Deep ADMM-Net for Compressive Sensing MRI
Deep ADMM-Net for Compressive Sensing MRI
复制标题
DOI：
--
复制
发表时间：
2016-12
期刊：
影响因子：
--
通讯作者：
Yan Yang;Jian Sun-;Huibin Li;Zongben Xu
中科院分区：
文献类型：
--
作者：
Yan Yang;Jian Sun-;Huibin Li;Zongben Xu
压缩感知是快速磁共振成像的有效方法。它的目的是从少量的欠采样数据在k空间重建MR图像，并加快在MRI的数据采集。为了提高当前MRI系统的重建精度和计算速度，在本文中，我们提出了一种新的深度架构，称为ADMM-Net。ADMM-Net定义在一个数据流图上，该图是从用于优化基于CS的MRI模型的交替方向乘法（ADMM）算法中的迭代过程导出的。在训练阶段，网络的所有参数，例如，图像变换、收缩函数等，使用L-BFGS算法进行端到端的区别性训练。在测试阶段，它具有类似于ADMM的计算开销，但使用从基于CS的重建任务的训练数据中学习的优化参数。在k空间不同采样率下的MRI图像重建实验表明，该算法明显改善了ADMM算法的基本性能，并在计算速度快的情况下获得了较高的重建精度。
Compressive Sensing (CS) is an effective approach for fast Magnetic Resonance Imaging (MRI). It aims at reconstructing MR image from a small number of under-sampled data in k-space, and accelerating the data acquisition in MRI. To improve the current MRI system in reconstruction accuracy and computational speed, in this paper, we propose a novel deep architecture, dubbed ADMM-Net. ADMM-Net is defined over a data flow graph, which is derived from the iterative procedures in Alternating Direction Method of Multipliers (ADMM) algorithm for optimizing a CS-based MRI model. In the training phase, all parameters of the net, e.g., image transforms, shrinkage functions, etc., are discriminatively trained end-to-end using L-BFGS algorithm. In the testing phase, it has computational overhead similar to ADMM but uses optimized parameters learned from the training data for CS-based reconstruction task. Experiments on MRI image reconstruction under different sampling ratios in k-space demonstrate that it significantly improves the baseline ADMM algorithm and achieves high reconstruction accuracies with fast computational speed.