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

TL;DR

This paper introduces D-VDAMP, a novel algorithm combining CNN-based denoising with VDAMP for improved MRI reconstruction, effectively handling colored Gaussian noise in iterative image reconstruction.

Contribution

It proposes a new denoising CNN architecture integrated with VDAMP, specifically designed for colored Gaussian noise, enhancing MRI image reconstruction quality.

Findings

D-VDAMP outperforms existing MRI reconstruction methods.

The CNN effectively removes colored Gaussian noise.

The approach improves convergence and image quality in compressive MRI.

Abstract

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 and combine it with the recently proposed VDAMP algorithm, whose effective noise follows a predictable colored Gaussian distribution. We apply the resulting denoising-based VDAMP (D-VDAMP) algorithm to variable density sampled compressive MRI where it substantially outperforms existing techniques.