Pramanik Aniket, Aggarwal Hemant, Jacob Mathews
The University of Iowa, Iowa City, USA.
Proc IEEE Int Symp Biomed Imaging. 2020 Apr;2020:1428-1431. doi: 10.1109/isbi45749.2020.9098490. Epub 2020 May 22.
We introduce a fast model based deep learning approach for calibrationless parallel MRI reconstruction. The proposed scheme is a non-linear generalization of structured low rank (SLR) methods that self learn linear annihilation filters from the same subject. It pre-learns non-linear annihilation relations in the Fourier domain from exemplar data. The pre-learning strategy significantly reduces the computational complexity, making the proposed scheme three orders of magnitude faster than SLR schemes. The proposed framework also allows the use of a complementary spatial domain prior; the hybrid regularization scheme offers improved performance over calibrated image domain MoDL approach. The calibrationless strategy minimizes potential mismatches between calibration data and the main scan, while eliminating the need for a fully sampled calibration region.
我们介绍一种基于快速模型的深度学习方法用于无校准并行磁共振成像重建。所提出的方案是结构化低秩（SLR）方法的非线性推广，它能从同一受试者中自学习线性消除滤波器。它从示例数据中在傅里叶域预学习非线性消除关系。预学习策略显著降低了计算复杂度，使所提出的方案比SLR方案快三个数量级。所提出的框架还允许使用互补的空间域先验；这种混合正则化方案比校准图像域的MoDL方法具有更好的性能。无校准策略使校准数据与主扫描之间的潜在不匹配最小化，同时消除了对完全采样校准区域的需求。
