Offset Sampling Improves Deep Learning based Accelerated MRI Reconstructions by Exploiting Symmetry

TL;DR

This paper demonstrates that carefully choosing offsets in k-space sampling enhances symmetry exploitation, leading to improved deep learning-based MRI reconstructions over traditional sampling methods.

Contribution

It introduces a novel offset sampling technique that leverages k-space symmetry to improve MRI reconstruction quality in deep learning models.

Findings

Offset sampling outperforms standard and randomized sampling methods.

Exploiting symmetry improves reconstruction quality.

Method enhances deep learning MRI reconstructions.

Abstract

Deep learning approaches to accelerated MRI take a matrix of sampled Fourier-space lines as input and produce a spatial image as output. In this work we show that by careful choice of the offset used in the sampling procedure, the symmetries in k-space can be better exploited, producing higher quality reconstructions than given by standard equally-spaced samples or randomized samples motivated by compressed sensing.