,1]）。基于生成图像的分割导致 Dice 相似性增加了 15.25%。观察者能够区分对比磁共振图像和我们的结果；然而，他们在 76.7%的情况下更喜欢 NN 增强的图像。对于基于 NN 增强数据创建的相位对比磁共振血管造影，这一比例增加到 93.3%。视觉分级评分分别为血液-组织对比度=4.30±0.74、噪声=3.12±0.98和伪影存在=3.63±0.76。ROI 内和外的图像结构分别产生 3.42±0.59 和 3.07±0.71 的评分（P<0.001）。
所提出的方法可提高磁共振图像中的血液-组织对比度，并可用于改善心血管 4D 流动数据的质量、可视化和后处理。
3 级
1 级
