Deep Learning Approach for Generating MRA Images From 3D Quantitative Synthetic MRI Without Additional Scans
Deep Learning Approach for Generating MRA Images From 3D Quantitative Synthetic MRI Without Additional Scans
复制标题
DOI：
10.1097/rli.0000000000000628
复制
发表时间：
2020-04-01
影响因子：
6.7
通讯作者：
Aoki, Shigeki
中科院分区：
文献类型：
--
作者：
Fujita, Shohei;Hagiwara, Akifumi;Aoki, Shigeki
目的定量合成磁共振成像（MRI）能够合成各种对比加权图像以及同时定量T1和T2弛豫时间和质子密度。然而，迄今为止，利用合成MRI生成磁共振血管造影（MRA）图像一直具有挑战性。本研究的目的是开发一种深度学习算法，根据3D合成MRI原始数据生成MRA图像。材料和方法11名健康志愿者和4例颅内动脉瘤患者被纳入本研究。所有参与者都接受了飞行时间（TOF）MRA序列和3D-QALAS合成MRI序列。3D-QALAS序列采集5张原始图像，用作深度学习网络的输入。通过单卷积和具有5倍交叉验证的U-网模型的组合将输入转换为其对应的MRA图像，然后将其与简单的线性组合模型进行比较。通过计算峰值信噪比（PSNR）、结构相似性指数测量（SSIM）和高频误差范数（HFEN）评价图像质量。这些计算是针对深度学习MRA（DL-MRA）和线性组合MRA（linear-MR）相对于TOF-MRA进行的，并使用非参数Wilcoxon符号秩检验进行比较。整体图像质量和分支可视化，每个评分5分制李克特量表，由2个委员会认证的放射科医师进行盲法和独立评定。DL-MRA的平均PSNR、SSIM和HFEN分别显著高于、高于和低于线性MRA（PSNR，35.3 ± 0.5 vs 34.0 ± 0.5，P < 0.001; SSIM，0.93 ± 0.02 vs 0.82 ± 0.02，P < 0.001; HFEN，0.61 ± 0.08 vs 0.86 ± 0.05，P < 0.001）。DL-MRA的总体图像质量与TOF-MRA相当（4.2 ± 0.7 vs 4.4 ± 0.7，P = 0.99），两种类型的图像均上级线性MRA（1.5 ± 0.6，均P < 0.001）。DL-MRA和TOF-MRA对颅内动脉分支的显示除眼动脉外无显著性差异（1.2 +/- 0.5 vs 2.3 +/- 1.2，P < 0.001）。结论通过3D合成MRI数据的深度学习生成的磁共振血管造影与TOF-MRA一样有效地显示了颅内主要动脉，具有固有对齐的定量图和多个对比加权图像。我们提出的算法可能是有用的颅内动脉瘤的筛查工具，而不需要额外的扫描时间。
ObjectivesQuantitative synthetic magnetic resonance imaging (MRI) enables synthesis of various contrast-weighted images as well as simultaneous quantification of T1 and T2 relaxation times and proton density. However, to date, it has been challenging to generate magnetic resonance angiography (MRA) images with synthetic MRI. The purpose of this study was to develop a deep learning algorithm to generate MRA images based on 3D synthetic MRI raw data.Materials and MethodsEleven healthy volunteers and 4 patients with intracranial aneurysms were included in this study. All participants underwent a time-of-flight (TOF) MRA sequence and a 3D-QALAS synthetic MRI sequence. The 3D-QALAS sequence acquires 5 raw images, which were used as the input for a deep learning network. The input was converted to its corresponding MRA images by a combination of a single-convolution and a U-net model with a 5-fold cross-validation, which were then compared with a simple linear combination model. Image quality was evaluated by calculating the peak signal-to-noise ratio (PSNR), structural similarity index measurements (SSIMs), and high frequency error norm (HFEN). These calculations were performed for deep learning MRA (DL-MRA) and linear combination MRA (linear-MR), relative to TOF-MRA, and compared with each other using a nonparametric Wilcoxon signed-rank test. Overall image quality and branch visualization, each scored on a 5-point Likert scale, were blindly and independently rated by 2 board-certified radiologists.ResultsDeep learning MRA was successfully obtained in all subjects. The mean PSNR, SSIM, and HFEN of the DL-MRA were significantly higher, higher, and lower, respectively, than those of the linear-MRA (PSNR, 35.3 +/- 0.5 vs 34.0 +/- 0.5, P < 0.001; SSIM, 0.93 +/- 0.02 vs 0.82 +/- 0.02, P < 0.001; HFEN, 0.61 +/- 0.08 vs 0.86 +/- 0.05, P < 0.001). The overall image quality of the DL-MRA was comparable to that of TOF-MRA (4.2 +/- 0.7 vs 4.4 +/- 0.7, P = 0.99), and both types of images were superior to that of linear-MRA (1.5 +/- 0.6, for both P < 0.001). No significant differences were identified between DL-MRA and TOF-MRA in the branch visibility of intracranial arteries, except for ophthalmic artery (1.2 +/- 0.5 vs 2.3 +/- 1.2, P < 0.001).ConclusionsMagnetic resonance angiography generated by deep learning from 3D synthetic MRI data visualized major intracranial arteries as effectively as TOF-MRA, with inherently aligned quantitative maps and multiple contrast-weighted images. Our proposed algorithm may be useful as a screening tool for intracranial aneurysms without requiring additional scanning time.