Clinical use of H1 MR spectroscopy in assessment of relapsing remitting and secondary progressive multiple sclerosis

Differentiation of relapsing-remitting and secondary progressive multiple sclerosis: a magnetic resonance spectroscopy study based on machine learning

INTRODUCTION

Magnetic resonance imaging (MRI) is the most important tool for diagnosis and follow-up in multiple sclerosis (MS). The discrimination of relapsing-remitting MS (RRMS) from secondary progressive MS (SPMS) is clinically difficult, and developing the proposal presented in this study would contribute to the process.

OBJECTIVE

This study aimed to ensure the automatic classification of healthy controls, RRMS, and SPMS by using MR spectroscopy and machine learning methods.

METHODS

MR spectroscopy (MRS) was performed on a total of 91 participants, distributed into healthy controls (n=30), RRMS (n=36), and SPMS (n=25). Firstly, MRS metabolites were identified using signal processing techniques. Secondly, feature extraction was performed based on MRS Spectra. N-acetylaspartate (NAA) was the most significant metabolite in differentiating MS types. Lastly, binary classifications (healthy controls-RRMS and RRMS-SPMS) were carried out according to features obtained by the Support Vector Machine algorithm.

RESULTS

RRMS cases were differentiated from healthy controls with 85% accuracy, 90.91% sensitivity, and 77.78% specificity. RRMS and SPMS were classified with 83.33% accuracy, 81.81% sensitivity, and 85.71% specificity.

CONCLUSIONS

A combined analysis of MRS and computer-aided diagnosis may be useful as a complementary imaging technique to determine MS types.

Monitoring interferon β treatment response with magnetic resonance spectroscopy in relapsing remitting multiple sclerosis

The aim of this study is to compare the white matter of multiple sclerosis (MS) patients with healthy controls and to monitor the response to the treatment with magnetic resonance spectroscopy (MRS).Fifteen healthy controls and 36 recently diagnosed MS patients never treated with interferon β were included in this study. In the patient group, MRS was performed before treatment, at 6th and 12th month after the initiation of treatment and once in control group. Patient group was divided into 3 interferon groups randomly. Physical examination findings were recorded as Expanded Disability Status Scale scores before treatment, at 6th and 12th month of interferon treatment.At the end of 1 year follow up, 26 of 36 patients completed the study. In patients' white matter lesions, N-acetylaspartate/creatine (NAA/Cr) ratios were lower than control group's white matters. NAA/Cr ratios were higher in control group's white matter than patient's normal appearing white matter but this difference was not statistically significant. There was no difference in choline/creatine (Cho/Cr) ratios between 2 groups. In follow-up period, NAA/Cr and Cho/Cr ratios obtained from patients' white matter lesions and normal appearing white matter did not change statistically.This study showed that in MS patients' white matters, especially in white matter lesions, neuron viability is reduced compared with healthy controls' normal white matter; and in the patients treated with interferon β NAA/Cr ratios remained stable. These stable levels of metabolite ratios in the patients who received interferon β therapy can be explained with either the shortness of the follow-up period post-treatment or may reflect a positive effect of the beta interferon therapy on the progress of MS.

Quantification of diagnostic biomarkers to detect multiple sclerosis lesions employing (1)H-MRSI at 3T

Proton magnetic resonance spectroscopic imaging ((1)H-MRSI) enables the quantification of metabolite concentration ratios in the brain. The major purpose of the current work is to characterize NAA/Cho, NAA/Cr and Myo/Cr in multiple sclerosis (MS) patients, and to estimate their reproducibility in healthy controls. Twelve MS patients and five healthy volunteers were imaged using (1)H-MRSI at 3T. Eddy current correction was performed using a single-voxel non-water suppressed acquisition on an external water phantom. Time-domain quantification was carried out using subtract-QUEST technique, and based on an optimal simulated metabolite database. Reproducibility was evaluated on the same quantified ratios in five normal subjects. An optimal database was created for the quantification of the MRSI data, consisting of choline (Cho), creatine (Cr), N-acetyl aspartate (NAA), lactate (Lac), lipids, myo-inositol (Myo) and glutamine + glutamate (Glx). Decreasing of NAA/Cr and NAA/Cho ratios, as well as an increase in Myo/Cr ratio were observed for MS patients in comparison with control group. Reproducibility of NAA/Cr, NAA/Cho and Myo/Cr in control group was 0.98, 0.87 and 0.64, respectively, expressed as the squared correlation coefficient R (2) between duplicate experiments. We showed that MRSI alongside the time-domain quantification of spectral ratios offers a sensitive and reproducible framework to differentiate MS patients from normals.