Diffusion tensor imaging (DTI) is an effective means of quantifying parameters of demyelination and axonal loss. The application of DTI in Multiple Sclerosis (MS) has yielded noteworthy results. DTI abnormalities, which are already detectable in patients with clinically isolated syndrome (CIS), become more pronounced as disease duration and neurological impairment increase. The assessment of the microstructural alterations of white and grey matter in MS may shed light on mechanisms responsible for irreversible disability accumulation. In this paper, we examine the DTI analysis methods, the results obtained in the various tissues of the central nervous system, and correlations with clinical features and other MRI parameters. The adoption of DTI metrics to assess the outcome of prognostic measures may represent an extremely important step forward in the MS research field.

Brain functional connectivity (FC) is defined as the coherence in the activity between cerebral areas under a task or in the resting-state (RS). By applying functional magnetic resonance imaging (fMRI), RS FC shows several patterns which define RS brain networks (RSNs) involved in specific functions, because brain function is known to depend not only on the activity within individual regions, but also on the functional interaction of different areas across the whole brain. Region-of-interest analysis and independent component analysis are the two most commonly applied methods for RS investigation. Multiple sclerosis (MS) is characterized by multiple lesions mainly affecting the white matter, determining both structural and functional disconnection between various areas of the central nervous system. The study of RS FC in MS is mainly aimed at understanding alterations in the intrinsic functional architecture of the brain and their role in disease progression and clinical impairment. In this paper, we will examine the results obtained by the application of RS fMRI in different multiple sclerosis (MS) phenotypes and the correlations of FC changes with clinical features in this pathology. The knowledge of RS FC changes may represent a substantial step forward in the MS research field, both for clinical and therapeutic purposes.

Objectives: To evaluate the accuracy of a data-driven approach, such as machine learning classification, in predicting disability progression in MS.Methods: We analyzed structural brain images of 163 subjects diagnosed with MS acquired at two different sites. Participants were followed up for 2–6 years, with disability progression defined according to the expanded disability status scale (EDSS) increment at follow-up. T2-weighted lesion load (T2LL), thalamic and cerebellar gray matter (GM) volumes, fractional anisotropy of the normal appearing white matter were calculated at baseline and included in supervised machine learning classifiers. Age, sex, phenotype, EDSS at baseline, therapy and time to follow-up period were also included. Classes were labeled as stable or progressed disability. Participants were randomly chosen from both sites to build a sample including 50% patients showing disability progression and 50% patients being stable. One-thousand machine learning classifiers were applied to the resulting sample, and after testing for overfitting, classifier confusion matrix, relative metrics and feature importance were evaluated.Results: At follow-up, 36% of participants showed disability progression. The classifier with the highest resulting metrics had accuracy of 0.79, area under the true positive versus false positive rates curve of 0.81, sensitivity of 0.90 and specificity of 0.71. T2LL, thalamic volume, disability at baseline and administered therapy were identified as important features in predicting disability progression. Classifiers built on radiological features had higher accuracy than those built on clinical features.Conclusions: Disability progression in MS may be predicted via machine learning classifiers, mostly evaluating neuroradiological features.

Background and Objectives Neuroimaging studies suggest that changes in the cerebellar-basal ganglia-thalamo-cortical sensorimotor circuit are a pathophysiologic feature of focal dystonia. However, it remains unclear whether structural and functional alterations vary in different forms of focal dystonia. Thus, in patients with cervical dystonia (CD) and blepharospasm (BSP), we aimed to investigate structural damage and resting-state functional alterations using whole-brain and seed-based approaches to test the hypothesis of possible functional connectivity (FC) alterations in specific circuits, including the cerebellum, basal ganglia, and cerebral cortex, in the context of preserved global FC. Methods In this cross-sectional study, we applied a multimodal 3T MRI protocol, including 3-dimensional T1-weighted images to extract brain volumes and cortical thickness, and fMRI at rest to study FC of the dentate nucleus and globus pallidus with a seed-based approach and whole-brain FC with a graph theory approach. Results This study included 33 patients (17 with CD [14 female] age 55.7 ± 10.1 years, 16 with BSP [11 female] age 62.9 ± 8.8 years) and 16 age- and sex-matched healthy controls (HC) (7 female) 54.3 ± 14.3 years if age. Patients with CD, patients with BSP, and HC did not differ in terms of cortical or subcortical volume. Compared to HC, both patients with CD and patients with BSP had a loss of dentate FC anticorrelation with the sensorimotor cortex. Patients with CD and those with BSP showed increased pallidal FC with the cerebellum, supplementary motor area, and prefrontal cortices with respect to HC. Increased dentate FC with the cerebellum and thalamus and increased pallidal FC with the bilateral thalamus, sensorimotor and temporo-occipital cortices, and right putamen were present in patients with CD but not patients with BSP compared to HC. Measures of global FC, that is, global efficiency and small-worldness, did not differ between patients and HC. Discussion Both patients with CD and those with BSP showed altered dentate and pallidal FC with regions belonging to the integrated cerebellar-basal ganglia-thalamo-cortical sensorimotor circuit, supporting the concept that focal dystonia is a disorder of specific networks and not merely a result of basal ganglia alterations in the context of a preserved whole-brain functional architecture. Differences in functional interplay among specific brain structures may distinguish CD and BSP.

BACKGROUND AND PURPOSE: Conventional MR imaging explains only a fraction of the clinical outcome variance in multiple sclerosis. We aimed to evaluate machine learning models for disability prediction on the basis of radiomic, volumetric, and connectivity features derived from routine brain MR images. MATERIALS AND METHODS: In this retrospective cross-sectional study, 3T brain MR imaging studies of patients with multiple sclerosis, including 3D T1-weighted and T2-weighted FLAIR sequences, were selected from 2 institutions. T1-weighted images were processed to obtain volume, connectivity score (inferred from the T2 lesion location), and texture features for an atlas-based set of GM regions. The site 1 cohort was randomly split into training (n = 400) and test (n = 100) sets, while the site 2 cohort (n = 104) constituted the external test set. After feature selection of clinicodemographic and MR imaging–derived variables, different machine learning algorithms predicting disability as measured with the Expanded Disability Status Scale were trained and cross-validated on the training cohort and evaluated on the test sets. The effect of different algorithms on model performance was tested using the 1-way repeated-measures ANOVA. RESULTS: The selection procedure identified the 9 most informative variables, including age and secondary-progressive course and a subset of radiomic features extracted from the prefrontal cortex, subcortical GM, and cerebellum. The machine learning models predicted disability with high accuracy (r approaching 0.80) and excellent intra- and intersite generalizability (r ≥ 0.73). The machine learning algorithm had no relevant effect on the performance. CONCLUSIONS: The multidimensional analysis of brain MR images, including radiomic features and clinicodemographic data, is highly informative of the clinical status of patients with multiple sclerosis, representing a promising approach to bridge the gap between conventional imaging and disability.