Low-rank and Sparse Matrix Decomposition with a-priori Knowledge for Dynamic 3D MRI Reconstruction

  title={Low-rank and Sparse Matrix Decomposition with a-priori Knowledge for Dynamic 3D MRI Reconstruction},
  author={D. Zonoobi and Shahrooz Faghih Roohi and Ashraf Ali Kassim},
It has been recently shown that incorporating priori knowledge significantly improves the performance of basic compressive sensing based approaches. We have managed to successfully exploit this idea for recovering a matrix as a summation of a Low-rank and a Sparse component from compressive measurements. When applied to the problem of construction of 4D Cardiac MR image sequences in real-time from highly under-sampled k-space data, our proposed method achieves superior… 

Figures from this paper

Dynamic Magnetic Resonance Imaging Reconstruction Based on Nonconvex Low-Rank Model
The quality of dynamic magnetic resonance imaging reconstruction has heavy impact on clinical diagnosis. In this paper, we propose a new reconstructive algorithm based on the model. In the algorithm,
A Fast Low-Rank Matrix Factorization Method for Dynamic Magnetic Resonance Imaging Restoration
This paper focuses on the reconstruction of dynamic magnetic resonance imaging (MRI), which is crucial to medical diagnoses and proposes a model based on robust principal component analysis (RPCA), which has been proved to be better than the nuclear norm.
Dynamic Magnetic Resonance Imaging via Nonconvex Low-Rank Matrix Approximation
Experimental results on cardiac perfusion and cardiac cine MRI data demonstrate that the proposed nonconvex alternating direction method outperforms the state-of-the-art MRI reconstruction methods in both image clarity and computation efficiency.
Sparse non-parametric Bayesian model for HEP-2 cell image classification
A non-parametric Bayesian model that is capable of determining the dictionary dimension automatically by exploiting the Indian Buffet Process (IBP) is proposed that obtained state-of-the-art cell classification accuracy and helps to reduce the computational cost significantly for the cell classification task.


Weighted-CS for reconstruction of highly under-sampled dynamic MRI sequences
  • D. Zonoobi, A. Kassim
  • Computer Science, Mathematics
    Proceedings of The 2012 Asia Pacific Signal and Information Processing Association Annual Summit and Conference
  • 2012
This paper investigates the potential of the new Weighted-Compressive Sensing approach which overcomes the major limitations of other compressive sensing and outperforms current state-of-the-art
Low rank matrix recovery for real-time cardiac MRI
In this paper, the Power Factorization algorithm is applied to efficiently recover the cardiac data matrix and promising results are presented to demonstrate the performance of this novel approach.
Accelerated Dynamic MRI Exploiting Sparsity and Low-Rank Structure: k-t SLR
A novel algorithm to reconstruct dynamic magnetic resonance imaging data from under-sampled k-t space data using the compact representation of the data in the Karhunen Louve transform (KLT) domain to exploit the correlations in the dataset.
On the reconstruction of sequences of sparse signals - The Weighted-CS
Compressed Sensing using Prior Rank , Intensity and Sparsity Model ( PRISM ) : Applications in Cardiac Cine MRI
Introduction: Compressed sensing (CS) has recently been applied to MR image reconstruction to shorten data acquisition time. In this work, we propose a novel CS method for dynamic MRI applications
Real-time cardiac MRI using low-rank and sparsity penalties
  • S. Lingala, Yue Hu, M. Jacob
  • Computer Science
    2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro
  • 2010
We introduce a novel algorithm to reconstruct real-time cardiac MRI data from undersampled radial acquisitions. We exploit the fact that the spatio-temporal data can be represented as the linear
A Fast Majorize–Minimize Algorithm for the Recovery of Sparse and Low-Rank Matrices
A novel algorithm to recover sparse and low-rank matrices from noisy and undersampled measurements and majorize the nondifferentiable spectral and sparsity penalties in the criterion by quadratic expressions to realize an iterative three-step alternating minimization scheme.