Is your system calibrated? MRI gradient system calibration for pre-clinical, high-resolution imaging.

James O’Callaghan,Jack Wells,Holly Holmes,Simon Richardson,Yichao Yu,Simon Walker-Samuel,Bernard Siow,Mark F Lythgoe,Paula A Da Costa Martins

doi:10.1371/journal.pone.0096568

Abstract

High-field, pre-clinical MRI systems are widely used to characterise tissue structure and volume in small animals, using high resolution imaging. Both applications rely heavily on the consistent, accurate calibration of imaging gradients, yet such calibrations are typically only performed during maintenance sessions by equipment manufacturers, and potentially with acceptance limits that are inadequate for phenotyping. To overcome this difficulty, we present a protocol for gradient calibration quality assurance testing, based on a 3D-printed, open source, structural phantom that can be customised to the dimensions of individual scanners and RF coils. In trials on a 9.4 T system, the gradient scaling errors were reduced by an order of magnitude, and displacements of greater than 100 µm, caused by gradient non-linearity, were corrected using a post-processing technique. The step-by-step protocol can be integrated into routine pre-clinical MRI quality assurance to measure and correct for these errors. We suggest that this type of quality assurance is essential for robust pre-clinical MRI experiments that rely on accurate imaging gradients, including small animal phenotyping and diffusion MR.

Highlights

Pre-clinical, high-field MRI systems are widely used to provide high-resolution images of animal models of human disease
Imaging gradients are assumed to be spatially linear, and complex image distortions can be introduced by gradient nonlinearity, which rapidly manifest with increasing distance from the magnet isocentre
We introduce the protocol and evaluate to what extent it can improve the accuracy of imaging gradients, compared with the values derived from the standard calibration procedure performed by the scanner manufacturer

Summary

Introduction

Pre-clinical, high-field MRI systems are widely used to provide high-resolution images of animal models of human disease Such phenotyping studies have enhanced our understanding of numerous disease processes and, when used in combination with advanced computational methods, have been used to detect subtle differences in tissue structure, in the brain [1]. Distances between structures are measured on a single slice of an MRI image of the phantom and compared to those of the original CAD design. This approach is highly vulnerable to error due to operator variability, the small number of measurements taken and the large slice thickness (1 mm) used. Acceptance limits specified (#5% linearity over a 40 mm diameter of spherical imaging volume (DSV)) are potentially unsuited to the degree of accuracy required for phenotyping studies

Methods

Results

Conclusion