Gaussian process regression can turn non-uniform and undersampled diffusion MRI data into diffusion spectrum imaging

TL;DR

This paper introduces a Gaussian process regression method to reconstruct diffusion spectrum imaging from non-uniform, undersampled diffusion MRI data, enabling accurate EAP estimation with less data and acquisition time.

Contribution

The paper presents a novel Gaussian process regression approach for diffusion MRI that improves reconstruction accuracy and enables undersampling, outperforming linear interpolation.

Findings

Superior to linear interpolation in non-uniform data

Allows drastic undersampling with minor accuracy loss

Enables diffusion spectrum imaging with limited acquisition time

Abstract

We propose to use Gaussian process regression to accurately estimate the diffusion MRI signal at arbitrary locations in q-space. By estimating the signal on a grid, we can do synthetic diffusion spectrum imaging: reconstructing the ensemble averaged propagator (EAP) by an inverse Fourier transform. We also propose an alternative reconstruction method guaranteeing a nonnegative EAP that integrates to unity. The reconstruction is validated on data simulated from two Gaussians at various crossing angles. Moreover, we demonstrate on non-uniformly sampled in vivo data that the method is far superior to linear interpolation, and allows a drastic undersampling of the data with only a minor loss of accuracy. We envision the method as a potential replacement for standard diffusion spectrum imaging, in particular when acquistion time is limited.