Department of Radiology, University of Yamanashi, 1110 Shimokato, Chuo, Yamanashi, 409-3898, Japan.
Department of Diagnostic Radiology and Neuroradiology, University Medicine Greifswald, Greifswald, Germany.
Eur Radiol. 2020 Nov;30(11):5923-5932. doi: 10.1007/s00330-020-07006-1. Epub 2020 Jun 17.
To reveal the utility of motion artifact reduction with convolutional neural network (MARC) in gadoxetate disodium-enhanced multi-arterial phase MRI of the liver.
This retrospective study included 192 patients (131 men, 68.7 ± 10.3 years) receiving gadoxetate disodium-enhanced liver MRI in 2017. Datasets were submitted to a newly developed filter (MARC), consisting of 7 convolutional layers, and trained on 14,190 cropped images generated from abdominal MR images. Motion artifact for training was simulated by adding periodic k-space domain noise to the images. Original and filtered images of pre-contrast and 6 arterial phases (7 image sets per patient resulting in 1344 sets in total) were evaluated regarding motion artifacts on a 4-point scale. Lesion conspicuity in original and filtered images was ranked by side-by-side comparison.
Of the 1344 original image sets, motion artifact score was 2 in 597, 3 in 165, and 4 in 54 sets. MARC significantly improved image quality over all phases showing an average motion artifact score of 1.97 ± 0.72 compared to 2.53 ± 0.71 in original MR images (p < 0.001). MARC improved motion scores from 2 to 1 in 177/596 (29.65%), from 3 to 2 in 119/165 (72.12%), and from 4 to 3 in 34/54 sets (62.96%). Lesion conspicuity was significantly improved (p < 0.001) without removing anatomical details.
Motion artifacts and lesion conspicuity of gadoxetate disodium-enhanced arterial phase liver MRI were significantly improved by the MARC filter, especially in cases with substantial artifacts. This method can be of high clinical value in subjects with failing breath-hold in the scan.
• This study presents a newly developed deep learning-based filter for artifact reduction using convolutional neural network (motion artifact reduction with convolutional neural network, MARC). • MARC significantly improved MR image quality after gadoxetate disodium administration by reducing motion artifacts, especially in cases with severely degraded images. • Postprocessing with MARC led to better lesion conspicuity without removing anatomical details.
揭示卷积神经网络（MARC）在钆塞酸二钠增强多动脉期肝脏 MRI 中的运动伪影减少的效用。
本回顾性研究纳入了 2017 年接受钆塞酸二钠增强肝脏 MRI 的 192 例患者（男 131 例，68.7±10.3 岁）。数据集被提交给一个新开发的滤波器（MARC），该滤波器由 7 个卷积层组成，并在 14190 张从腹部 MRI 图像生成的裁剪图像上进行训练。通过向图像添加周期性的 k 空间域噪声来模拟运动伪影。对原始和对比前及 6 个动脉期（每位患者 7 个图像集，共 1344 个图像集）的图像进行运动伪影的 4 分制评分评估。通过并排比较对原始和滤波图像的病灶显影进行评分。
在 1344 个原始图像集中，运动伪影评分在 597 个中为 2，在 165 个中为 3，在 54 个中为 4。MARC 显著改善了所有相位的图像质量，与原始 MR 图像的 2.53±0.71 相比，平均运动伪影评分为 1.97±0.72（p<0.001）。MARC 将运动评分从 2 提高到 1，在 177/596（29.65%）中，从 3 提高到 2，在 119/165（72.12%）中，从 4 提高到 3，在 34/54（62.96%）中。病灶显影明显改善（p<0.001），而不消除解剖细节。
使用 MARC 滤波器可显著改善钆塞酸二钠增强动脉期肝脏 MRI 的运动伪影和病灶显影，尤其是在存在大量伪影的情况下。对于在扫描中无法屏住呼吸的患者，该方法具有较高的临床价值。
本研究提出了一种新的基于深度学习的卷积神经网络（运动伪影减少的卷积神经网络，MARC）用于减少伪影的滤波器。
MARC 显著改善了钆塞酸二钠给药后的磁共振图像质量，降低了运动伪影，特别是在图像严重恶化的情况下。
用 MARC 进行后处理可以改善病灶显影，而不消除解剖细节。
