D-VDAMP: Denoising-Based Approximate Message Passing for Compressive MRI

@article{Metzler2021DVDAMPDA,
  title={D-VDAMP: Denoising-Based Approximate Message Passing for Compressive MRI},
  author={Christopher A. Metzler and Gordon Wetzstein},
  journal={ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  year={2021},
  pages={1410-1414}
}
  • Christopher A. Metzler, G. Wetzstein
  • Published 25 October 2020
  • Computer Science
  • ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Plug and play (P&P) algorithms iteratively apply highly optimized image denoisers to impose priors and solve computational image reconstruction problems, to great effect. However, in general the "effective noise", that is the difference between the true signal and the intermediate solution, within the iterations of P&P algorithms is neither Gaussian nor white. This fact makes existing denoising algorithms suboptimal.In this work, we propose a CNN architecture for removing colored Gaussian noise… 

Figures and Tables from this paper

Expectation Consistent Plug-and-Play for MRI
TLDR
A PnP method using the expectation consistent (EC) approximation algorithm, a generalization of AMP, that offers predictable error statistics at each iteration, from which a deep-net denoiser can be effectively trained.
TFPnP: Tuning-free Plug-and-Play Proximal Algorithm with Applications to Inverse Imaging Problems
TLDR
This work presents a tuning-free PnP proximal algorithm, which can automatically determine the internal parameters including the penalty parameter, the denoising strength and the termination time, and develops a policy network for automatic search of parameters.
Tuning-free multi-coil compressed sensing MRI with Parallel Variable Density Approximate Message Passing (P-VDAMP)
TLDR
The proposed Parallel VDAMP (P-VDAMP) algorithm is found to have a similar reconstruction quality and time to convergence as FISTA with an optimally tuned sparse weighting and offers substantial robustness and reconstruction quality improvements over competing tuning-free methods.
Suremap: Predicting Uncertainty in Cnn-Based Image Reconstructions Using Stein’s Unbiased Risk Estimate
TLDR
Stein’s unbiased risk estimate (SURE) is used to develop per-pixel confidence intervals, in the form of heatmaps, for compressive sensing reconstruction using the approximate message passing (AMP) framework with CNN-based denoisers, which could greatly improve the utility of CNNs in various computational imaging applications.

References

SHOWING 1-10 OF 31 REFERENCES
Denoising AMP for MRI Reconstruction: BM3D-AMP-MRI
TLDR
This work utilizes Block Matching 3D (BM3D) as the denoiser of choice for the introduced MRI reconstruction algorithm and extends the Denoising Approximate Message Passing (D-AMP) algorithm from this list to the magnetic resonance imaging (MRI) reconstruction problem.
Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
TLDR
This paper investigates the construction of feed-forward denoising convolutional neural networks (DnCNNs) to embrace the progress in very deep architecture, learning algorithm, and regularization method into image Denoising, and uses residual learning and batch normalization to speed up the training process as well as boost theDenoising performance.
Learned D-AMP: Principled Neural Network based Compressive Image Recovery
TLDR
The LDAMP network is easy to train, can be applied to a variety of different measurement matrices, and comes with a state-evolution heuristic that accurately predicts its performance, which outperforms the state-of-the-art BM3D-AMP and NLR-CS algorithms in terms of both accuracy and run time.
Deep ADMM-Net for Compressive Sensing MRI
TLDR
Experiments on MRI image reconstruction under different sampling ratios in k-space demonstrate that the proposed novel ADMM-Net algorithm significantly improves the baseline ADMM algorithm and achieves high reconstruction accuracies with fast computational speed.
Plug-and-Play priors for model based reconstruction
TLDR
This paper demonstrates with some simple examples how Plug-and-Play priors can be used to mix and match a wide variety of existing denoising models with a tomographic forward model, thus greatly expanding the range of possible problem solutions.
The Little Engine That Could: Regularization by Denoising (RED)
TLDR
This paper provides an alternative, more powerful, and more flexible framework for achieving Regularization by Denoising (RED): using the denoising engine in defining the regulariza...
From Denoising to Compressed Sensing
TLDR
An extension of the approximate message passing (AMP) framework is developed, called denoising-based AMP (D-AMP), that can integrate a wide class of denoisers within its iterations, and demonstrates that, when used with a high-performance denoiser for natural images, D-AMP offers the state-of-the-art CS recovery performance while operating tens of times faster than competing methods.
Non-local Methods with Shape-Adaptive Patches (NLM-SAP)
TLDR
This paper provides a fast algorithm to compute the NL-Means with arbitrary shapes thanks to the Fast Fourier Transform and considers local combinations of the estimators associated with various shapes by using Stein’s Unbiased Risk Estimate (SURE).
Sparse MRI: The application of compressed sensing for rapid MR imaging
TLDR
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.
Image Denoising by Sparse 3-D Transform-Domain Collaborative Filtering
TLDR
An algorithm based on an enhanced sparse representation in transform domain based on a specially developed collaborative Wiener filtering achieves state-of-the-art denoising performance in terms of both peak signal-to-noise ratio and subjective visual quality.
...
1
2
3
4
...