Deep MRI Reconstruction with Radial Subsampling

TL;DR

This paper compares the effects of rectilinear and radial subsampling in MRI data on deep learning reconstruction quality, finding radial subsampling yields higher fidelity images.

Contribution

It provides a comparative analysis of rectilinear versus radial subsampling in deep learning-based MRI reconstruction, highlighting the superior performance of radial subsampling.

Findings

Radial subsampling leads to higher reconstruction fidelity.

Deep neural networks perform better with radial subsampling.

Radial subsampling improves the robustness of MRI reconstructions.

Abstract

In spite of its extensive adaptation in almost every medical diagnostic and examinatorial application, Magnetic Resonance Imaging (MRI) is still a slow imaging modality which limits its use for dynamic imaging. In recent years, Parallel Imaging (PI) and Compressed Sensing (CS) have been utilised to accelerate the MRI acquisition. In clinical settings, subsampling the k-space measurements during scanning time using Cartesian trajectories, such as rectilinear sampling, is currently the most conventional CS approach applied which, however, is prone to producing aliased reconstructions. With the advent of the involvement of Deep Learning (DL) in accelerating the MRI, reconstructing faithful images from subsampled data became increasingly promising. Retrospectively applying a subsampling mask onto the k-space data is a way of simulating the accelerated acquisition of k-space data in real clinical setting. In this paper we compare and provide a review for the effect of applying either rectilinear or radial retrospective subsampling on the quality of the reconstructions outputted by trained deep neural networks. With the same choice of hyper-parameters, we train and evaluate two distinct Recurrent Inference Machines (RIMs), one for each type of subsampling. The qualitative and quantitative results of our experiments indicate that the model trained on data with radial subsampling attains higher performance and learns to estimate reconstructions with higher fidelity paving the way for other DL approaches to involve radial subsampling.