A plug-and-play synthetic data deep learning for undersampled magnetic resonance image reconstruction

TL;DR

This paper introduces a versatile deep learning approach for undersampled MRI reconstruction that adapts to various sampling patterns using a plug-and-play denoiser, improving robustness and efficiency.

Contribution

It presents a novel plug-and-play deep denoising method that generalizes across different MRI undersampling scenarios without retraining.

Findings

Robust reconstruction across multiple undersampling patterns.

Improved image quality both visually and quantitatively.

Flexible adaptation to different sampling rates.

Abstract

Magnetic resonance imaging (MRI) plays an important role in modern medical diagnostic but suffers from prolonged scan time. Current deep learning methods for undersampled MRI reconstruction exhibit good performance in image de-aliasing which can be tailored to the specific k-space undersampling scenario. But it is very troublesome to configure different deep networks when the sampling setting changes. In this work, we propose a deep plug-and-play method for undersampled MRI reconstruction, which effectively adapts to different sampling settings. Specifically, the image de-aliasing prior is first learned by a deep denoiser trained to remove general white Gaussian noise from synthetic data. Then the learned deep denoiser is plugged into an iterative algorithm for image reconstruction. Results on in vivo data demonstrate that the proposed method provides nice and robust accelerated image reconstruction performance under different undersampling patterns and sampling rates, both visually and quantitatively.