Deep Generalization of Structured Low-Rank Algorithms (Deep-SLR).
Deep Generalization of Structured Low-Rank Algorithms (Deep-SLR).
复制标题
DOI：
10.1109/tmi.2020.3014581
复制
发表时间：
2020-12
影响因子：
10.6
通讯作者：
Jacob M
中科院分区：
文献类型：
--
作者：
Pramanik A;Aggarwal HK;Jacob M
结构化低阶(SLR)算法是一种强大的图像重建框架，它利用了不同性质导致的信号傅里叶样本之间的湮没关系。该方案依靠低阶矩阵补全来估计测量数据中的湮灭关系。这一策略的主要挑战是矩阵补全的高计算复杂性。我们引入深度学习(DL)方法来显著降低计算复杂度。具体地说，我们使用基于卷积神经网络(CNN)的滤波器组，该滤波器组被训练来估计磁共振成像(MRI)中不完美(欠采样和噪声)k空间测量的湮灭关系。与从数据集本身学习线性滤波器组参数的SLR方案相比，计算效率的主要原因是从样本数据预先学习非线性CNN的参数。实验结果表明，该方案可以实现无定标的并行核磁共振成像，其性能与SLR方案相近，而运行时间减少了约三个数量级。与预定标和自定标方法不同，提出的未定标方法对运动误差不敏感，并提供更高的加速度。该方案还加入了互补的图像域先验信息，从而显著改善了SLR方案的性能。
Structured low-rank (SLR) algorithms, which exploit annihilation relations between the Fourier samples of a signal resulting from different properties, is a powerful image reconstruction framework in several applications. This scheme relies on low-rank matrix completion to estimate the annihilation relations from the measurements. The main challenge with this strategy is the high computational complexity of matrix completion. We introduce a deep learning (DL) approach to significantly reduce the computational complexity. Specifically, we use a convolutional neural network (CNN)-based filterbank that is trained to estimate the annihilation relations from imperfect (under-sampled and noisy) k-space measurements of Magnetic Resonance Imaging (MRI). The main reason for the computational efficiency is the pre-learning of the parameters of the non-linear CNN from exemplar data, compared to SLR schemes that learn the linear filterbank parameters from the dataset itself. Experimental comparisons show that the proposed scheme can enable calibration-less parallel MRI; it can offer performance similar to SLR schemes while reducing the runtime by around three orders of magnitude. Unlike pre-calibrated and self-calibrated approaches, the proposed uncalibrated approach is insensitive to motion errors and affords higher acceleration. The proposed scheme also incorporates image domain priors that are complementary, thus significantly improving the performance over that of SLR schemes.