A dictionary-based graph-cut algorithm for MRI reconstruction.
A dictionary-based graph-cut algorithm for MRI reconstruction.
复制标题
DOI：
10.1002/nbm.4344
复制
发表时间：
2020-12
影响因子：
2.9
通讯作者：
Raj, Ashish
中科院分区：
文献类型：
--
作者：
Xu, Jiexun;Pannetier, Nicolas;Raj, Ashish
基于压缩感知的图像重建方法已经提出了随机欠采样方案，该方案产生非相干的、类似噪声的混叠伪影，这些伪影更容易去除。去噪过程通过施加稀疏性实施先验得到了关键的辅助。稀疏性是已知的，如果先验是Lp(0≤p≤1)范数的形式。CS方法一般使用这些先验的凸松弛，就像L1范数一样，这可能不能充分利用CS的能力。提出了一种有效的离散优化方法，它不仅适用于任意Lp范数先验，如一些非凸CS方法，而且还适用于高度非凸的截断罚函数，从而产生特定类型的保边先验。这些高级特征使得最小化问题高度非凸化，因此需要更复杂的最小化例程。这项工作结合了保边先验和随机欠采样，并使用一组称为图割的离散优化方法来求解所产生的优化。所产生的优化问题通过在字典内迭代地应用图割来解决，该字典在这里被定义为与这里使用的脑MRI数据相关的适当构造的一组向量。给出了活体数据的实验结果。对于活体数据的重建，所提出的算法比正则化感知或标准压缩感知具有更好的效果。
Compressive sensing based image reconstruction methods have proposed random under-sampling schemes that produces incoherent, noise-like aliasing artifacts, which are easier to remove. The denoising process is critically assisted by imposing sparsity-enforcing priors. Sparsity is known to be induced if the prior is of the form of Lp (0 ≤ p ≤ 1) norm. CS methods generally use a convex relaxation of these priors like the L1 norm, which may not exploit the full power of CS. An efficient, discrete optimization formulation is proposed which works not only on arbitrary Lp norm priors as some non-convex CS methods do, but also on highly non-convex truncated penalty functions, resulting in a specific type of edge preserving priors. These advanced features make the minimization problem highly non-convex, and thus call for more sophisticated minimization routines. The work combines edge-preserving priors with random under-sampling, and solve the resulting optimization using a set of discrete optimization methods called Graph Cuts. The resulting optimization problem is solved by applying graph cuts iteratively within a dictionary, defined here as an appropriately constructed set of vectors relevant to brain MRI data used here. Experimental results with in vivo data are presented. The proposed algorithm produces better results than regularized SENSE or standard compressive sensing for reconstruction of in vivo data.
登录
查看更多内容
DOI：
10.1109/tpami.2010.135
发表时间：
2011-04
影响因子：
23.6
作者：
Felzenszwalb PF;Zabih R
通讯作者：
Zabih R
影响因子：
3.3
作者：
Griswold, MA;Jakob, PM;Haase, A
通讯作者：
Haase, A
DOI：
10.1023/b:visi.0000022288.19776.77
发表时间：
2004-09-01
影响因子：
19.5
作者：
Felzenszwalb, PF;Huttenlocher, DP
通讯作者：
Huttenlocher, DP
DOI：
10.1109/tpami.2004.1262177
发表时间：
2004-02-01
影响因子：
23.6
作者：
Kolmogorov, V;Zabih, R
通讯作者：
Zabih, R
影响因子：
3.3
作者：
Haldar, Justin P.;Hernando, Diego;Liang, Zhi-Pei
通讯作者：
Liang, Zhi-Pei