Division of Image Processing, Department of Radiology, Leiden University Medical Center, Leiden, The Netherlands.
Circuits & Systems Group, Electrical Engineering, Mathematics and Computer Science Faculty, Delft University of Technology, Delft, The Netherlands.
Magn Reson Med. 2022 Apr;87(4):2063-2073. doi: 10.1002/mrm.29073. Epub 2021 Nov 9.
To learn a preconditioner that accelerates parallel imaging (PI) and compressed sensing (CS) reconstructions.
A convolutional neural network (CNN) with residual connections was used to train a preconditioning operator. Training and validation data were simulated using 50% brain images and 50% white Gaussian noise images. Each multichannel training example contains a simulated sampling mask, complex coil sensitivity maps, and two regularization parameter maps. The trained model was integrated in the preconditioned conjugate gradient (PCG) method as part of the split Bregman CS method. The acceleration performance was compared with that of a circulant PI-CS preconditioner for varying undersampling factors, number of coil elements and anatomies.
The learned preconditioner reduces the number of PCG iterations by a factor of 4, yielding a similar acceleration as an efficient circulant preconditioner. The method generalizes well to different sampling schemes, coil configurations and anatomies.
It is possible to learn adaptable preconditioners for PI and CS reconstructions that meet the performance of state-of-the-art preconditioners. Further acceleration could be achieved by optimizing the network architecture and the training set. Such a preconditioner could also be integrated in fully learned reconstruction methods to accelerate the training process of unrolled networks.
学习一种能够加速并行成像（PI）和压缩感知（CS）重建的预处理算子。
使用具有残差连接的卷积神经网络（CNN）来训练预处理算子。使用 50%的脑图像和 50%的白高斯噪声图像模拟训练和验证数据。每个多通道训练示例包含一个模拟的采样掩模、复数线圈灵敏度图和两个正则化参数图。训练好的模型作为分裂 Bregman CS 方法的一部分集成到预处理共轭梯度（PCG）方法中。将加速性能与不同欠采样因子、线圈元素数量和解剖结构的循环 PI-CS 预处理器进行了比较。
所学习的预处理算子将 PCG 迭代次数减少了 4 倍，产生了与高效循环预处理器相似的加速效果。该方法很好地适用于不同的采样方案、线圈配置和解剖结构。
可以学习适用于 PI 和 CS 重建的自适应预处理算子，以满足最先进预处理器的性能要求。通过优化网络架构和训练集，可以进一步提高加速效果。这样的预处理器也可以集成到完全学习的重建方法中，以加速展开网络的训练过程。
