Optshrink LR + S: accelerated fMRI reconstruction using non-convex optimal singular value shrinkage

Aggarwal, Priya; Shrivastava, Parth; Kabra, Tanay; Gupta, Anubha

doi:10.1007/s40708-016-0059-x

Cited by 12 publications

(16 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Radial sampling patterns are used to undersample available k-space data as used in [34,24,25]. These patterns represent different sampling masks used for one brain slice of size n x × n y at one time point with zeros at non-sampled locations and ones at sampled locations.…”

Section: Retrospective Undersamplingmentioning

confidence: 99%

“…In general, it is assumed that the data is sparse in some transform domain and that the chosen samples are incoherent [15]. Compressive sensing framework helps in fMRI reconstruction in two significant ways: 1) It helps in increasing the statistical power of the BOLD signal [16,19] because of its inherent denoising property and 2) it provides improvement in the spatiotemporal resolution of fMRI data [17,21,13,22,14,18,20,15,24,25].…”

Section: Introductionmentioning

confidence: 99%

“…Various CS based reconstruction methods have been proposed so far for accelerated fMRI reconstruction [13,14,15,16,17,18,19,20,21,22,25,24]. These methods can be largely divided into two categories.…”

Section: Introductionmentioning

confidence: 99%

“…These methods reconstruct brain volume at time t using the volume at time t − 1 by assuming causality in the reconstruction framework. Second category includes offline methods that first store k -space data of all fMRI volumes and later, utilize this complete information across both time and space, also called k-t space data, to reconstruct fMRI data [18,19,20,21,22,25,24].…”

Section: Introductionmentioning

confidence: 99%

“…In another work [22,24], fMRI reconstruction is performed using low-rank plus sparse (LR+S) decomposition of fMRI signals. Here, an iterative framework is used that reconstructs the low rank and the sparse components of fMRI data separately.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Double temporal sparsity based accelerated reconstruction of compressively sensed resting-state fMRI

Aggarwal

Gupta

2017

Computers in Biology and Medicine

Self Cite

View full text Add to dashboard Cite

A number of reconstruction methods have been proposed recently for accelerated functional Magnetic Resonance Imaging (fMRI) data collection. However, existing methods suffer with the challenge of greater artifacts at high acceleration factors. This paper addresses the issue of accelerating fMRI collection via undersampled k -space measurements combined with the proposed Double Temporal Sparsity based Reconstruction (DTSR) method with the l 1 − l 1 norm constraint. The robustness of the proposed DTSR method has been thoroughly evaluated both at the subject level and at the group level on real fMRI data. Results are presented at various acceleration factors. Quantitative analysis in terms of Peak Signal-to-Noise Ratio (PSNR) and other metrics, and qualitative analysis in terms of reproducibility of brain Resting State Networks (RSNs) demonstrate that the proposed method is accurate and robust. In addition, the proposed DTSR method preserves brain networks that are important for studying fMRI data. Compared to the existing accelerated fMRI reconstruction methods, the DTSR method shows promising potential with an improvement of 10-12dB in PSNR with acceleration factors upto 3.5. Simulation results on real data demonstrate that DTSR method can be used to acquire accelerated fMRI with accurate detection of RSNs.

show abstract

Section: Retrospective Undersamplingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Double temporal sparsity based accelerated reconstruction of compressively sensed resting-state fMRI

Aggarwal

Gupta

2017

Computers in Biology and Medicine

Self Cite

View full text Add to dashboard Cite

show abstract

PEAR: PEriodic And fixed Rank separation for fast fMRI

et al. 2017

View full text Add to dashboard Cite

PurposeIn functional MRI (fMRI), faster acquisition via undersampling of data can improve the spatial‐temporal resolution trade‐off and increase statistical robustness through increased degrees‐of‐freedom. High‐quality reconstruction of fMRI data from undersampled measurements requires proper modeling of the data. We present an fMRI reconstruction approach based on modeling the fMRI signal as a sum of periodic and fixed rank components, for improved reconstruction from undersampled measurements.MethodsThe proposed approach decomposes the fMRI signal into a component which has a fixed rank and a component consisting of a sum of periodic signals which is sparse in the temporal Fourier domain. Data reconstruction is performed by solving a constrained problem that enforces a fixed, moderate rank on one of the components, and a limited number of temporal frequencies on the other. Our approach is coined PEAR ‐ PEriodic And fixed Rank separation for fast fMRI.ResultsExperimental results include purely synthetic simulation, a simulation with real timecourses and retrospective undersampling of a real fMRI dataset. Evaluation was performed both quantitatively and visually versus ground truth, comparing PEAR to two additional recent methods for fMRI reconstruction from undersampled measurements. Results demonstrate PEAR's improvement in estimating the timecourses and activation maps versus the methods compared against at acceleration ratios of R = 8,10.66 (for simulated data) and R = 6.66,10 (for real data).ConclusionsThis paper presents PEAR, an undersampled fMRI reconstruction approach based on decomposing the fMRI signal to periodic and fixed rank components. PEAR results in reconstruction with higher fidelity than when using a fixed‐rank based model or a conventional Low‐rank + Sparse algorithm. We have shown that splitting the functional information between the components leads to better modeling of fMRI, over state‐of‐the‐art methods.

show abstract

Highlight removal for endoscopic images based on accelerated adaptive non-convex RPCA decomposition

Pan

Liu

et al. 2023

Computer Methods and Programs in Biomedicine

View full text Add to dashboard Cite

Optshrink LR + S: accelerated fMRI reconstruction using non-convex optimal singular value shrinkage

Cited by 12 publications

References 47 publications

Double temporal sparsity based accelerated reconstruction of compressively sensed resting-state fMRI

Double temporal sparsity based accelerated reconstruction of compressively sensed resting-state fMRI

PEAR: PEriodic And fixed Rank separation for fast fMRI

Highlight removal for endoscopic images based on accelerated adaptive non-convex RPCA decomposition

Contact Info

Product

Resources

About