Baseline biomarkers of connectome disruption and atrophy predict future processing speed in early multiple sclerosis

An update on the role of magnetic resonance imaging in predicting and monitoring multiple sclerosis progression

INTRODUCTION

While magnetic resonance imaging (MRI) is established in diagnosing and monitoring disease activity in multiple sclerosis (MS), its utility in predicting and monitoring disease progression is less clear.

AREAS COVERED

The authors consider changing concepts in the phenotypic classification of MS, including progression independent of relapses; pathological processes underpinning progression; advances in MRI measures to assess them; how well MRI features explain and predict clinical outcomes, including models that assess disease effects on neural networks, and the potential role for machine learning.

EXPERT OPINION

Relapsing-remitting and progressive MS have evolved from being viewed as mutually exclusive to having considerable overlap. Progression is likely the consequence of several pathological elements, each important in building more holistic prognostic models beyond conventional phenotypes. MRI is well placed to assess pathogenic processes underpinning progression, but we need to bridge the gap between MRI measures and clinical outcomes. Mapping pathological effects on specific neural networks may help and machine learning methods may be able to optimize predictive markers while identifying new, or previously overlooked, clinically relevant features. The ever-increasing ability to measure features on MRI raises the dilemma of what to measure and when, and the challenge of translating research methods into clinically useable tools.

Basal Ganglia Atrophy and Impaired Cognitive Processing Speed in Multiple Sclerosis

Impaired cognitive processing speed is among the important higher brain dysfunctions in multiple sclerosis (MS). However, the exact structural mechanisms of the dysfunction remain uncertain. This study aimed to identify the brain regions associated with the impaired cognitive processing speed in MS by comparing the cognitive processing speed, measured using the Cognitive Processing Speed Test (CogEval) z-score, and brain regional volumetric data. Altogether, 80 patients with MS (64 with relapsing-remitting MS [RRMS] and 16 with secondary progressive MS [SPMS]) were enrolled. Consequently, CogEval z-scores were worse in patients with SPMS than in those with RRMS (p=0.001). In the univariate correlation analyses, significant correlations with CogEval z-score were suggested in the MS lesion volume (p<0.001; Spearman's rank correlation test) and atrophies in the cerebral cortex (p=0.031), cerebral white matter (p=0.013), corpus callosum (p=0.001), thalamus (p=0.001), and putamen (p<0.001). Multiple linear regression analysis revealed that putamen atrophy was significantly associated with CogEval z-score (p=0.038) independent of volume in other brain regions, while thalamic atrophy was not (p=0.79). Univariate correlation analyses were further performed in each of RRMS and SPMS. None of the evaluated volumetric data indicated a significant correlation with the CogEval z-score in RRMS. Meanwhile, atrophies in the cerebral white matter (p=0.008), corpus callosum (p=0.002), putamen (p=0.011), and pallidum (p=0.017) demonstrated significant correlations with CogEval z-score in SPMS. In summary, the putamen could be an important region of atrophy contributing to the impaired cognitive speed in MS, especially in the later disease stages after a transition to SPMS.

The sequence of regional structural disconnectivity due to multiple sclerosis lesions

Prediction of disease progression is challenging in multiple sclerosis as the sequence of lesion development and retention of inflammation within a subset of chronic lesions is heterogeneous among patients. We investigated the sequence of lesion-related regional structural disconnectivity across the spectrum of disability and cognitive impairment in multiple sclerosis. In a full cohort of 482 multiple sclerosis patients (age: 41.83 ± 11.63 years, 71.57% females), the Expanded Disability Status Scale was used to classify patients into (i) no or mild (Expanded Disability Status Scale <3) versus (ii) moderate or severe disability groups (Expanded Disability Status Scale ≥3). In 363 out of 482 patients, quantitative susceptibility mapping was used to identify paramagnetic rim lesions, which are maintained by a rim of iron-laden innate immune cells. In 171 out of 482 patients, Brief International Cognitive Assessment was used to identify subjects as being cognitively preserved or impaired. Network Modification Tool was used to estimate the regional structural disconnectivity due to multiple sclerosis lesions. Discriminative event-based modelling was applied to investigate the sequence of regional structural disconnectivity due to (i) all representative T2 fluid-attenuated inversion recovery lesions, (ii) paramagnetic rim lesions versus non-paramagnetic rim lesions separately across disability groups ('no to mild disability' to 'moderate to severe disability'), (iii) all representative T2 fluid-attenuated inversion recovery lesions and (iv) paramagnetic rim lesions versus non-paramagnetic rim lesions separately across cognitive status ('cognitively preserved' to 'cognitively impaired'). In the full cohort, structural disconnection in the ventral attention and subcortical networks, particularly in the supramarginal and putamen regions, was an early biomarker of moderate or severe disability. The earliest biomarkers of disability progression were structural disconnections due to paramagnetic rim lesions in the motor-related regions. Subcortical structural disconnection, particularly in the ventral diencephalon and thalamus regions, was an early biomarker of cognitive impairment. Our data-driven model revealed that the structural disconnection in the subcortical regions, particularly in the thalamus, is an early biomarker for both disability and cognitive impairment in multiple sclerosis. Paramagnetic rim lesions-related structural disconnection in the motor cortex may identify the patients at risk for moderate or severe disability in multiple sclerosis. Such information might be used to identify people with multiple sclerosis who have an increased risk of disability progression or cognitive decline in order to provide personalized treatment plans.

Mapping the Relationship of White Matter Lesions to Depression in Multiple Sclerosis

BACKGROUND

Multiple sclerosis (MS) is an immune-mediated neurological disorder, and up to 50% of patients experience depression. We investigated how white matter network disruption is related to depression in MS.

METHODS

Using electronic health records, 380 participants with MS were identified. Depressed individuals (MS+Depression group; n = 232) included persons who had an ICD-10 depression diagnosis, had a prescription for antidepressant medication, or screened positive via Patient Health Questionnaire (PHQ)-2 or PHQ-9. Age- and sex-matched nondepressed individuals with MS (MS-Depression group; n = 148) included persons who had no prior depression diagnosis, had no psychiatric medication prescriptions, and were asymptomatic on PHQ-2 or PHQ-9. Research-quality 3T structural magnetic resonance imaging was obtained as part of routine care. We first evaluated whether lesions were preferentially located within the depression network compared with other brain regions. Next, we examined if MS+Depression patients had greater lesion burden and if this was driven by lesions in the depression network. Primary outcome measures were the burden of lesions (e.g., impacted fascicles) within a network and across the brain.

RESULTS

MS lesions preferentially affected fascicles within versus outside the depression network (β = 0.09, 95% CI = 0.08 to 0.10, p < .001). MS+Depression patients had more lesion burden (β = 0.06, 95% CI = 0.01 to 0.10, p = .015); this was driven by lesions within the depression network (β = 0.02, 95% CI = 0.003 to 0.040, p = .020).

CONCLUSIONS

We demonstrated that lesion location and burden may contribute to depression comorbidity in MS. MS lesions disproportionately impacted fascicles in the depression network. MS+Depression patients had more disease than MS-Depression patients, which was driven by disease within the depression network. Future studies relating lesion location to personalized depression interventions are warranted.

Prognostic models for predicting clinical disease progression, worsening and activity in people with multiple sclerosis

BACKGROUND

Multiple sclerosis (MS) is a chronic inflammatory disease of the central nervous system that affects millions of people worldwide. The disease course varies greatly across individuals and many disease-modifying treatments with different safety and efficacy profiles have been developed recently. Prognostic models evaluated and shown to be valid in different settings have the potential to support people with MS and their physicians during the decision-making process for treatment or disease/life management, allow stratified and more precise interpretation of interventional trials, and provide insights into disease mechanisms. Many researchers have turned to prognostic models to help predict clinical outcomes in people with MS; however, to our knowledge, no widely accepted prognostic model for MS is being used in clinical practice yet.

OBJECTIVES

To identify and summarise multivariable prognostic models, and their validation studies for quantifying the risk of clinical disease progression, worsening, and activity in adults with MS.

SEARCH METHODS

We searched MEDLINE, Embase, and the Cochrane Database of Systematic Reviews from January 1996 until July 2021. We also screened the reference lists of included studies and relevant reviews, and references citing the included studies.

SELECTION CRITERIA

We included all statistically developed multivariable prognostic models aiming to predict clinical disease progression, worsening, and activity, as measured by disability, relapse, conversion to definite MS, conversion to progressive MS, or a composite of these in adult individuals with MS. We also included any studies evaluating the performance of (i.e. validating) these models. There were no restrictions based on language, data source, timing of prognostication, or timing of outcome.

DATA COLLECTION AND ANALYSIS

Pairs of review authors independently screened titles/abstracts and full texts, extracted data using a piloted form based on the Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies (CHARMS), assessed risk of bias using the Prediction Model Risk Of Bias Assessment Tool (PROBAST), and assessed reporting deficiencies based on the checklist items in Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD). The characteristics of the included models and their validations are described narratively. We planned to meta-analyse the discrimination and calibration of models with at least three external validations outside the model development study but no model met this criterion. We summarised between-study heterogeneity narratively but again could not perform the planned meta-regression.

MAIN RESULTS

We included 57 studies, from which we identified 75 model developments, 15 external validations corresponding to only 12 (16%) of the models, and six author-reported validations. Only two models were externally validated multiple times. None of the identified external validations were performed by researchers independent of those that developed the model. The outcome was related to disease progression in 39 (41%), relapses in 8 (8%), conversion to definite MS in 17 (18%), and conversion to progressive MS in 27 (28%) of the 96 models or validations. The disease and treatment-related characteristics of included participants, and definitions of considered predictors and outcome, were highly heterogeneous amongst the studies. Based on the publication year, we observed an increase in the percent of participants on treatment, diversification of the diagnostic criteria used, an increase in consideration of biomarkers or treatment as predictors, and increased use of machine learning methods over time. Usability and reproducibility All identified models contained at least one predictor requiring the skills of a medical specialist for measurement or assessment. Most of the models (44; 59%) contained predictors that require specialist equipment likely to be absent from primary care or standard hospital settings. Over half (52%) of the developed models were not accompanied by model coefficients, tools, or instructions, which hinders their application, independent validation or reproduction. The data used in model developments were made publicly available or reported to be available on request only in a few studies (two and six, respectively). Risk of bias We rated all but one of the model developments or validations as having high overall risk of bias. The main reason for this was the statistical methods used for the development or evaluation of prognostic models; we rated all but two of the included model developments or validations as having high risk of bias in the analysis domain. None of the model developments that were externally validated or these models' external validations had low risk of bias. There were concerns related to applicability of the models to our research question in over one-third (38%) of the models or their validations. Reporting deficiencies Reporting was poor overall and there was no observable increase in the quality of reporting over time. The items that were unclearly reported or not reported at all for most of the included models or validations were related to sample size justification, blinding of outcome assessors, details of the full model or how to obtain predictions from it, amount of missing data, and treatments received by the participants. Reporting of preferred model performance measures of discrimination and calibration was suboptimal.

AUTHORS' CONCLUSIONS

The current evidence is not sufficient for recommending the use of any of the published prognostic prediction models for people with MS in clinical routine today due to lack of independent external validations. The MS prognostic research community should adhere to the current reporting and methodological guidelines and conduct many more state-of-the-art external validation studies for the existing or newly developed models.

Mapping the relationship of white matter lesions to depression in multiple sclerosis

Importance

Multiple sclerosis (MS) is an immune-mediated neurological disorder that affects nearly one million people in the United States. Up to 50% of patients with MS experience depression.

Objective

To investigate how white matter network disruption is related to depression in MS.

Design

Retrospective case-control study of participants who received research-quality 3-tesla neuroimaging as part of MS clinical care from 2010-2018. Analyses were performed from May 1 to September 30, 2022.

Setting

Single-center academic medical specialty MS clinic.

Participants

Participants with MS were identified via the electronic health record (EHR). All participants were diagnosed by an MS specialist and completed research-quality MRI at 3T. After excluding participants with poor image quality, 783 were included. Inclusion in the depression group (MS+Depression) required either: 1) ICD-10 depression diagnosis (F32-F34.*); 2) prescription of antidepressant medication; or 3) screening positive via Patient Health Questionnaire-2 (PHQ-2) or -9 (PHQ-9). Age- and sex-matched nondepressed comparators (MS-Depression) included persons with no depression diagnosis, no psychiatric medications, and were asymptomatic on PHQ-2/9.

Exposure

Depression diagnosis.

Main Outcomes and Measures

We first evaluated if lesions were preferentially located within the depression network compared to other brain regions. Next, we examined if MS+Depression patients had greater lesion burden, and if this was driven by lesions specifically in the depression network. Outcome measures were the burden of lesions (e.g., impacted fascicles) within a network and across the brain. Secondary measures included between-diagnosis lesion burden, stratified by brain network. Linear mixed-effects models were employed.

Results

Three hundred-eighty participants met inclusion criteria, (232 MS+Depression: age[SD]=49[12], %females=86; 148 MS-Depression: age[SD]=47[13], %females=79). MS lesions preferentially affected fascicles within versus outside the depression network (β=0.09, 95% CI=0.08-0.10, P<0.001). MS+Depression had more white matter lesion burden (β=0.06, 95% CI=0.01-0.10, P=0.015); this was driven by lesions within the depression network (β=0.02, 95% CI 0.003-0.040, P=0.020).

Conclusions and Relevance

We provide new evidence supporting a relationship between white matter lesions and depression in MS. MS lesions disproportionately impacted fascicles in the depression network. MS+Depression had more disease than MS-Depression, which was driven by disease within the depression network. Future studies relating lesion location to personalized depression interventions are warranted.

The sequence of regional structural disconnectivity due to multiple sclerosis lesions

Objective

Prediction of disease progression is challenging in multiple sclerosis (MS) as the sequence of lesion development and retention of inflammation within a subset of chronic lesions is heterogeneous among patients. We investigated the sequence of lesion-related regional structural disconnectivity across the spectrum of disability and cognitive impairment in MS.

Methods

In a full cohort of 482 patients, the Expanded Disability Status Scale was used to classify patients into (i) no or mild vs (ii) moderate or severe disability groups. In 363 out of 482 patients, Quantitative Susceptibility Mapping was used to identify paramagnetic rim lesions (PRL), which are maintained by a rim of iron-laden innate immune cells. In 171 out of 482 patients, Brief International Cognitive Assessment was used to identify subjects with cognitive impairment. Network Modification Tool was used to estimate the regional structural disconnectivity due to MS lesions. Discriminative event-based modeling was applied to investigate the sequence of regional structural disconnectivity due to all representative lesions across the spectrum of disability and cognitive impairment.

Results

Structural disconnection in the ventral attention and subcortical networks was an early biomarker of moderate or severe disability. The earliest biomarkers of disability progression were structural disconnections due to PRL in the motor-related regions. Subcortical structural disconnection was an early biomarker of cognitive impairment.

Interpretation

MS lesion-related structural disconnections in the subcortex is an early biomarker for both disability and cognitive impairment in MS. PRL-related structural disconnection in the motor cortex may identify the patients at risk for moderate or severe disability in MS.

Classification of multiple sclerosis clinical profiles using machine learning and grey matter connectome

Purpose: The main goal of this study is to investigate the discrimination power of Grey Matter (GM) thickness connectome data between Multiple Sclerosis (MS) clinical profiles using statistical and Machine Learning (ML) methods.

Materials and Methods: A dataset composed of 90 MS patients acquired at the MS clinic of Lyon Neurological Hospital was used for the analysis. Four MS profiles were considered, corresponding to Clinical Isolated Syndrome (CIS), Relapsing-Remitting MS (RRMS), Secondary Progressive MS (SPMS), and Primary Progressive MS (PPMS). Each patient was classified in one of these profiles by our neurologist and underwent longitudinal MRI examinations including T1-weighted image acquisition at each examination, from which the GM tissue was segmented and the cortical GM thickness measured. Following the GM parcellation using two different atlases (FSAverage and Glasser 2016), the morphological connectome was built and six global metrics (Betweenness Centrality (BC), Assortativity (r), Transitivity (T), Efficiency (E_g), Modularity (Q) and Density (D)) were extracted. Based on their connectivity metrics, MS profiles were first statistically compared and second, classified using four different learning machines (Logistic Regression, Random Forest, Support Vector Machine and AdaBoost), combined in a higher level ensemble model by majority voting. Finally, the impact of the GM spatial resolution on the MS clinical profiles classification was analyzed.

Results: Using binary comparisons between the four MS clinical profiles, statistical differences and classification performances higher than 0.7 were observed. Good performances were obtained when comparing the two early clinical forms, RRMS and PPMS (F1 score of 0.86), and the two neurodegenerative profiles, PPMS and SPMS (F1 score of 0.72). When comparing the two atlases, slightly better performances were obtained with the Glasser 2016 atlas, especially between RRMS with PPMS (F1 score of 0.83), compared to the FSAverage atlas (F1 score of 0.69). Also, the thresholding value for graph binarization was investigated suggesting more informative graph properties in the percentile range between 0.6 and 0.8.

Conclusion: An automated pipeline was proposed for the classification of MS clinical profiles using six global graph metrics extracted from the GM morphological connectome of MS patients. This work demonstrated that GM morphological connectivity data could provide good classification performances by combining four simple ML models, without the cost of long and complex MR techniques, such as MR diffusion, and/or deep learning architectures.

Abnormal fractional Amplitude of Low-Frequency Fluctuation in chronic ketamine users

BACKGROUND

Ketamine has become a major substance of abuse worldwide. Nevertheless, The long-term effects of ketamine use on intrinsic spontaneous neural activity remain unknown.

OBJECTIVES

In the present study, rs-fMRI was used to explore whether chronic ketamine use changes the intrinsic spontaneous neural activity, and whether the intrinsic spontaneous neural activity changes in chronic ketamine users(CKUs) are associated with cognitive impairments observed in chronic ketamine users.

METHODS

28 CKUs and 30 healthy controls(HC) were enrolled. The fractional amplitude of low-frequency fluctuations (fALFF) was measured to evaluate the intrinsic spontaneous neural activity in multiple brain regions. Cognitive alterations were assessed using MATRICS Consensus Cognitive Battery (MCCB).

RESULTS

CKUs showed higher fALFF in the right parahippocampal gyrus(PHG), right anterior cingulate cortex(ACC), left cerebellar vermis, left posterior cingulate cortex(PCC), bilateral caudate, and lower fALFF in the right middle occipital gyrus(MOG), left cuneus, right precuneus. The fALFF in the right PHG, left cerebellar vermis, bilateral caudate, right ACC of CKUs presented a negative correlation with the average quantity of ketamine use/day(g) and estimated total ketamine consumption. The fALFF in left PCC had a negative correlation with the average quantity of ketamine use/day(g). Speed of processing on MCCB presented a negative correlation with the fALFF in the right MOG.

CONCLUSION

Our study found abnormal fALFF in multiple brain areas in CKUs, which indicated the changes of intrinsic spontaneous neural activity in multiple brain areas. The changes of fALFF were associated with the severity of ketamine use and cognitive impairment in CKUs.

Brain disconnectome mapping derived from white matter lesions and serum neurofilament light levels in multiple sclerosis: A longitudinal multicenter study

•

Individual disconnectome maps generated using a template of 7T MRI data.

•

Disconnectome maps conceptualize distal brain network aberrations.

•

Using lesions maps from our MS cohort, we produced individual disconnectome maps.

•

Serum neurofilament light levels were associated with disconnectome maps.

•

Voxel-wise analyses revealed interesting association with serum neurofilament light levels.

Background and Objectives

Connectivity-based approaches incorporating the distribution and magnitude of the extended brain network aberrations caused by lesions may offer higher sensitivity for axonal damage in patients with multiple sclerosis (MS) than conventional lesion characteristics. Using individual brain disconnectome mapping, we tested the longitudinal associations between putative imaging-based brain network aberrations and levels of serum neurofilament light chain (NfL) as a neuroaxonal injury biomarker.

Methods

MS patients (n = 312, mean age 42.9 years, 71 % female) and healthy controls (HC) (n = 59, mean age 39.9 years, 78 % female) were prospectively enrolled at four European MS centres, and reassessed after two years (MS, n = 242; HC, n = 30). Post-processing of 3 Tesla (3 T) MRI data was performed at one centre using a harmonized pipeline, and disconnectome maps were calculated using BCBtoolkit based on individual lesion maps. Global disconnectivity (GD) was defined as the average disconnectome probability in each patient’s white matter. Serum NfL concentrations were measured by single molecule array (Simoa). Robust linear mixed models (rLMM) with GD or T2-lesion volume (T2LV) as dependent variables, patient as a random factor, serum NfL, age, sex, timepoint for visit, diagnosis, treatment, and center as fixed factors were run.

Results

rLMM revealed significant associations between GD and serum NfL (t = 2.94, p = 0.003), age (t = 4.21, p = 2.5 × 10⁻⁵), and longitudinal changes in NfL (t = -2.29, p = 0.02), but not for sex (t = 0.63, p = 0.53) or treatments (t = 0.80–0.83, p = 0.41–0.42). Voxel-wise analyses revealed significant associations between dysconnectivity in cerebellar and brainstem regions and serum NfL (t = 7.03, p < 0.001).

Discussion

In our prospective multi-site MS cohort, rLMMs demonstrated that the extent of global and regional brain disconnectivity is sensitive to a systemic biomarker of axonal damage, serum NfL, in patients with MS. These findings provide a neuroaxonal correlate of advanced disconnectome mapping and provide a platform for further investigations of the functional and potential clinical relevance of brain disconnectome mapping in patients with brain disorders.

Time course of lesion-induced atrophy in multiple sclerosis

BACKGROUND AND PURPOSE

White matter (WM) tract disruption impacts volume loss in connected deep gray matter (DGM) over 5 years in people with multiple sclerosis (PwMS). However, the timeline of this phenomenon remains poorly characterized.

MATERIALS AND METHODS

Annual serial MRI for 181 PwMS was retrospectively analyzed from a 10-year clinical trial database. Annualized thalamic atrophy, DGM atrophy, and disruption of connected WM tracts were measured. For time series analysis, ~700 epochs were collated using a sliding 5-year window, and regression models predicting 1-year atrophy were applied to characterize the influence of new tract disruption from preceding years, while controlling for whole brain atrophy and other relevant factors.

RESULTS

Disruptions of WM tracts connected to the thalamus were significantly associated with thalamic atrophy 1 year later (β: 0.048-0.103). This effect was not observed for thalamic tract disruption concurrent with the time of atrophy nor for thalamic tract disruption preceding the atrophy by 2-4 years. Similarly, disruptions of white matter tracts connected to the DGM were significantly associated with DGM atrophy 1 year later (β: 0.078-0.111), but not for tract disruption concurrent with, nor preceding the atrophy by 2-4 years.

CONCLUSION

Increased rates of thalamic and DGM atrophy were restricted to 1 year following newly developed disruption in connected WM tracts. In research and clinical settings, additional gray matter atrophy may be expected 1 year following new lesion growth in connected white matter.

Disease correlates of rim lesions on quantitative susceptibility mapping in multiple sclerosis

Quantitative susceptibility mapping (QSM), an imaging technique sensitive to brain iron, has been used to detect paramagnetic rims of iron-laden active microglia and macrophages in a subset of multiple sclerosis (MS) lesions, known as rim+ lesions, that are consistent with chronic active lesions. Because of the potential impact of rim+ lesions on disease progression and tissue damage, investigating their influence on disability and neurodegeneration is critical to establish the impact of these lesions on the disease course. This study aimed to explore the relationship between chronic active rim+ lesions, identified as having a hyperintense rim on QSM, and both clinical disability and imaging measures of neurodegeneration in patients with MS. The patient cohort was composed of 159 relapsing-remitting multiple sclerosis patients. The Expanded Disability Status Scale (EDSS) and Brief International Cognitive Assessment for Multiple Sclerosis, which includes both the Symbol Digit Modalities Test and California Verbal Learning Test-II, were used to assess clinical disability. Cortical thickness and thalamic volume were evaluated as imaging measures of neurodegeneration. A total of 4469 MS lesions were identified, of which 171 QSM rim+ (3.8%) lesions were identified among 57 patients (35.8%). In a multivariate regression model, as the overall total lesion burden increased, patients with at least one rim+ lesion on QSM performed worse on both physical disability and cognitive assessments, specifically the Symbol Digit Modalities Test (p = 0.010), California Verbal Learning Test-II (p = 0.030), and EDSS (p = 0.001). In a separate univariate regression model, controlling for age (p < 0.001) and having at least one rim+ lesion was related to more cortical thinning (p = 0.03) in younger patients (< 45 years). Lower thalamic volume was associated with older patients (p = 0.038) and larger total lesion burden (p < 0.001); however, the association did not remain significant with rim+ lesions (p = 0.10). Our findings demonstrate a novel observation that chronic active lesions, as identified on QSM, modify the impact of lesion burden on clinical disability in MS patients. These results support further exploration of rim+ lesions for therapeutic targeting in MS to reduce disability and subsequent neurodegeneration.

Dynamic Functional Connectivity Better Predicts Disability Than Structural and Static Functional Connectivity in People With Multiple Sclerosis

Background: Advanced imaging techniques such as diffusion and functional MRI can be used to identify pathology-related changes to the brain's structural and functional connectivity (SC and FC) networks and mapping of these changes to disability and compensatory mechanisms in people with multiple sclerosis (pwMS). No study to date performed a comparison study to investigate which connectivity type (SC, static or dynamic FC) better distinguishes healthy controls (HC) from pwMS and/or classifies pwMS by disability status.

Aims: We aim to compare the performance of SC, static FC, and dynamic FC (dFC) in classifying (a) HC vs. pwMS and (b) pwMS who have no disability vs. with disability. The secondary objective of the study is to identify which brain regions' connectome measures contribute most to the classification tasks.

Materials and Methods: One hundred pwMS and 19 HC were included. Expanded Disability Status Scale (EDSS) was used to assess disability, where 67 pwMS who had EDSS<2 were considered as not having disability. Diffusion and resting-state functional MRI were used to compute the SC and FC matrices, respectively. Logistic regression with ridge regularization was performed, where the models included demographics/clinical information and either pairwise entries or regional summaries from one of the following matrices: SC, FC, and dFC. The performance of the models was assessed using the area under the receiver operating curve (AUC).

Results: In classifying HC vs. pwMS, the regional SC model significantly outperformed others with a median AUC of 0.89 (p <0.05). In classifying pwMS by disability status, the regional dFC and dFC metrics models significantly outperformed others with a median AUC of 0.65 and 0.61 (p < 0.05). Regional SC in the dorsal attention, subcortical and cerebellar networks were the most important variables in the HC vs. pwMS classification task. Increased regional dFC in dorsal attention and visual networks and decreased regional dFC in frontoparietal and cerebellar networks in certain dFC states was associated with being in the group of pwMS with evidence of disability.

Discussion: Damage to SCs is a hallmark of MS and, unsurprisingly, the most accurate connectomic measure in classifying patients and controls. On the other hand, dynamic FC metrics were most important for determining disability level in pwMS, and could represent functional compensation in response to white matter pathology in pwMS.

Towards Multimodal Machine Learning Prediction of Individual Cognitive Evolution in Multiple Sclerosis

Multiple sclerosis (MS) manifests heterogeneously among persons suffering from it, making its disease course highly challenging to predict. At present, prognosis mostly relies on biomarkers that are unable to predict disease course on an individual level. Machine learning is a promising technique, both in terms of its ability to combine multimodal data and through the capability of making personalized predictions. However, most investigations on machine learning for prognosis in MS were geared towards predicting physical deterioration, while cognitive deterioration, although prevalent and burdensome, remained largely overlooked. This review aims to boost the field of machine learning for cognitive prognosis in MS by means of an introduction to machine learning and its pitfalls, an overview of important elements for study design, and an overview of the current literature on cognitive prognosis in MS using machine learning. Furthermore, the review discusses new trends in the field of machine learning that might be adopted for future studies in the field.

Structural disconnectivity from paramagnetic rim lesions is related to disability in multiple sclerosis

BACKGROUND

In people with multiple sclerosis (pwMS), lesions with a hyperintense rim (rim+) on Quantitative Susceptibility Mapping (QSM) have been shown to have greater myelin damage compared to rim- lesions, but their association with disability has not yet been investigated. Furthermore, how QSM rim+ and rim- lesions differentially impact disability through their disruptions to structural connectivity has not been explored. We test the hypothesis that structural disconnectivity due to rim+ lesions is more predictive of disability compared to structural disconnectivity due to rim- lesions.

METHODS

Ninety-six pwMS were included in our study. Individuals with Expanded Disability Status Scale (EDSS) <2 were considered to have lower disability (n = 59). For each gray matter region, a Change in Connectivity (ChaCo) score, that is, the percent of connecting streamlines also passing through a rim- or rim+ lesion, was computed. Adaptive Boosting was used to classify the pwMS into lower versus greater disability groups based on ChaCo scores from rim+ and rim- lesions. Classification performance was assessed using the area under ROC curve (AUC).

RESULTS

The model based on ChaCo from rim+ lesions outperformed the model based on ChaCo from rim- lesions (AUC = 0.67 vs 0.63, p-value < .05). The left thalamus and left cerebellum were the most important regions in classifying pwMS into disability categories.

CONCLUSION

rim+ lesions may be more influential on disability through their disruptions to the structural connectome than rim- lesions. This study provides a deeper understanding of how rim+ lesion location/size and resulting disruption to the structural connectome can contribute to MS-related disability.

Gray matter atrophy in relapsing-remitting multiple sclerosis is associated with white matter lesions in connecting fibers

Background:

Lesions of brain white matter (WM) and atrophy of brain gray matter (GM) are well-established surrogate parameters in multiple sclerosis (MS), but it is unclear how closely these parameters relate to each other.

Objective:

To assess across the whole cerebrum whether GM atrophy can be explained by lesions in connecting WM tracts.

Methods:

GM images of 600 patients with relapsing-remitting MS (women = 68%; median age = 33.0 years, median expanded disability status scale score = 1.5) were converted to atrophy maps by data from a healthy control cohort. An atlas of WM tracts from the Human Connectome Project and individual lesion maps were merged to identify potentially disconnected GM regions, leading to individual disconnectome maps. Across the whole cerebrum, GM atrophy and potentially disconnected GM were tested for association both cross-sectionally and longitudinally.

Results:

We found highly significant correlations between disconnection and atrophy across most of the cerebrum. Longitudinal analysis demonstrated a close temporal relation of WM lesion formation and GM atrophy in connecting fibers.

Conclusion:

GM atrophy is associated with WM lesions in connecting fibers. Caution is warranted when interpreting group differences in GM atrophy exclusively as differences in early neurodegeneration independent of WM lesion formation.

Estimated connectivity networks outperform observed connectivity networks when classifying people with multiple sclerosis into disability groups

BACKGROUND

Multiple Sclerosis (MS), a neurodegenerative and neuroinflammatory disease, causing lesions that disrupt the brain's anatomical and physiological connectivity networks, resulting in cognitive, visual and/or motor disabilities. Advanced imaging techniques like diffusion and functional MRI allow measurement of the brain's structural connectivity (SC) and functional connectivity (FC) networks, and can enable a better understanding of how their disruptions cause disability in people with MS (pwMS). However, advanced MRI techniques are used mainly for research purposes as they are expensive, time-consuming and require high-level expertise to acquire and process. As an alternative, the Network Modification (NeMo) Tool can be used to estimate SC and FC using lesion masks derived from pwMS and a reference set of controls' connectivity networks.

OBJECTIVE

Here, we test the hypothesis that estimated SC and FC (eSC and eFC) from the NeMo Tool, based only on an individual's lesion masks, can be used to classify pwMS into disability categories just as well as SC and FC extracted from advanced MRI directly in pwMS. We also aim to find the connections most important for differentiating between no disability vs evidence of disability groups.

MATERIALS AND METHODS

One hundred pwMS (age:45.5 ± 11.4 years, 66% female, disease duration: 12.97 ± 8.07 years) were included in this study. Expanded Disability Status Scale (EDSS) was used to assess disability, 67 pwMS had no disability (EDSS < 2). Observed SC and FC were extracted from diffusion and functional MRI directly in pwMS, respectively. The NeMo Tool was used to estimate the remaining structural connectome (eSC), by removing streamlines in a reference set of tractograms that intersected the lesion mask. The NeMo Tool's eSC was used then as input to a deep neural network to estimate the corresponding FC (eFC). Logistic regression with ridge regularization was used to classify pwMS into disability categories (no disability vs evidence of disability), based on demographics/clinical information (sex, age, race, disease duration, clinical phenotype, and spinal lesion burden) and either pairwise entries or regional summaries from one of the following matrices: SC, FC, eSC, and eFC. The area under the ROC curve (AUC) was used to assess the classification performance. Both univariate statistics and parameter coefficients from the classification models were used to identify features important to differentiating between the groups.

RESULTS

The regional eSC and eFC models outperformed their observed FC and SC counterparts (p-value < 0.05), while the pairwise eSC and SC performed similarly (p = 0.10). Regional eSC and eFC models had higher AUC (0.66-0.68) than the pairwise models (0.60-0.65), with regional eFC having highest classification accuracy across all models. Ridge regression coefficients for the regional eFC and regional observed FC models were significantly correlated (Pearson's r = 0.52, p-value < 10e-7). Decreased estimated SC node strength in default mode and ventral attention networks and increased eFC node strength in visual networks was associated with evidence of disability.

DISCUSSION

Here, for the first time, we use clinically acquired lesion masks to estimate both structural and functional connectomes in patient populations to better understand brain lesion-dysfunction mapping in pwMS. Models based on the NeMo Tool's estimates of SC and FC better classified pwMS by disability level than SC and FC observed directly in the individual using advanced MRI. This work provides a viable alternative to performing high-cost, advanced MRI in patient populations, bringing the connectome one step closer to the clinic.

Correlations between hippocampal functional connectivity, structural changes, and clinical data in patients with relapsing-remitting multiple sclerosis: a case-control study using multimodal magnetic resonance imaging

Multiple sclerosis is associated with structural and functional brain alterations leading to cognitive impairments across multiple domains including attention, memory, and the speed of information processing. The hippocampus, which is a brain important structure involved in memory, undergoes microstructural changes in the early stage of multiple sclerosis. In this study, we analyzed hippocampal function and structure in patients with relapsing-remitting multiple sclerosis and explored correlations between the functional connectivity of the hippocampus to the whole brain, changes in local brain function and microstructure, and cognitive function at rest. We retrospectively analyzed data from 20 relapsing-remitting multiple sclerosis patients admitted to the Department of Neurology at the China-Japan Union Hospital of Jilin University, China, from April 2015 to November 2019. Sixteen healthy volunteers were recruited as the healthy control group. All participants were evaluated using a scale of extended disability status and the Montreal cognitive assessment within 1 week before and after head diffusion tensor imaging and functional magnetic resonance imaging. Compared with the healthy control group, the patients with relapsing-remitting multiple sclerosis had lower Montreal cognitive assessment scores and regions of simultaneously enhanced and attenuated whole-brain functional connectivity and local functional connectivity in the bilateral hippocampus. Hippocampal diffusion tensor imaging data showed that, compared with the healthy control group, patients with relapsing-remitting multiple sclerosis had lower hippocampal fractional anisotropy values and higher mean diffusivity values, suggesting abnormal hippocampal structure. The left hippocampus whole-brain functional connectivity was negatively correlated with the Montreal cognitive assessment score (r = −0.698, P = 0.025), and whole-brain functional connectivity of the right hippocampus was negatively correlated with extended disability status scale score (r = −0.649, P = 0.042). The mean diffusivity value of the left hippocampus was negatively correlated with the Montreal cognitive assessment score (r = −0.729, P = 0.017) and positively correlated with the extended disability status scale score (r = 0.653, P = 0.041). The right hippocampal mean diffusivity value was positively correlated with the extended disability status scale score (r = 0.684, P = 0.029). These data suggest that the functional connectivity and presence of structural abnormalities in the hippocampus in patients with relapse-remission multiple sclerosis are correlated with the degree of cognitive function and extent of disability. This study was approved by the Ethics Committee of China-Japan Union Hospital of Jilin University, China (approval No. 201702202) on February 22, 2017.

Neuroimaging-based Individualized Prediction of Cognition and Behavior for Mental Disorders and Health: Methods and Promises

The neuroimaging community has witnessed a paradigm shift in biomarker discovery from using traditional univariate brain mapping approaches to multivariate predictive models, allowing the field to move toward a translational neuroscience era. Regression-based multivariate models (hereafter "predictive modeling") provide a powerful and widely used approach to predict human behavior with neuroimaging features. These studies maintain a focus on decoding individual differences in a continuously behavioral phenotype from neuroimaging data, opening up an exciting opportunity to describe the human brain at the single-subject level. In this survey, we provide an overview of recent studies that utilize machine learning approaches to identify neuroimaging predictors over the past decade. We first review regression-based approaches and highlight connectome-based predictive modeling, which has grown in popularity in recent years. Next, we systematically describe recent representative studies using these tools in the context of cognitive function, symptom severity, personality traits, and emotion processing. Finally, we highlight a few challenges related to combining multimodal data, longitudinal prediction, external validations, and the employment of deep learning methods that have emerged from our review of the existing literature, as well as present some promising and challenging future directions.

Both Stationary and Dynamic Functional Interhemispheric Connectivity Are Strongly Associated With Performance on Cognitive Tests in Multiple Sclerosis

Although functional connectivity has been extensively studied in MS, robust estimates of both stationary (static connectivity at the time) and dynamic (connectivity variation across time) functional connectivity has not been commonly evaluated and neither has its association to cognition. In this study, we focused on interhemispheric connections as previous research has shown links between anatomical homologous connections and cognition. We examined functional interhemispheric connectivity (IC) in MS during resting-state functional MRI using both stationary and dynamic strategies and related connectivity measures to processing speed performance. Twenty-five patients with relapsing-remitting MS and 41 controls were recruited. Stationary functional IC was assessed between homologous Regions of Interest (ROIs) using correlation. For dynamic IC, a sliding window approach was used to quantify changes between homologous ROIs across time. We related IC measures to cognitive performance with correlation and regression. Compared to control subjects, MS demonstrated increased IC across homologous regions, which accurately predicted performance on the symbol digit modalities test (SDMT) (R ² = 0.96) and paced auditory serial addition test (PASAT) (R ² = 0.59). Dynamic measures were not different between the 2 groups, but dynamic IC was related to PASAT scores. The associations between stationary/dynamic connectivity and cognitive tests demonstrated that different aspects of functional IC were associated with cognitive processes. Processing speed measured in SDMT was associated with static interhemispheric connections and better PASAT performance, which requires working memory, sustain attention, and processing speed, was more related to rigid IC, underlining the neurophysiological mechanism of cognition in MS.

Structural brain networks and functional motor outcome after stroke-a prospective cohort study

The time course of topological reorganization that occurs in the structural connectome after an ischaemic stroke is currently not well understood. We aimed to determine the evolution of structural brain networks in stroke patients with motor deficits and relate changes in their global topology to residual symptom burden and functional impairment. In this prospective cohort study, ischaemic stroke patients with supratentorial infarcts and motor symptoms were assessed longitudinally by advanced diffusion MRI and detailed clinical testing of upper extremity motor function at four time points from the acute to the chronic stage. For each time point, structural connectomes were reconstructed, and whole-hemisphere global network topology was quantified in terms of integration and segregation parameters. Using non-linear joint mixed-effects regression modelling, network evolution was related to lesion volume and clinical outcome. Thirty patients were included for analysis. Graph-theoretical analysis demonstrated that, over time, brain networks became less integrated and more segregated with decreasing global efficiency and increasing modularity. Changes occurred in both stroke and intact hemispheres and, in the latter, were positively associated with lesion volume. Greater change in topology was associated with larger residual symptom burden and greater motor impairment 1, 3 and 12 months after stroke. After ischaemic stroke, brain networks underwent characteristic changes in both ipsi- and contralesional hemispheres. Topological network changes reflect the severity of damage to the structural network and are associated with functional outcome beyond the impact of lesion volume.

Partial Least Squares Regression Performs Well in MRI-Based Individualized Estimations

Estimation of individuals' cognitive, behavioral and demographic (CBD) variables based on MRI has attracted much research interest in the past decade, and effective machine learning techniques are of great importance for these estimations. Partial least squares regression (PLSR) is an attractive machine learning technique that can accommodate both single- and multi-label learning in a simple framework, while its potential for MRI-based estimations of CBD variables remains to be explored. In this study, we systemically investigated the performance of PLSR in MRI-based estimations of individuals' CBD variables, especially its performance in simultaneous estimation of multiple CBD variables (multi-label learning). We performed the study on the dataset included in the HCP S1200 release. Resting state functional connections (RSFCs) were used as features, and a total of 10 CBD variables (e.g., age, gender, grip strength, and picture vocabulary) were estimated. The results showed that PLSR performed well in both single- and multi-label learning. In fact, the present estimations were better than those reported in literatures, as indicated by stronger correlations between the estimated and actual CBD variables, as well as high gender classification accuracy (97.8% in this study). Moreover, the RSFCs that contributed to the estimations exhibited strong correlations with the CBD variable estimated, that is, PLSR algorithm automatically selected the RSFCs closely related to one CBD variable to establish predictive models for the variable. Besides, the estimation accuracies based on RSFCs among 100, 200, and 300 regions of interest (ROIs) were higher than those based on RSFCs among 15, 25, and 50 ROIs; the estimation accuracies based on RSFCs evaluated using partial correlation were higher than those based on RSFCs evaluated using full correlation. In addition to the aforementioned virtues, PLSR is efficient in model training and testing, and it is simple and easy to use. Therefore, PLSR can be a favorable choice for future MRI-based estimations of CBD variables.

The impact of white matter hyperintensities on the structural connectome in late-life depression: Relationship to executive functions

BACKGROUND

White matter hyperintensities (WMH) represent ischemic white matter damage in late-life depression (LLD) and are associated with cognitive control dysfunction. Understanding the impact of WMH on the structural connectivity of gray matter and the cognitive control correlates of WMH-related structural dysconnectivity can provide insight into the pathophysiology of LLD.

METHODS

We compared WMH burden and performance on clinical measures of cognitive control in patients with LLD (N = 44) and a control group of non-depressed older adults (N = 59). We used the Network Modification (NeMo) Tool to investigate the impact of WMH on structural dysconnectivity in specific gray matter regions, and how such connectivity was related to cognitive control functions.

RESULTS

Compared to the control group, LLD participants had greater WMH burden, poorer performance on Trail Making Test (TMT) A & B, and greater self-reported dysexecutive behavior on the Frosntal Systems Behavior Scale-Executive Function subscale (FrSBe-EF). Within the LLD group, disrupted connectivity in the left supramarginal gyrus, paracentral lobule, thalamus, and pallidum was associated with psychomotor slowing (TMT-A). Altered connectivity in the left supramarginal gyrus, paracentral lobule, precentral gyrus, postcentral gyrus, thalamus, and pallidum was associated with poor attentional set-shifting (TMT-B). A follow-up analysis that isolated set-shifting ability (TMT-B/A ratio) confirmed the association with dysconnectivity in the bilateral paracentral lobule, right thalamus, left precentral gyrus, postcentral gyrus, and pallidum; additionally, it revealed associations with dysconnectivity in the right posterior cingulate, and left anterior cingulate, middle frontal cortex, and putamen.

CONCLUSIONS

In LLD, WMH are associated with region-specific disruptions in cortical and subcortical gray matter areas involved in attentional aspects of cognitive control systems and sensorimotor processing, which in turn are associated with slower processing speed, and reduced attentional set-shifting.

CLINICAL TRIALS REGISTRATION

https://clinicaltrials.gov/ct2/show/NCT01728194.