A Plug-and-Play Approach to Multiparametric Quantitative MRI: Image Reconstruction using Pre-Trained Deep Denoisers

TL;DR

This paper introduces a flexible, plug-and-play deep learning method for MRI reconstruction that adapts to different acquisition patterns using a pre-trained denoiser, enabling robust quantitative imaging without retraining for each pattern.

Contribution

It proposes an iterative MRI reconstruction framework utilizing a pre-trained CNN denoiser as a universal prior, adaptable to various acquisition schemes without retraining.

Findings

Consistent de-aliasing across different subsampling patterns

Accurate quantitative tissue property mapping

Robustness to unknown or changing acquisition processes

Abstract

Current spatiotemporal deep learning approaches to Magnetic Resonance Fingerprinting (MRF) build artefact-removal models customised to a particular k-space subsampling pattern which is used for fast (compressed) acquisition. This may not be useful when the acquisition process is unknown during training of the deep learning model and/or changes during testing time. This paper proposes an iterative deep learning plug-and-play reconstruction approach to MRF which is adaptive to the forward acquisition process. Spatiotemporal image priors are learned by an image denoiser i.e. a Convolutional Neural Network (CNN), trained to remove generic white gaussian noise (not a particular subsampling artefact) from data. This CNN denoiser is then used as a data-driven shrinkage operator within the iterative reconstruction algorithm. This algorithm with the same denoiser model is then tested on two simulated acquisition processes with distinct subsampling patterns. The results show consistent de-aliasing performance against both acquisition schemes and accurate mapping of tissues' quantitative bio-properties. Software available: https://github.com/ketanfatania/QMRI-PnP-Recon-POC