Denoising Generalized Expectation-Consistent Approximation for MRI Image Recovery

by   Saurav K. Shastri, et al.

To solve inverse problems, plug-and-play (PnP) methods have been developed that replace the proximal step in a convex optimization algorithm with a call to an application-specific denoiser, often implemented using a deep neural network (DNN). Although such methods have been successful, they can be improved. For example, denoisers are usually designed/trained to remove white Gaussian noise, but the denoiser input error in PnP algorithms is usually far from white or Gaussian. Approximate message passing (AMP) methods provide white and Gaussian denoiser input error, but only when the forward operator is a large random matrix. In this work, for Fourier-based forward operators, we propose a PnP algorithm based on generalized expectation-consistent (GEC) approximation – a close cousin of AMP – that offers predictable error statistics at each iteration, as well as a new DNN denoiser that leverages those statistics. We apply our approach to magnetic resonance imaging (MRI) image recovery and demonstrate its advantages over existing PnP and AMP methods.


page 4

page 11

page 16

page 18

page 22

page 25


Expectation Consistent Plug-and-Play for MRI

For image recovery problems, plug-and-play (PnP) methods have been devel...

MRI Image Recovery using Damped Denoising Vector AMP

Motivated by image recovery in magnetic resonance imaging (MRI), we prop...

Plug and play methods for magnetic resonance imaging

Magnetic Resonance Imaging (MRI) is a non-invasive diagnostic tool that ...

Autotuning Plug-and-Play Algorithms for MRI

For magnetic resonance imaging (MRI), recently proposed "plug-and-play" ...

Poisson Inverse Problems by the Plug-and-Play scheme

The Anscombe transform offers an approximate conversion of a Poisson ran...

Image reconstruction algorithms in radio interferometry: from handcrafted to learned denoisers

We introduce a new class of iterative image reconstruction algorithms fo...

On 1-Laplacian Elliptic Equations Modeling Magnetic Resonance Image Rician Denoising

Modeling magnitude Magnetic Resonance Images (MRI) rician denoising in a...