Dynamic MRI Reconstruction Exploiting Partial Separability and t-SVD

In this paper, we proposed a new method to reconstruct dynamic magnetic imaging (dMRI) data from highly undersampled k-t space measurements. First, we use the partial separability (PS) model to capture the spatiotemporal correlations of dMRI data. Then, we introduce a new tensor decomposition method named as tensor singular value decomposition (t-SVD) to the reconstruction problem. PS and low tensor multi-rank constrains are jointly enforced to reconstruct dynamic MRI data. We develop an efficient algorithm based on the alternating direction method of multipliers (ADMM) to solve the proposed optimization problem. The experimental results demonstrate the superior performance of the proposed method.

[1]  Bing Chen,et al.  Hybrid CS-DMRI: Periodic Time-Variant Subsampling and Omnidirectional Total Variation Based Reconstruction , 2017, IEEE Transactions on Medical Imaging.

[2]  Zemin Zhang,et al.  Exact Tensor Completion Using t-SVD , 2015, IEEE Transactions on Signal Processing.

[3]  V. Aggarwal,et al.  Efficient Low Rank Tensor Ring Completion , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[4]  Yang Wang,et al.  Real-time dynamic MRI using parallel dictionary learning and dynamic total variation , 2017, Neurocomputing.

[5]  Emmanuel J. Candès,et al.  A Singular Value Thresholding Algorithm for Matrix Completion , 2008, SIAM J. Optim..

[6]  M. Lustig,et al.  Fast dynamic 3D MR spectroscopic imaging with compressed sensing and multiband excitation pulses for hyperpolarized 13C studies , 2011, Magnetic resonance in medicine.

[7]  Junbin Gao,et al.  Subspace Clustering via Learning an Adaptive Low-Rank Graph , 2018, IEEE Transactions on Image Processing.

[8]  Zhi-Pei Liang,et al.  Spatiotemporal Imaging with Partially Separable Functions , 2007, 2007 Joint Meeting of the 6th International Symposium on Noninvasive Functional Source Imaging of the Brain and Heart and the International Conference on Functional Biomedical Imaging.

[9]  Liqing Zhang,et al.  Tensor Ring Decomposition , 2016, ArXiv.

[10]  Michael Lustig,et al.  k-t SPARSE: High frame rate dynamic MRI exploiting spatio-temporal sparsity , 2006 .

[11]  Mathews Jacob,et al.  Accelerated Dynamic MRI Exploiting Sparsity and Low-Rank Structure: k-t SLR , 2011, IEEE Transactions on Medical Imaging.

[12]  Misha Elena Kilmer,et al.  Third-Order Tensors as Operators on Matrices: A Theoretical and Computational Framework with Applications in Imaging , 2013, SIAM J. Matrix Anal. Appl..

[13]  Eric L. Miller,et al.  Tensor-Based Formulation and Nuclear Norm Regularization for Multienergy Computed Tomography , 2013, IEEE Transactions on Image Processing.

[14]  E. Tyrtyshnikov,et al.  TT-cross approximation for multidimensional arrays , 2010 .

[15]  Zhi-Pei Liang,et al.  SPATIOTEMPORAL IMAGINGWITH PARTIALLY SEPARABLE FUNCTIONS , 2007, 2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[16]  Justin P. Haldar,et al.  PSF model-based reconstruction with sparsity constraint: Algorithm and application to real-time cardiac MRI , 2010, 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology.

[17]  Tamara G. Kolda,et al.  Tensor Decompositions and Applications , 2009, SIAM Rev..

[18]  Stuart Crozier,et al.  Multidimensional Compressed Sensing MRI Using Tensor Decomposition-Based Sparsifying Transform , 2014, PloS one.

[19]  Justin P. Haldar,et al.  Further development of image reconstruction from highly undersampled (k, t)-space data with joint partial separability and sparsity constraints , 2011, 2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[20]  Misha Elena Kilmer,et al.  Novel Methods for Multilinear Data Completion and De-noising Based on Tensor-SVD , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.