Bayesian Nonparametric Dictionary Learning for Compressed Sensing MRI

  title={Bayesian Nonparametric Dictionary Learning for Compressed Sensing MRI},
  author={Yue Huang and John William Paisley and Qin Lin and Xinghao Ding and Xueyang Fu and Xiao-Ping Zhang},
  journal={IEEE Transactions on Image Processing},
We develop a Bayesian nonparametric model for reconstructing magnetic resonance images (MRIs) from highly undersampled \(k \) -space data. We perform dictionary learning as part of the image reconstruction process. To this end, we use the beta process as a nonparametric dictionary learning prior for representing an image patch as a sparse combination of dictionary elements. The size of the dictionary and patch-specific sparsity pattern are inferred from the data, in addition to other dictionary… 
Application of dictionary learning in compressed sensing of data in MRI
  • Himanshu Padole, S. Joshi
  • Computer Science
    2017 International Conference on Circuits, Controls, and Communications (CCUBE)
  • 2017
A general framework for the adaptive learning of the sparsifying transform (dictionary) and reconstruction of the MR image from undersampled k-space data simultaneously is proposed and an efficient algorithm to solve the corresponding optimization problem is proposed.
Orthogonal tensor dictionary learning for accelerated dynamic MRI
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.
Compressed sensing magnetic resonance imaging based on dictionary updating and block-matching and three-dimensional filtering regularisation
The proposed block-matching and three-dimensional (3D) filtering regularisation is incorporated into the authors’ image CS recovery, which can combine the self-similarities within the image, the 3D transform sparsity and the local sparsity into image recovery process.
Scalable Bayesian nonparametric dictionary learning
A stochastic EM algorithm for scalable dictionary learning with the beta-Bernoulli process, a Bayesian nonpara-metric prior that learns the dictionary size in addition to the sparse coding of each signal to provide a new way for doing inference in nonparametric dictionary learning models.
Bayesian K-SVD Using Fast Variational Inference
A fully-automated Bayesian method is proposed that considers the uncertainty of the estimates and produces a sparse representation of the data without prior information on the number of non-zeros in each representation vector and develops an efficient variational inference framework that reduces computational complexity.
Dictionary learning for data recovery in positron emission tomography
The proposed CS with DL is a good approach to recover partially sampled PET data and has implications toward reducing scanner cost while maintaining accurate PET image quantification.
Low-Rank and Adaptive Sparse Signal (LASSI) Models for Highly Accelerated Dynamic Imaging
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 is investigated.
Convex optimization and greedy iterative algorithms for dictionary learning in the presence of Rician noise
An attempt is being made to bring out a sparse coding technique which can provide better reconstruction in the presence of Rician noise, and results show that greedy algorithms achieve higher PSNR and have very high computational speed compared to convex techniques when the MR images are corrupted with Rician Noise.


MR Image Reconstruction From Highly Undersampled k-Space Data by Dictionary Learning
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.
Nonparametric Bayesian Dictionary Learning for Analysis of Noisy and Incomplete Images
Nonparametric Bayesian methods are considered for recovery of imagery based upon compressive, incomplete, and/or noisy measurements and significant improvements in image recovery are manifested using learned dictionaries, relative to using standard orthonormal image expansions.
An efficient algorithm for compressed MR imaging using total variation and wavelets
This work proposes an efficient algorithm that jointly minimizes the lscr1 norm, total variation, and a least squares measure, one of the most powerful models for compressive MR imaging, based upon an iterative operator-splitting framework.
Sparse MRI: The application of compressed sensing for rapid MR imaging
Practical incoherent undersampling schemes are developed and analyzed by means of their aliasing interference and demonstrate improved spatial resolution and accelerated acquisition for multislice fast spin‐echo brain imaging and 3D contrast enhanced angiography.
Iterative thresholding compressed sensing MRI based on contourlet transform
Simulation results demonstrate that contourlet-based CS-MRI can better reconstruct the curves and edges than traditional wavelet- based methods, especially at low k-space sampling rate.
Image Denoising Via Sparse and Redundant Representations Over Learned Dictionaries
This work addresses the image denoising problem, where zero-mean white and homogeneous Gaussian additive noise is to be removed from a given image, and uses the K-SVD algorithm to obtain a dictionary that describes the image content effectively.
Image Sequence Denoising via Sparse and Redundant Representations
This paper generalizes the above algorithm by offering several extensions: i) the atoms used are 3-D; ii) the dictionary is propagated from one frame to the next, reducing the number of required iterations; and iii) averaging is done on patches in both spatial and temporal neighboring locations.
Undersampled MRI reconstruction with patch-based directional wavelets.
Bayesian Robust Principal Component Analysis
The Bayesian framework infers an approximate representation for the noise statistics while simultaneously inferring the low-rank and sparse-outlier contributions; the model is robust to a broad range of noise levels, without having to change model hyperparameter settings.
K-SVD : An Algorithm for Designing of Overcomplete Dictionaries for Sparse Representation
A novel algorithm for adapting dictionaries in order to achieve sparse signal representations, K-SVD, an iterative method that alternates between sparse coding of the examples based on the current dictionary, and a process of updating the dictionary atoms to better fit the data.