KerNL: Kernel-Based Nonlinear Approach to Parallel MRI Reconstruction.
KerNL: Kernel-Based Nonlinear Approach to Parallel MRI Reconstruction.
复制标题
DOI：
10.1109/tmi.2018.2864197
复制
发表时间：
2019-01
影响因子：
10.6
通讯作者：
Ying L
中科院分区：
文献类型：
--
作者：
Lyu J;Nakarmi U;Liang D;Sheng J;Ying L
传统的基于校准的并行成像方法假设采集的多通道k空间数据和未采集的缺失数据之间的线性关系，其中使用一些自动校准数据来估计线性系数。在这项工作中，我们首先分析了传统的基于校准的方法中的模型误差，并证明了非线性关系。然后，提出了一个更一般的非线性框架的自动校准并行成像。在这个框架中，核技巧被用来表示一般的非线性关系之间的收购和未收购的k-空间数据，而不增加计算复杂度。非线性关系的识别仍然通过求解线性方程组来执行。实验结果表明，在较高的净缩减因子下，该方法的重建质量优于GRAPPA和NL-GRAPPA算法，具有上级的特点。
The conventional calibration-based parallel imaging method assumes a linear relationship between the acquired multichannel k-space data and the unacquired missing data, where the linear coefficients are estimated using some auto-calibration data. In this work, we first analyze the model errors in the conventional calibration-based methods and demonstrate the nonlinear relationship. Then a much more general nonlinear framework is proposed for auto-calibrated parallel imaging. In this framework, kernel tricks are employed to represent the general nonlinear relationship between acquired and unacquired k-space data without increasing the computational complexity. Identification of the nonlinear relationship is still performed by solving linear equations. Experimental results demonstrate that the proposed method can achieve reconstruction quality superior to GRAPPA and NL-GRAPPA at high net reduction factors.