Advanced Technology Research Department, Research and Development Center, Canon Medical Systems Corporation, Kawasaki-shi, Kanagawa, Japan.
Magn Reson Med. 2021 Aug;86(2):820-834. doi: 10.1002/mrm.28758. Epub 2021 Mar 14.
The purposes of this work are to develop a method for efficiently processing MR-specific artifacts using a convolutional neural network (CNN), and to present its applications for the removal of the artifacts without suppressing actual signals. In MR images that are acquired using parallel imaging and/or EPI, the locations of aliasing artifacts and/or N-half ghost artifacts can be analytically calculated. However, existing methods using CNNs do not take the structures of the artifacts into account, and therefore need a large number of convolution layers for processing the artifacts.
For processing the artifacts, a new layer that is named the aliasing layer (AL) is proposed. Because a CNN stands on the assumption that an image has spatial locality, a convolution layer is formulated as a linear function of neighbor locations. For processing the artifacts, the AL preprocesses MR images by moving the calculated locations to the locations accessible through summations over all channels in a standard convolution layer. To evaluate the application of ALs for the removal of parallel imaging and EPI artifacts, CNNs with ALs were compared with those without ALs.
The results showed that image-quality metrics of a six-layer CNN with ALs were better than those of a 12-layer CNN without ALs. The results also showed that CNNs with ALs suppressed the artifacts selectively.
The aliasing layer is proposed for processing MR-specific artifacts efficiently. The experimental results demonstrated that the AL improved CNNs for removing artifacts from parallel imaging and EPI.
本研究旨在开发一种利用卷积神经网络（CNN）有效处理磁共振特定伪影的方法，并展示其在不抑制实际信号的情况下去除伪影的应用。在使用并行成像和/或 EPI 采集的磁共振图像中，可以分析计算混叠伪影和/或 N 半鬼影伪影的位置。然而，现有的基于 CNN 的方法没有考虑到伪影的结构，因此需要大量的卷积层来处理伪影。
为了处理伪影，提出了一种新的层，称为混叠层（AL）。由于 CNN 基于图像具有空间局部性的假设，卷积层被表示为邻居位置的线性函数。为了处理伪影，AL 通过将计算出的位置移动到通过标准卷积层中所有通道的求和可到达的位置，对磁共振图像进行预处理。为了评估 AL 在去除并行成像和 EPI 伪影中的应用，比较了具有和不具有 AL 的 CNN。
结果表明，具有 6 层 AL 的 CNN 的图像质量指标优于没有 AL 的 12 层 CNN。结果还表明，具有 AL 的 CNN 可以有选择地抑制伪影。
提出了混叠层来有效地处理磁共振特定的伪影。实验结果表明，AL 提高了 CNN 去除并行成像和 EPI 伪影的能力。
