Accelerated MRI using iterative non-local shrinkage.
Accelerated MRI using iterative non-local shrinkage.
复制标题
DOI：
10.1109/embc.2014.6943897
复制
发表时间：
2014
期刊：
影响因子：
--
通讯作者：
Jacob M
中科院分区：
文献类型：
--
作者：
Mohsin YQ;Ongie G;Jacob M
我们引入了一种快速迭代的非局部收缩算法来从欠采样傅立叶测量中恢复MRI数据。这种方法是通过将当前的非局部方案重新制定为最小化全局准则的交替算法来实现的。该算法在非局部收缩步骤和二次子问题之间交替进行。由此产生的算法被观察到比当前的交替非局部算法要快得多。我们使用有效的延续策略来最小化局部最小问题。所提出的方案与最先进的正则化方案的比较表明，在混叠伪影和边缘的保存相当大的减少。
We introduce a fast iterative non-local shrinkage algorithm to recover MRI data from undersampled Fourier measurements. This approach is enabled by the reformulation of current non-local schemes as an alternating algorithm to minimize a global criterion. The proposed algorithm alternates between a non-local shrinkage step and a quadratic subproblem. The resulting algorithm is observed to be considerably faster than current alternating non-local algorithms. We use efficient continuation strategies to minimize local minima issues. The comparisons of the proposed scheme with state-of-the-art regularization schemes show a considerable reduction in alias artifacts and preservation of edges.