IEEE Trans Biomed Eng. 2018 Sep;65(9):1985-1995. doi: 10.1109/TBME.2018.2821699. Epub 2018 Apr 2.
Accelerated magnetic resonance (MR) image acquisition with compressed sensing (CS) and parallel imaging is a powerful method to reduce MR imaging scan time. However, many reconstruction algorithms have high computational costs. To address this, we investigate deep residual learning networks to remove aliasing artifacts from artifact corrupted images.
The deep residual learning networks are composed of magnitude and phase networks that are separately trained. If both phase and magnitude information are available, the proposed algorithm can work as an iterative k-space interpolation algorithm using framelet representation. When only magnitude data are available, the proposed approach works as an image domain postprocessing algorithm.
Even with strong coherent aliasing artifacts, the proposed network successfully learned and removed the aliasing artifacts, whereas current parallel and CS reconstruction methods were unable to remove these artifacts.
Comparisons using single and multiple coil acquisition show that the proposed residual network provides good reconstruction results with orders of magnitude faster computational time than existing CS methods.
The proposed deep learning framework may have a great potential for accelerated MR reconstruction by generating accurate results immediately.
利用压缩感知（CS）和并行成像进行加速磁共振（MR）图像采集是一种降低 MR 成像扫描时间的有效方法。然而，许多重建算法的计算成本很高。为此，我们研究了深度残差学习网络，以从有伪影的图像中去除混叠伪影。
深度残差学习网络由幅度网络和相位网络组成，分别进行训练。如果同时有相位和幅度信息，则所提出的算法可以作为使用帧表示的迭代 k 空间插值算法工作。当仅存在幅度数据时，所提出的方法可以作为图像域后处理算法工作。
即使存在强相干混叠伪影，所提出的网络也成功地学习并去除了混叠伪影，而现有的并行和 CS 重建方法无法去除这些伪影。
使用单线圈和多线圈采集的比较表明，所提出的残差网络提供了良好的重建结果，其计算时间比现有的 CS 方法快几个数量级。
所提出的深度学习框架可以通过立即生成准确的结果，为加速 MR 重建提供巨大的潜力。
