Low-Rank and Adaptive Sparse Signal (LASSI) Models for Highly Accelerated Dynamic Imaging

Sparsity-based approaches have been popular in many applications in image processing and imaging. Compressed sensing exploits the sparsity of images in a transform domain or dictionary to improve image recovery fromundersampledmeasurements. In the context of inverse problems in dynamic imaging, recent research has demonstrated the promise of sparsity and low-rank techniques. For example, the patches of the underlying data are modeled as sparse in an adaptive dictionary domain, and the resulting image and dictionary estimation from undersampled measurements is called dictionary-blind compressed sensing, or the dynamic image sequence is modeled as a sum of low-rank and sparse (in some transform domain) components (L+S model) that are estimated from limited measurements. In this work, we investigate a data-adaptive extension of the L+S model, dubbed LASSI, where the temporal image sequence is decomposed into a low-rank component and a component whose spatiotemporal (3D) patches are sparse in some adaptive dictionary domain. We investigate various formulations and efficient methods for jointly estimating the underlying dynamic signal components and the spatiotemporal dictionary from limited measurements. We also obtain efficient sparsity penalized dictionary-blind compressed sensing methods as special cases of our LASSI approaches. Our numerical experiments demonstrate the promising performance of LASSI schemes for dynamicmagnetic resonance image reconstruction from limited k-t space data compared to recent methods such as k-t SLR and L+S, and compared to the proposed dictionary-blind compressed sensing method.

[1]  Emmanuel J. Candès,et al.  Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information , 2004, IEEE Transactions on Information Theory.

[2]  Rabab Kreidieh Ward,et al.  Learning space-time dictionaries for blind compressed sensing dynamic MRI reconstruction , 2015, 2015 IEEE International Conference on Image Processing (ICIP).

[3]  Kay Nehrke,et al.  k‐t PCA: Temporally constrained k‐t BLAST reconstruction using principal component analysis , 2009, Magnetic resonance in medicine.

[4]  A. Bilgin,et al.  Wavelet-based Compressed Sensing using Gaussian Scale Mixtures , 2009 .

[5]  Leon Axel,et al.  Combination of Compressed Sensing and Parallel Imaging for Highly-Accelerated 3 D First-Pass Cardiac Perfusion MRI , 2009 .

[6]  Leslie Ying,et al.  Undersampled dynamic magnetic resonance imaging using patch-based spatiotemporal dictionaries , 2013, 2013 IEEE 10th International Symposium on Biomedical Imaging.

[7]  Justin P. Haldar,et al.  Spatiotemporal imaging with partially separable functions: A matrix recovery approach , 2010, 2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[8]  Dong Liang,et al.  Parallel imaging via sparse representation over a learned dictionary , 2015, 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI).

[9]  Patrick L. Combettes,et al.  Signal Recovery by Proximal Forward-Backward Splitting , 2005, Multiscale Model. Simul..

[10]  Jong Chul Ye,et al.  k‐t FOCUSS: A general compressed sensing framework for high resolution dynamic MRI , 2009, Magnetic resonance in medicine.

[11]  Justin P. Haldar,et al.  Image Reconstruction From Highly Undersampled $( {\bf k}, {t})$-Space Data With Joint Partial Separability and Sparsity Constraints , 2012, IEEE Transactions on Medical Imaging.

[12]  Yoram Bresler,et al.  ADAPTIVE REAL-TIME CARDIAC MRI USING PARADISE: VALIDATION BY THE PHYSIOLOGICALLY IMPROVED NCAT PHANTOM , 2007, 2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[13]  Y. Bresler,et al.  Multiscale Dictionary Learning for MRI , 2010 .

[14]  Stephen P. Boyd,et al.  Proximal Algorithms , 2013, Found. Trends Optim..

[15]  Michael Elad,et al.  Sparse Representation for Color Image Restoration , 2008, IEEE Transactions on Image Processing.

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

[17]  M. Elad,et al.  $rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation , 2006, IEEE Transactions on Signal Processing.

[18]  A. Bruckstein,et al.  K-SVD : An Algorithm for Designing of Overcomplete Dictionaries for Sparse Representation , 2005 .

[19]  Michael Elad,et al.  Image Denoising Via Sparse and Redundant Representations Over Learned Dictionaries , 2006, IEEE Transactions on Image Processing.

[20]  Daniel Rueckert,et al.  Dictionary Learning and Time Sparsity in Dynamic MRI , 2012, MICCAI.

[21]  David J. Field,et al.  Emergence of simple-cell receptive field properties by learning a sparse code for natural images , 1996, Nature.

[22]  Suyash P. Awate,et al.  Spatiotemporal dictionary learning for undersampled dynamic MRI reconstruction via joint frame-based and dictionary-based sparsity , 2012, 2012 9th IEEE International Symposium on Biomedical Imaging (ISBI).

[23]  Daniel K Sodickson,et al.  Low‐rank plus sparse matrix decomposition for accelerated dynamic MRI with separation of background and dynamic components , 2015, Magnetic resonance in medicine.

[24]  Charles R. Johnson,et al.  Topics in Matrix Analysis , 1991 .

[25]  Jeffrey A. Fessler,et al.  Improved Robust PCA using low-rank denoising with optimal singular value shrinkage , 2014, 2014 IEEE Workshop on Statistical Signal Processing (SSP).

[26]  D. Donoho,et al.  Sparse MRI: The application of compressed sensing for rapid MR imaging , 2007, Magnetic resonance in medicine.

[27]  Yonina C. Eldar,et al.  Blind Compressed Sensing , 2010, IEEE Transactions on Information Theory.

[28]  Wei Lu,et al.  Real-time dynamic MR image reconstruction using Kalman Filtered Compressed Sensing , 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

[29]  Bastian Goldlücke,et al.  Variational Analysis , 2014, Computer Vision, A Reference Guide.

[30]  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.

[31]  Y. C. Pati,et al.  Orthogonal matching pursuit: recursive function approximation with applications to wavelet decomposition , 1993, Proceedings of 27th Asilomar Conference on Signals, Systems and Computers.

[32]  Yi Ma,et al.  Robust principal component analysis? , 2009, JACM.

[33]  Qin Lin,et al.  Bayesian Nonparametric Dictionary Learning for Compressed Sensing MRI , 2013, IEEE Transactions on Image Processing.

[34]  Philip J. Bones,et al.  An improved approach in applying compressed sensing in parallel MR imaging , 2009 .

[35]  Karin Schnass,et al.  Dictionary Identification—Sparse Matrix-Factorization via $\ell_1$ -Minimization , 2009, IEEE Transactions on Information Theory.

[36]  Raj Rao Nadakuditi,et al.  The singular values and vectors of low rank perturbations of large rectangular random matrices , 2011, J. Multivar. Anal..

[37]  Ping Feng,et al.  Spectrum-blind minimum-rate sampling and reconstruction of multiband signals , 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

[38]  Pingkun Yan,et al.  Alternatively Constrained Dictionary Learning For Image Superresolution , 2014, IEEE Transactions on Cybernetics.

[39]  Mathews Jacob,et al.  Blind compressed sensing with sparse dictionaries for accelerated dynamic MRI , 2013, 2013 IEEE 10th International Symposium on Biomedical Imaging.

[40]  L. Ying,et al.  Accelerating SENSE using compressed sensing , 2009, Magnetic resonance in medicine.

[41]  Ganesh Adluru,et al.  Reordering for Improved Constrained Reconstruction from Undersampled k-Space Data , 2008, Int. J. Biomed. Imaging.

[42]  Mathews Jacob,et al.  Blind Compressive Sensing Dynamic MRI , 2013, IEEE Transactions on Medical Imaging.

[43]  Pablo A. Parrilo,et al.  Rank-Sparsity Incoherence for Matrix Decomposition , 2009, SIAM J. Optim..

[44]  Jeffrey A. Fessler,et al.  LASSI: A low-rank and adaptive sparse signal model for highly accelerated dynamic imaging , 2016, 2016 IEEE 12th Image, Video, and Multidimensional Signal Processing Workshop (IVMSP).

[45]  S. Frick,et al.  Compressed Sensing , 2014, Computer Vision, A Reference Guide.

[46]  Y. Bresler,et al.  Spectrum-blind minimum-rate sampling and reconstruction of 2-D multiband signals , 1996, Proceedings of 3rd IEEE International Conference on Image Processing.

[47]  Armando Manduca,et al.  Highly Undersampled Magnetic Resonance Image Reconstruction via Homotopic $\ell_{0}$ -Minimization , 2009, IEEE Transactions on Medical Imaging.

[48]  Jeffrey A. Fessler,et al.  Efficient Sum of Outer Products Dictionary Learning (SOUP-DIL) and Its Application to Inverse Problems , 2015, IEEE Transactions on Computational Imaging.

[49]  Kjersti Engan,et al.  Method of optimal directions for frame design , 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

[50]  A. Manduca,et al.  Local versus Global Low-Rank Promotion in Dynamic MRI Series Reconstruction , 2010 .

[51]  Rabab Kreidieh Ward,et al.  Learning the sparsity basis in low-rank plus sparse model for dynamic MRI reconstruction , 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[52]  Jeffrey A. Fessler,et al.  5002 Dynamic MRI Reconstruction using Low-Rank plus Sparse model with Optimal Rank Regularized Eigen-Shrinkage , 2013 .

[53]  Yoram Bresler,et al.  MR Image Reconstruction From Highly Undersampled k-Space Data by Dictionary Learning , 2011, IEEE Transactions on Medical Imaging.

[54]  Daniel Rueckert,et al.  Dictionary Learning and Time Sparsity for Dynamic MR Data Reconstruction , 2014, IEEE Transactions on Medical Imaging.

[55]  Namrata Vaswani,et al.  An Online Algorithm for Separating Sparse and Low-Dimensional Signal Sequences From Their Sum , 2013, IEEE Transactions on Signal Processing.

[56]  Peter Boesiger,et al.  Compressed sensing in dynamic MRI , 2008, Magnetic resonance in medicine.

[57]  Guillermo Sapiro,et al.  Online Learning for Matrix Factorization and Sparse Coding , 2009, J. Mach. Learn. Res..

[58]  David Atkinson,et al.  Dynamic MR Image Reconstruction–Separation From Undersampled (${\bf k},t$)-Space via Low-Rank Plus Sparse Prior , 2014, IEEE Transactions on Medical Imaging.

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

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

[61]  Justin P. Haldar,et al.  Low rank matrix recovery for real-time cardiac MRI , 2010, 2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[62]  John Wright,et al.  RASL: Robust alignment by sparse and low-rank decomposition for linearly correlated images , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[63]  Leslie Ying,et al.  Compressed Sensing Dynamic Cardiac Cine MRI Using Learned Spatiotemporal Dictionary , 2014, IEEE Transactions on Biomedical Engineering.

[64]  Raj Rao Nadakuditi,et al.  OptShrink: An Algorithm for Improved Low-Rank Signal Matrix Denoising by Optimal, Data-Driven Singular Value Shrinkage , 2013, IEEE Transactions on Information Theory.

[65]  P. Boesiger,et al.  Advances in sensitivity encoding with arbitrary k‐space trajectories , 2001, Magnetic resonance in medicine.

[66]  Rick Chartrand,et al.  Compressed sensing recovery via nonconvex shrinkage penalties , 2015, ArXiv.

[67]  W. Marsden I and J , 2012 .