Myelin Measurement Using Quantitative Magnetic Resonance Imaging: A Correlation Study Comparing Various Imaging Techniques in Patients with Multiple Sclerosis

Abstract

Evaluation of myelin by magnetic resonance imaging (MRI) is a difficult challenge, but holds promise in demyelinating diseases, such as multiple sclerosis (MS). Although multiple techniques have been developed, no gold standard has been established. This study aims to evaluate the correlation between synthetic MRI myelin volume fraction (SyMRI_MVF) and myelin fraction estimated by other techniques, i.e., magnetization transfer saturation (MTsat), T1-weighted images divided by T2-weighted images (T1w/T2w), and radial diffusivity (RD) in patients with MS. We also compared the sensitivities of these techniques for detecting MS-related myelin damage. SyMRI_MVF, MTsat, T1w/T2w, and RD were averaged on plaque, periplaque white matter, and normal-appearing white matter (NAWM). Pairwise correlation was calculated using Spearman's correlation analysis. For all segmented regions, strong correlations were found between SyMRI_MVF and T1w/T2w (Rho = 0.89), MTsat (Rho = 0.82), or RD (Rho = -0.75). For each technique, the average estimated myelin differed significantly among regions, but the percentage change of NAWM from both periplaque white matter and plaque were highest in SyMRI_MVF. SyMRI_MVF might be suitable for myelin evaluation in MS patients, with relevant results as compared to other well-studied techniques. Moreover, it presented better sensitivity for the detection of the difference between plaque or periplaque white matter and NAWM.

Keywords: multiple sclerosis; myelin; synthetic magnetic resonance imaging.

Figure 1

Synthetic T2-weighted images (A) were used for semi-automated segmentation of plaque (red), periplaque (orange), and contralateral normal-appearing white matter (green) (B). Regions-of-interest were copied and pasted onto SyMRI_MVF (C), T1w/T2w (D), MTsat (E), and RD (F) maps.

Figure 2

Estimation of myelin with 4 different techniques (SyMRI_MVF, MTsat, T1w/T2w, and RD). Each technique can differentiate plaque, periplaque, and NAWM regions. These metrics were the lowest in plaque for SyMRI_MVF, MTsat, and T1w/T2w and the highest in plaque for RD. *** p < 0.001.

Figure 3

Percentage changes in the metrics (SyMRI_MVF, T1w/T2w, MTsat, and RD) for plaque and periplaque compared to NAWM regions. SyMRI_MVF showed the highest contrast between NAWM and both plaque and periplaque regions. * p < 0.05. ** p < 0.01. *** p < 0.001.

Figure 4

Scatterplots of SyMRI_MVF, MTsat, T1w/T2w, and RD, plotted by subgroup of segmented regions-of-interest: black square = plaque, red triangle = periplaque, green circle = NAWM. Plot concentration ellipses are also drawn, with concentration levels of 0.5.