MRI Image Recovery using Damped Denoising Vector AMP

by   Subrata Sarkar, et al.

Motivated by image recovery in magnetic resonance imaging (MRI), we propose a new approach to solving linear inverse problems based on iteratively calling a deep neural-network, sometimes referred to as plug-and-play recovery. Our approach is based on the vector approximate message passing (VAMP) algorithm, which is known for mean-squared error (MSE)-optimal recovery under certain conditions. The forward operator in MRI, however, does not satisfy these conditions, and thus we design new damping and initialization schemes to help VAMP. The resulting DD-VAMP++ algorithm is shown to outperform existing algorithms in convergence speed and accuracy when recovering images from the fastMRI database for the practical case of Cartesian sampling.


page 1

page 4


Denoising Generalized Expectation-Consistent Approximation for MRI Image Recovery

To solve inverse problems, plug-and-play (PnP) methods have been develop...

Autotuning Plug-and-Play Algorithms for MRI

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

Sparse recovery based on the generalized error function

In this paper, we propose a novel sparse recovery method based on the ge...

Expectation Consistent Plug-and-Play for MRI

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

Performance Limits with Additive Error Metrics in Noisy Multi-Measurement Vector Problem

Real-world applications such as magnetic resonance imaging with multiple...

Sequential image recovery using joint hierarchical Bayesian learning

Recovering temporal image sequences (videos) based on indirect, noisy, o...

Plug-in Estimation in High-Dimensional Linear Inverse Problems: A Rigorous Analysis

Estimating a vector x from noisy linear measurements Ax+w often requires...