Magnetic resonance image reconstruction using trained geometric directions in 2D redundant wavelets domain and non-convex optimization

Ning, Bende; Qu, Xiaobo; Guo, Di; Hu, Changwei; Chen, Zhong

doi:10.1016/j.mri.2013.07.010

Cited by 67 publications

(71 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, some new transforms are desired to sparsely represent MR images. For example, adaptive transforms [19][20][21][22] or dictionaries [31][32][33][34][35] can improve the quality ing nor in realistic non-Cartesian sampling. Besides, there is still concern that the NUFFT or k-space re-gridding may affect the advantage of these patch-based images reconstruction.…”

Section: General Cs-mrimentioning

confidence: 99%

See 1 more Smart Citation

Patch-Based Directional Redundant Wavelets in Compressed Sensing Parallel Magnetic Resonance Imaging with Radial Sampling Trajectory

Ye¹,

Qu²,

Guo³

et al. 2016

j med imaging hlth inform

Self Cite

View full text Add to dashboard Cite

Compressed sensing has been shown promising to speed up magnetic resonance imaging, and its combination with partially parallel imaging can further accelerate the data acquisition. For compressed sensing, a sparser representation of an image usually leads to lower reconstruction errors. Recently, a patch-based directional wavelets (PBDW), providing an adaptive sparse representation of image patches with geometric information, has been proposed in compressed sensing MRI to improve the edge reconstruction. However, it is still unknown how to incorporate PBDW into partially parallel imaging. In this work, we propose to use patch-based directional redundant wavelets (PBDRW) as an adaptive sparsifying transform in compressed sensing sensitivity encoding, and wed the new method with radial sampling to achieve higher acceleration factors. Results from simulation and in vivo data indicate that PBDRW in sensitivity encoding achieves lower reconstruction errors and preserves more image details than traditional total variation and wavelets.

show abstract

Section: General Cs-mrimentioning

confidence: 99%

“…[16][17][18][19][20][21][22] This new technology is called CS-MRI for short. The CS-MRI tries to reconstruct the faithful magnetic resonance (MR) images from undersampled data, and consequently save the imaging time.…”

Section: Introductionmentioning

confidence: 99%

Patch-Based Directional Redundant Wavelets in Compressed Sensing Parallel Magnetic Resonance Imaging with Radial Sampling Trajectory

Ye¹,

Qu²,

Guo³

et al. 2016

j med imaging hlth inform

Self Cite

View full text Add to dashboard Cite

show abstract

“…Hao et al [15] suggested to use contourlet as a new sparse transform. Ning et al [31] suggested to use patch-based directional wavelets (PBDW) that trained geometric directions from undersampled data. PBDW had better performance in preserving image edges than conventional sparsifying transforms.…”

Section: Sparse Representationmentioning

confidence: 99%

Exponential Wavelet Iterative Shrinkage Thresholding Algorithm for compressed sensing magnetic resonance imaging

Zhang

Dong

Phillips

et al. 2015

Information Sciences

103

View full text Add to dashboard Cite

“…Sparsifying transforms that perform well in CS can be a wide variety from orthogonal to redundant to adaptive dictionaries, each with varying degrees of complexity and applicability. Ning et al investigate the patched-based trained directional wavelets and extend them into the translation invariant domain to enhance MRI image features [4]. Computationally, orthogonal transforms will operate faster than redundant or adaptive dictionaries which can add considerable time to CS simulations and reconstructions.…”

Section: Introductionmentioning

confidence: 99%

Comparison of MRI Under-Sampling Techniques for Compressed Sensing with Translation Invariant Wavelets Using FastTestCS: A Flexible Simulation Tool

Baker¹

2016

JSIP

View full text Add to dashboard Cite

A sparsifying transform for use in Compressed Sensing (CS) is a vital piece of image reconstruction for Magnetic Resonance Imaging (MRI). Previously, Translation Invariant Wavelet Transforms (TIWT) have been shown to perform exceedingly well in CS by reducing repetitive line pattern image artifacts that may be observed when using orthogonal wavelets. To further establish its validity as a good sparsifying transform, the TIWT is comprehensively investigated and compared with Total Variation (TV), using six under-sampling patterns through simulation. Both trajectory and random mask based under-sampling of MRI data are reconstructed to demonstrate a comprehensive coverage of tests. Notably, the TIWT in CS reconstruction performs well for all varieties of under-sampling patterns tested, even for cases where TV does not improve the mean squared error. This improved Image Quality (IQ) gives confidence in applying this transform to more CS applications which will contribute to an even greater speed-up of a CS MRI scan. High vs low resolution time of flight MRI CS reconstructions are also analyzed showing how partial Fourier acquisitions must be carefully addressed in CS to prevent loss of IQ. In the spirit of reproducible research, novel software is introduced here as FastTestCS. It is a helpful tool to quickly develop and perform tests with many CS customizations. Easy integration and testing for the TIWT and TV 1  minimization are exemplified. Simulations of 3D MRI datasets are shown to be efficiently distributed as a scalable solution for large studies. Comparisons in reconstruction computation time are made between the Wavelab toolbox and Gnu Scientific Library in FastTestCS that show a significant time savings factor of 60×. The addition of FastTestCS is proven to be a fast, flexible, portable and reproducible simulation aid for CS research.

show abstract

Magnetic resonance image reconstruction using trained geometric directions in 2D redundant wavelets domain and non-convex optimization

Cited by 67 publications

References 39 publications

Patch-Based Directional Redundant Wavelets in Compressed Sensing Parallel Magnetic Resonance Imaging with Radial Sampling Trajectory

Patch-Based Directional Redundant Wavelets in Compressed Sensing Parallel Magnetic Resonance Imaging with Radial Sampling Trajectory

Exponential Wavelet Iterative Shrinkage Thresholding Algorithm for compressed sensing magnetic resonance imaging

Comparison of MRI Under-Sampling Techniques for Compressed Sensing with Translation Invariant Wavelets Using FastTestCS: A Flexible Simulation Tool

Contact Info

Product

Resources

About