Increased brain atrophy and lesion load is associated with stronger lower alpha MEG power in multiple sclerosis patients

Radial diffusivity reflects general decline rather than specific cognitive deterioration in multiple sclerosis

Advanced structural brain imaging techniques, such as diffusion tensor imaging (DTI), have been used to study the relationship between DTI-parameters and cognitive scores in multiple sclerosis (MS). In this study, we assessed cognitive function in 61 individuals with MS and a control group of 35 healthy individuals with the Symbol Digit Modalities Test, the California Verbal Learning Test-II, the Brief Visuospatial Memory Test-Revised, the Controlled Oral Word Association Test, and Stroop-test. We also acquired diffusion-weighted images (b = 1000; 32 directions), which were processed to obtain the following DTI scalars: fractional anisotropy, mean, axial, and radial diffusivity. The relation between DTI scalars and cognitive parameters was assessed through permutations. Although fractional anisotropy and axial diffusivity did not correlate with any of the cognitive tests, mean and radial diffusivity were negatively correlated with all of these tests. However, this effect was not specific to any specific white matter tract or cognitive test and demonstrated a general effect with only low to moderate individual voxel-based correlations of <0.6. Similarly, lesion and white matter volume show a general effect with medium to high voxel-based correlations of 0.5-0.8. In conclusion, radial diffusivity is strongly related to cognitive impairment in MS. However, the strong associations of radial diffusivity with both cognition and whole brain lesion volume suggest that it is a surrogate marker for general decline in MS, rather than a marker for specific cognitive functions.

The utility of Magnetoencephalography in multiple sclerosis - A systematic review

•

We conducted a Systematic Review of studies, looking at 30 studies from 13 centres.

•

MS patients had reduced power in some induced responses (motor beta, visual gamma).

•

Increased latency and reduced connectivity were seen for somatosensory evoked fields.

•

There was an association between upper alpha connectivity and cognitive function.

•

MEG shows promise, although work is too preliminary to recommend current clinical use.

Introduction

Magnetoencephalography (MEG), allows for a high degree temporal and spatial accuracy in recording cortical oscillatory activity and evoked fields. To date, no review has been undertaken to synthesise all MEG studies in Multiple Sclerosis (MS). We undertook a Systematic Review of the utility of MEG in MS.

Methods

We identified MEG studies carried out in MS using EMBASE, Medline, Cochrane, TRIP and Psychinfo databases. We included original research articles with a cohort of minimum of five multiple sclerosis patients and quantifying of at least one MEG parameter. We used a modified version of the JBI (mJBI) for case-control studies to assess for risk of bias.

Results

We identified 30 studies from 13 centres involving at least 433 MS patients and 347 controls. We found evidence that MEG shows perturbed activity (most commonly reduced power modulations), reduced connectivity and association with altered clinical function in Multiple Sclerosis. Specific replicated findings were decreased motor induced responses in the beta band, diminished increase of gamma power after visual stimulation, increased latency and reduced connectivity for somatosensory evoked fields. There was an association between upper alpha connectivity and cognitive measures in people with MS. Overall studies were of moderate quality (mean mJBI score 6.7).

Discussion

We find evidence for the utility of MEG in Multiple Sclerosis. Event-related designs are of particular value and show replicability between centres. At this stage, it is not clear whether these changes are specific to Multiple Sclerosis or are also observable in other diseases. Further studies should look to explore cognitive control in more depth using in-task designs and undertake longitudinal studies to determine whether these changes have prognostic value.

Applications of deep learning techniques for automated multiple sclerosis detection using magnetic resonance imaging: A review

Multiple Sclerosis (MS) is a type of brain disease which causes visual, sensory, and motor problems for people with a detrimental effect on the functioning of the nervous system. In order to diagnose MS, multiple screening methods have been proposed so far; among them, magnetic resonance imaging (MRI) has received considerable attention among physicians. MRI modalities provide physicians with fundamental information about the structure and function of the brain, which is crucial for the rapid diagnosis of MS lesions. Diagnosing MS using MRI is time-consuming, tedious, and prone to manual errors. Research on the implementation of computer aided diagnosis system (CADS) based on artificial intelligence (AI) to diagnose MS involves conventional machine learning and deep learning (DL) methods. In conventional machine learning, feature extraction, feature selection, and classification steps are carried out by using trial and error; on the contrary, these steps in DL are based on deep layers whose values are automatically learn. In this paper, a complete review of automated MS diagnosis methods performed using DL techniques with MRI neuroimaging modalities is provided. Initially, the steps involved in various CADS proposed using MRI modalities and DL techniques for MS diagnosis are investigated. The important preprocessing techniques employed in various works are analyzed. Most of the published papers on MS diagnosis using MRI modalities and DL are presented. The most significant challenges facing and future direction of automated diagnosis of MS using MRI modalities and DL techniques are also provided.