Fast Multiclass Dictionaries Learning With Geometrical Directions in MRI Reconstruction

@article{Zhan2016FastMD,
  title={Fast Multiclass Dictionaries Learning With Geometrical Directions in MRI Reconstruction},
  author={Zhifang Zhan and Jian-Feng Cai and Di Guo and Yunsong Liu and Zhong Chen and Xiaobo Qu},
  journal={IEEE Transactions on Biomedical Engineering},
  year={2016},
  volume={63},
  pages={1850-1861}
}
Objective: Improve the reconstructed image with fast and multiclass dictionaries learning when magnetic resonance imaging is accelerated by undersampling the k-space data. Methods: A fast orthogonal dictionary learning method is introduced into magnetic resonance image reconstruction to provide adaptive sparse representation of images. To enhance the sparsity, image is divided into classified patches according to the same geometrical direction and dictionary is trained within each class. A new… 
CS-MRI reconstruction based on analysis dictionary learning and manifold structure regularization
TLDR
A novel CS-MRI model based on analysis dictionary learning and manifold structure regularization and a proper tight frame constraint is used to obtain an effective overcomplete analysis dictionary with a high sparsifying capacity is proposed.
Efficient directionality-driven dictionary learning for compressive sensing magnetic resonance imaging reconstruction
TLDR
An MR reconstruction algorithm is proposed that employs the double sparsity model coupled with online sparse dictionary learning to learn directional features of the region under observation from existing prior knowledge to enhance the capability of sparsely representing directional features in an MR image and results in better reconstructions.
Sparse representation of classified patches for CS-MRI reconstruction
TLDR
A patch based uniform model according to orthogonal dictionary learning and lp norm minimization (ODNM) is developed and achieves a better performance than several state-of-the-art algorithms.
Highly undersampled MR image reconstruction using an improved dual-dictionary learning method with self-adaptive dictionaries
TLDR
The proposed method can efficiently and significantly improve the quality and robustness of MR image reconstruction and feature improved adaptability by using self-adaptive dictionaries.
Adaptive Transform Learning and Joint Sparsity Based PLORAKS Parallel Magnetic Resonance Image Reconstruction
TLDR
This work proposed combining adaptive transform learning and joint sparsity with the PLORAKS model to obtain two algorithms, and reconstruction problems are solved by using the alternating direction method of multipliers (ADMM), conjugate gradient techniques, and structural similarity index measure (SSIM).
Sparse MRI reconstruction using multi-contrast image guided graph representation.
TLDR
This work proposes a new approach to reconstruct magnetic resonance images by learning the prior knowledge from these multi-contrast images with graph-based wavelet representations and forms the reconstruction as a bi-level optimization problem to allow misalignment between these images.
Accelerated image reconstruction with separable Hankel regularization in parallel MRI
  • Xinlin Zhang, Zi Wang, Xi Peng, Qin Xu, D. Guo, X. Qu
  • Medicine
    2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)
  • 2021
TLDR
A separable Hankel low rank reconstruction method to explore the low rankness of each row and each column using the self-consistence and conjugate symmetry property of k-space data is proposed.
Transform Learning for Magnetic Resonance Image Reconstruction: From Model-Based Learning to Building Neural Networks
TLDR
A unified framework for incorporating various TL-based models is presented and the connections between TL and convolutional or filter-bank models and corresponding multilayer extensions, with connections to deep learning are discussed.
Orthogonal tensor dictionary learning for accelerated dynamic MRI
TLDR
Numerical experiments on phantom and synthetic data show significant improvements in reconstruction accuracy and computational efficiency obtained by the proposed scheme over the existing method that uses the 1D/2D model with overcomplete dictionary learning.
Image reconstruction with low-rankness and self-consistency of k-space data in parallel MRI
TLDR
An image reconstruction approach named STDLR-SPiriT is proposed to explore the simultaneous two-directional low-rankness (STDLR) in the k-space data and to mine the data correlation from multiple receiver coils with the iterative self-consistent parallel imaging reconstruction (SPIRiT).
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 74 REFERENCES
Undersampled MRI reconstruction with patch-based directional wavelets.
TLDR
Simulation results on phantom and in vivo data indicate that the proposed patch-based directional wavelets method outperforms conventional compressed sensing MRI methods in preserving the edges and suppressing the noise.
MR Image Reconstruction From Highly Undersampled k-Space Data by Dictionary Learning
TLDR
Dramatic improvements on the order of 4-18 dB in reconstruction error and doubling of the acceptable undersampling factor using the proposed adaptive dictionary as compared to previous CS methods are demonstrated.
Magnetic resonance image reconstruction using trained geometric directions in 2D redundant wavelets domain and non-convex optimization.
TLDR
Numerical simulation results on vivo magnetic resonance images demonstrate that the proposed PBDW-based MRI reconstruction is improved from two aspects: an efficient non-convex minimization algorithm is modified to enhance image quality and P BDW are extended into shift-invariant discrete wavelet domain to enhance the ability of transform on sparsifying piecewise smooth image features.
Highly Undersampled Magnetic Resonance Image Reconstruction Using Two-Level Bregman Method With Dictionary Updating
TLDR
A two-level Bregman Method with dictionary updating for highly undersampled magnetic resonance (MR) image reconstruction that can efficiently reconstruct MR images and present advantages over the current state-of-the-art reconstruction approach.
Magnetic resonance image reconstruction from undersampled measurements using a patch-based nonlocal operator
TLDR
This paper designs a patch-based nonlocal operator (PANO) to sparsify magnetic resonance images by making use of the similarity of image patches to achieve lower reconstruction error and higher visual quality than conventional CS-MRI methods.
A novel method and fast algorithm for MR image reconstruction with significantly under-sampled data
The aim of this work is to improve the accuracy, robustness and efficiency of the compressed sensing reconstruction technique in magnetic resonance imaging. We propose a novel variational model
Dictionary Learning and Time Sparsity for Dynamic MR Data Reconstruction
TLDR
An iterative algorithm is presented that enables the application of DL for the reconstruction of cardiac cine data with Cartesian undersampling and is compared to and shown to systematically outperform k- t FOCUSS, a successful CS method that uses a fixed basis transform.
Iterative thresholding compressed sensing MRI based on contourlet transform
Reducing the acquisition time is important for clinical magnetic resonance imaging (MRI). Compressed sensing has recently emerged as a theoretical foundation for the reconstruction of magnetic
Accelerated Dynamic MRI Exploiting Sparsity and Low-Rank Structure: k-t SLR
TLDR
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.
Bayesian Nonparametric Dictionary Learning for Compressed Sensing MRI
TLDR
A Bayesian nonparametric model for reconstructing magnetic resonance images (MRIs) from highly undersampled \(k \) -space data is developed, and the proposed regularization framework can improve reconstruction accuracy over other methods.
...
1
2
3
4
5
...