MRI Recovery with A Self-calibrated Denoiser

TL;DR

ReSiDe is a novel MRI reconstruction method that self-calibrates a denoiser from the image being reconstructed, eliminating the need for external training data and enabling progressive image refinement.

Contribution

It introduces a self-calibrated denoiser training approach integrated within a PnP framework for MRI recovery, removing the dependency on pre-trained denoisers.

Findings

ReSiDe outperforms traditional compressed sensing methods.

ReSiDe achieves comparable or better results than PnP with BM3D.

The method effectively refines images iteratively without external training data.

Abstract

Plug-and-play (PnP) methods that employ application-specific denoisers have been proposed to solve inverse problems, including MRI reconstruction. However, training application-specific denoisers is not feasible for many applications due to the lack of training data. In this work, we propose a PnP-inspired recovery method that does not require data beyond the single, incomplete set of measurements. The proposed method, called recovery with a self-calibrated denoiser (ReSiDe), trains the denoiser from the patches of the image being recovered. The denoiser training and a call to the denoising subroutine are performed in each iteration of a PnP algorithm, leading to a progressive refinement of the reconstructed image. For validation, we compare ReSiDe with a compressed sensing-based method and a PnP method with BM3D denoising using single-coil MRI brain data.