MRI of Transcallosal White Matter Helps to Predict Motor Impairment in Multiple Sclerosis

Predicting multiple sclerosis disease progression and outcomes with machine learning and MRI-based biomarkers: a review

Multiple sclerosis (MS) is a demyelinating neurological disorder with a highly heterogeneous clinical presentation and course of progression. Disease-modifying therapies are the only available treatment, as there is no known cure for the disease. Careful selection of suitable therapies is necessary, as they can be accompanied by serious risks and adverse effects such as infection. Magnetic resonance imaging (MRI) plays a central role in the diagnosis and management of MS, though MRI lesions have displayed only moderate associations with MS clinical outcomes, known as the clinico-radiological paradox. With the advent of machine learning (ML) in healthcare, the predictive power of MRI can be improved by leveraging both traditional and advanced ML algorithms capable of analyzing increasingly complex patterns within neuroimaging data. The purpose of this review was to examine the application of MRI-based ML for prediction of MS disease progression. Studies were divided into five main categories: predicting the conversion of clinically isolated syndrome to MS, cognitive outcome, EDSS-related disability, motor disability and disease activity. The performance of ML models is discussed along with highlighting the influential MRI-derived biomarkers. Overall, MRI-based ML presents a promising avenue for MS prognosis. However, integration of imaging biomarkers with other multimodal patient data shows great potential for advancing personalized healthcare approaches in MS.

Network Analysis in Multiple Sclerosis and Related Disorders

Multiple sclerosis (MS) is a neuroinflammatory and neurodegenerative disease of the central nervous system, commonly featuring disability and cognitive impairment. The pathologic hallmark of MS lies in demyelination and hence impaired structural and functional neuronal pathways. Recent studies have shown that MS shows extensive structural disconnection of key network hub areas like the thalamus, combined with a functional network reorganization that can mostly be related to poorer clinical functioning. As MS can, therefore, be considered a network disorder, this review outlines recent innovations in the field of network neuroscience in MS.

Exploring subtypes of multiple sclerosis through unsupervised machine learning of automated fiber quantification

PURPOSE

This study aimed to subtype multiple sclerosis (MS) patients using unsupervised machine learning on white matter (WM) fiber tracts and investigate the implications for cognitive function and disability outcomes.

MATERIALS AND METHODS

We utilized the automated fiber quantification (AFQ) method to extract 18 WM fiber tracts from the imaging data of 103 MS patients in total. Unsupervised machine learning techniques were applied to conduct cluster analysis and identify distinct subtypes. Clinical and diffusion tensor imaging (DTI) metrics were compared among the subtypes, and survival analysis was conducted to examine disability progression and cognitive impairment.

RESULTS

The clustering analysis revealed three distinct subtypes with variations in fractional anisotropy (FA), mean diffusivity (MD), axial diffusivity (AD), and radial diffusivity (RD). Significant differences were observed in clinical and DTI metrics among the subtypes. Subtype 3 showed the fastest disability progression and cognitive decline, while Subtype 2 exhibited a slower rate, and Subtype 1 fell in between.

CONCLUSIONS

Subtyping MS based on WM fiber tracts using unsupervised machine learning identified distinct subtypes with significant cognitive and disability differences. WM abnormalities may serve as biomarkers for predicting disease outcomes, enabling personalized treatment strategies and prognostic predictions for MS patients.

Cognitive function in primary and secondary progressive multiple sclerosis: A multiparametric magnetic resonance imaging study

BACKGROUND AND PURPOSE

The differences in cognitive function between primary progressive and secondary progressive multiple sclerosis (MS) remain unclear. We compared cognitive performance between primary progressive multiple sclerosis (PPMS) and secondary progressive multiple sclerosis (SPMS), and explored the structural and functional magnetic resonance imaging (MRI) correlates of their cognitive functions.

METHODS

Seventy-five healthy controls and 183 MS patients (60 PPMS and 123 SPMS) underwent 3.0-T MRI. MS patients were administered the Brief Repeatable Battery of Neuropsychological Tests; cognitive domain z-scores were calculated and then averaged to obtain a measure of global cognition. Using hierarchical linear regression analysis, the contribution of lesion volumes, normalized brain volumes, white matter (WM) fractional anisotropy (FA) and mean diffusivity abnormalities, and resting state (RS) functional connectivity (FC) alterations to global cognition in PPMS and SPMS was investigated.

RESULTS

PPMS and SPMS had similar z-scores in all investigated cognitive domains. Poor global cognitive function was associated with decreased FA of the medial lemniscus (ΔR 2  = 0.11, p = 0.011) and lower normalized gray matter volume (ΔR 2  = 0.29, p < 0.001) in PPMS, and with decreased FA of the fornix (ΔR 2  = 0.35, p < 0.001) and lower normalized WM volume (ΔR 2  = 0.05; p = 0.034) in SPMS.

CONCLUSIONS

PPMS and SPMS had similar neuropsychological performance. Cognitive dysfunction in PPMS and SPMS was related to distinct patterns of structural MRI abnormalities and involvement of different WM tracts, whereas RS FC alterations did not contribute to explaining their global cognitive functioning.

Structural and functional magnetic resonance imaging correlates of fatigue and dual-task performance in progressive multiple sclerosis

BACKGROUND

Frontal cortico-subcortical dysfunction may contribute to fatigue and dual-task impairment of walking and cognition in progressive multiple sclerosis (PMS).

PURPOSE

To explore the associations among fatigue, dual-task performance and structural and functional abnormalities of frontal cortico-subcortical network in PMS.

METHODS

Brain 3 T structural and functional MRI sequences, Modified Fatigue Impact Scale (MFIS), dual-task motor and cognitive performances were obtained from 57 PMS patients and 10 healthy controls (HC). The associations of thalamic, caudate nucleus and dorsolateral prefrontal cortex (DLPFC) atrophy, microstructural abnormalities of their connections and their resting state effective connectivity (RS-EC) with fatigue and dual-task performance were investigated using random forest.

RESULTS

Thirty-seven PMS patients were fatigued (F) (MFIS ≥ 38). Compared to HC, non-fatigued (nF) and F-PMS patients had significantly worse dual-task performance (p ≤ 0.002). Predictors of fatigue (out-of-bag [OOB]-accuracy = 0.754) and its severity (OOB-R² = 0.247) were higher Expanded Disability Status scale (EDSS) score, lower RS-EC from left-caudate nucleus to left-DLPFC, lower fractional anisotropy between left-caudate nucleus and left-thalamus, higher mean diffusivity between right-caudate nucleus and right-thalamus, and longer disease duration. Microstructural abnormalities in connections among thalami, caudate nuclei and DLPFC, mainly left-lateralized in nF-PMS and more bilateral in F-PMS, higher RS-EC from left-DLPFC to right-DLPFC in nF-PMS and lower RS-EC from left-caudate nucleus to left-DLPFC in F-PMS, higher EDSS score, higher WM lesion volume, and lower cortical volume predicted worse dual-task performances (OOB-R² from 0.426 to 0.530).

CONCLUSIONS

In PMS, structural and functional frontal cortico-subcortical abnormalities contribute to fatigue and worse dual-task performance, with different patterns according to the presence of fatigue.