Scan-specific robust artificial-neural-networks for k-space interpolation (RAKI) reconstruction: Database-free deep learning for fast imaging.
Scan-specific robust artificial-neural-networks for k-space interpolation (RAKI) reconstruction: Database-free deep learning for fast imaging.
复制标题
DOI：
10.1002/mrm.27420
复制
发表时间：
2019-01
影响因子：
3.3
通讯作者：
Uğurbil K
中科院分区：
文献类型：
--
作者：
Akçakaya M;Moeller S;Weingärtner S;Uğurbil K
使用在自动校准信号 (ACS) 数据上训练的扫描特定深度学习来开发改进的 k 空间重建方法。用于 k 空间插值 (RAKI) 重建的鲁棒人工神经网络在 ACS 数据上训练卷积神经网络。与传统的基于线性 k 空间插值的方法（例如基于线性卷积核的 GRAPPA）相反，这使得能够从采集的 k 空间数据中对丢失的 k 空间线进行非线性估计，并具有改进的噪声恢复能力。训练算法是使用梯度下降算法在 ACS 区域中的目标点上使用均方误差损失函数来实现的。神经网络包含三层卷积运算符，其中两层包含非线性激活函数。在体模以及神经和心脏体内数据集中，将 RAKI 方法的噪声性能和重建质量与 GRAPPA 进行了比较。幻影成像表明，无论是视觉上还是定量上，所提出的 RAKI 方法在高（≥4）加速度下都优于 GRAPPA。定量心脏成像显示，与 GRAPPA 相比，高加速度（速率 4：23% 和速率 5：48%）下的噪声恢复能力有所提高。在高加速度下的高分辨率脑成像中也观察到了相同的抗噪能力提高的趋势。 RAKI 方法为 MRI 重建提供了一种无需训练数据库的深度学习方法，有可能改进许多现有的重建方法，并且与传统的数据采集协议兼容。
To develop an improved k-space reconstruction method using scan-specific deep learning that is trained on autocalibration signal (ACS) data. Robust Artificial-neural-networks for k-space Interpolation (RAKI) reconstruction trains convolutional neural networks on ACS data. This enables non-linear estimation of missing k-space lines from acquired k-space data with improved noise resilience, as opposed to conventional linear k-space interpolation-based methods, such as GRAPPA, which are based on linear convolutional kernels. The training algorithm is implemented using a mean square error loss function over the target points in the ACS region, using a gradient descent algorithm. The neural network contains three layers of convolutional operators, with two of these including non-linear activation functions. The noise performance and reconstruction quality of the RAKI method was compared with GRAPPA in phantom, as well as in neurological and cardiac in vivo datasets. Phantom imaging shows that the proposed RAKI method outperforms GRAPPA at high (≥4) acceleration rates, both visually and quantitatively. Quantitative cardiac imaging shows improved noise resilience at high acceleration rates (rate 4: 23% and rate 5: 48%) over GRAPPA. The same trend of improved noise resilience is also observed in high-resolution brain imaging at high acceleration rates. The RAKI method offers a training database-free deep learning approach for MRI reconstruction, with the potential to improve many existing reconstruction approaches, and is compatible with conventional data acquisition protocols.
登录
查看更多内容
影响因子：
3.3
作者：
Doneva, Mariya;Boernert, Peter;Mertins, Alfred
通讯作者：
Mertins, Alfred
影响因子：
3.3
作者：
Blaimer, Martin;Breuer, Felix A.;Jakob, Peter M.
通讯作者：
Jakob, Peter M.
影响因子：
3.3
作者：
Griswold, MA;Jakob, PM;Haase, A
通讯作者：
Haase, A
影响因子：
10.6
作者：
Lingala SG;Hu Y;DiBella E;Jacob M
通讯作者：
Jacob M
影响因子：
3.3
作者：
Akcakaya, Mehmet;Basha, Tamer A.;Goddu, Beth;Goepfert, Lois A.;Kissinger, Kraig V.;Tarokh, Vahid;Manning, Warren J.;Nezafat, Reza
通讯作者：
Nezafat, Reza