Weekly follow up of acute lesions in three early multiple sclerosis patients using MR spectroscopy and diffusion.

OBJECT: Pathophysiological mechanisms underlying multiple sclerosis (MS) lesion formation, including inflammation, demyelination/remyelination and axonal damage, and their temporal evolution are still not clearly understood. To this end, three acute white matter lesions were monitored using a weekly multimodal magnetic resonance (MR) protocol. MATERIALS AND METHODS: Three untreated patients with early relapsing-remitting MS and one healthy control subject were followed weekly for two months. MR protocol included conventional MR imaging (MRI), diffusion tensor imaging (DTI), and localized MR spectroscopy (MRS), performed on the largest gadolinium-enhancing lesion, selected at the first exam. RESULTS: Mean diffusivity increased and fractional anisotropy decreased in lesions compared to healthy control. Cho/Cr ratios remained elevated in lesions throughout the follow-up. In contrast, temporal profiles of mI/Cr ratios varied between patients' lesions. For patient 1, mI/Cr ratios were already elevated at the beginning of the follow-up. Patients 2 and 3 ratios increase was delayed by two and five weeks. Blood-brain barrier (BBB) recovery occurred after three weeks. CONCLUSION: This multimodal MR follow-up highlighted the complementary role of DTI and MRS in identifying temporal relationships between BBB disruption, inflammation, and demyelination. Diffusion metrics showed high sensitivity to detect inflammatory processes. The different temporal profiles of mI suggested a potential better specificity to monitor pathological mechanisms occurring after lesion formation, such as glial proliferation and remyelination.

Ensemble Learning for Multiple Sclerosis Disability Estimation Using Brain Structural Connectivity.

Background: Multiple sclerosis (MS) is an autoimmune inflammatory disease of the central nervous system characterized by demyelination and neurodegeneration processes. It leads to different clinical courses and degrees of disability that need to be anticipated by the neurologist for personalized therapy. Recently, machine learning (ML) techniques have reached a high level of performance in brain disease diagnosis and/or prognosis, but the decision process of a trained ML system is typically nontransparent. Using brain structural connectivity data, a fully automatic ensemble learning model, augmented with an interpretable model, is proposed for the estimation of MS patients' disability, measured by the Expanded Disability Status Scale (EDSS). Materials and Methods: An ensemble of four boosting-based models (GBM, XGBoost, CatBoost, and LightBoost) organized following a stacking generalization scheme was developed using diffusion tensor imaging (DTI)-based structural connectivity data. In addition, an interpretable model based on conditional logistic regression was developed to explain the best performances in terms of white matter (WM) links for three classes of EDSS (low, medium, and high). Results: The ensemble model reached excellent level of performance (root mean squared error of 0.92 ± 0.28) compared with single-based models and provided a better EDSS estimation using DTI-based structural connectivity data compared with conventional magnetic resonance imaging measures associated with patient data (age, gender, and disease duration). Used for interpretation of the estimation process, the counterfactual method showed the importance of certain brain networks, corresponding mainly to left hemisphere WM links, connecting the left superior temporal with the left posterior cingulate and the right precuneus gray matter regions, and the interhemispheric WM links constituting the corpus callosum. Also, a better accuracy estimation was found for the high disability class. Conclusion: The combination of advanced ML models and sensitive techniques such as DTI-based structural connectivity demonstrated to be useful for the estimation of MS patients' disability and to point out the most important brain WM networks involved in disability. Impact statement An ensemble of "boosting" machine learning (ML) models was more performant than single models to estimate disability in multiple sclerosis. Diffusion tensor imaging (DTI)-based structural connectivity led to better performance than conventional magnetic resonance imaging. An interpretable model, based on counterfactual perturbation, highlighted the most relevant white matter fiber links for disability estimation. These findings demonstrated the clinical interest of combining DTI, graph modeling, and ML techniques.

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.

Case Report: True Motor Recovery of Upper Limb Beyond 5 Years Post-stroke.

Most of motor recovery usually occurs within the first 3 months after stroke. Herein is reported a remarkable late recovery of the right upper-limb motor function after a left middle cerebral artery stroke. This recovery happened progressively, from two to 12 years post-stroke onset, and along a proximo-distal gradient, including dissociated finger movements after 5 years. Standardized clinical assessment and quantified analysis of the reach-to-grasp movement were repeated over time to characterize the recovery. Twelve years after stroke onset, diffusion tensor imaging (DTI), functional magnetic resonance imaging (fMRI), and transcranial magnetic stimulation (TMS) analyses of the corticospinal tracts were carried out to investigate the plasticity mechanisms and efferent pathways underlying motor control of the paretic hand. Clinical evaluations and quantified movement analysis argue for a true neurological recovery rather than a compensation mechanism. DTI showed a significant decrease of fractional anisotropy, associated with a severe atrophy, only in the upper part of the left corticospinal tract (CST), suggesting an alteration of the CST at the level of the infarction that is not propagated downstream. The finger opposition movement of the right paretic hand was associated with fMRI activations of a broad network including predominantly the contralateral sensorimotor areas. Motor evoked potentials were normal and the selective stimulation of the right hemisphere did not elicit any response of the ipsilateral upper limb. These findings support the idea that the motor control of the paretic hand is mediated mainly by the contralateral sensorimotor cortex and the corresponding CST, but also by a plasticity of motor-related areas in both hemispheres. To our knowledge, this is the first report of a high quality upper-limb recovery occurring more than 2 years after stroke with a genuine insight of brain plasticity mechanisms.

Data augmentation using generative adversarial neural networks on brain structural connectivity in multiple sclerosis.

BACKGROUND AND OBJECTIVE: Machine learning frameworks have demonstrated their potentials in dealing with complex data structures, achieving remarkable results in many areas, including brain imaging. However, a large collection of data is needed to train these models. This is particularly challenging in the biomedical domain since, due to acquisition accessibility, costs and pathology related variability, available datasets are limited and usually imbalanced. To overcome this challenge, generative models can be used to generate new data. METHODS: In this study, a framework based on generative adversarial network is proposed to create synthetic structural brain networks in Multiple Sclerosis (MS). The dataset consists of 29 relapsing-remitting and 19 secondary-progressive MS patients. T1 and diffusion tensor imaging (DTI) acquisitions were used to obtain the structural brain network for each subject. Evaluation of the quality of newly generated brain networks is performed by (i) analysing their structural properties and (ii) studying their impact on classification performance. RESULTS: We demonstrate that advanced generative models could be directly applied to the structural brain networks. We quantitatively and qualitatively show that newly generated data do not present significant differences compared to the real ones. In addition, augmenting the existing dataset with generated samples leads to an improvement of the classification performance (F1score 81%) with respect to the baseline approach (F1score 66%). CONCLUSIONS: Our approach defines a new tool for biomedical application when connectome-based data augmentation is needed, providing a valid alternative to usual image-based data augmentation techniques.

Constrained Tensor Decomposition for Longitudinal Analysis of Diffusion Imaging Data.

Analysis of complex data is still a challenge in medical image analysis. Due to the heterogeneous information that can be extracted from magnetic resonance imaging (MRI) it can be difficult to fuse such data in a proper way. One interesting case is given by the analysis of diffusion imaging (DI) data. DI techniques give an important variety of information about the status of microstructure in the brain. This is interesting information to use especially in longitudinal setting where the temporal evolution of the pathology is an important added value. In this paper, we propose a new tensor-based framework capable to detect longitudinal changes appearing in DI data in multiple sclerosis (MS) patients. We focus our attention to the analysis of longitudinal changes occurring along different white matter (WM) fiber-bundles. Our main goal is to detect which subset of fibers (within a bundle) and which sections of these fibers contain "pathological" longitudinal changes. The framework consists of three main parts: i) preprocessing of longitudinal diffusion acquisitions and WM fiber-bundles extraction, ii) data tensorization and rank selection, iii) application of a parallelized constrained tensor factorization algorithm to detect longitudinal "pathological" changes. The proposed method was applied on simulated longitudinal variations and on real MS data. High level of accuracy and precision were obtained in the detection of small longitudinal changes along the WM fiber-bundles.

White matter microarchitecture and structural network integrity correlate with children intelligence quotient.

The neural substrate of high intelligence performances remains not well understood. Based on diffusion tensor imaging (DTI) which provides microstructural information of white matter fibers, we proposed in this work to investigate the relationship between structural brain connectivity and intelligence quotient (IQ) scores. Fifty-seven children (8-12 y.o.) underwent a MRI examination, including conventional T1-weighted and DTI sequences, and neuropsychological testing using the fourth edition of Wechsler Intelligence Scale for Children (WISC-IV), providing an estimation of the Full-Scale Intelligence Quotient (FSIQ) based on four subscales: verbal comprehension index (VCI), perceptual reasoning index (PRI), working memory index (WMI), and processing speed index (PSI). Correlations between the IQ scores and both graphs and diffusivity metrics were explored. First, we found significant correlations between the increased integrity of WM fiber-bundles and high intelligence scores. Second, the graph theory analysis showed that integration and segregation graph metrics were positively and negatively correlated with WISC-IV scores, respectively. These results were mainly driven by significant correlations between FSIQ, VCI, and PRI and graph metrics in the temporal and parietal lobes. In conclusion, these findings demonstrated that intelligence performances are related to the integrity of WM fiber-bundles as well as the density and homogeneity of WM brain networks.

Tensor Based Blind Source Separation in Longitudinal Magnetic Resonance Imaging Analysis.

Study of white matter (WM) fiber-bundles is a crucial challenge in the investigation of neurological diseases like multiple sclerosis (MS). In this activity, the amount of data to process is huge, and an automated approach to carry out this task is in order.In this paper we show how tensor-based blind source separation (BSS) techniques can be successfully applied to model complex anatomical brain structures. More in detail, we show how through vector hankelization it is possible to formalize data extracted from WM fiber-bundles using a tensor model. Two main tensor factorization techniques, namely (Lr, Lr, 1) block term decomposition (BTD) and canonical polyadic decomposition (CPD), were applied to the generated tensor. The information extracted from the factorization was then used to differentiate between sets of fibers, within the bundle, affected by the pathology and normal appearing fibers.Performances of the proposed tensor-based model was evaluated on simulated data representing pathological effects of MS. Results show the capability of our tensor-based model to detect small pathological phenomena appearing along WM fibers.

Classification of Multiple Sclerosis Clinical Profiles via Graph Convolutional Neural Networks.

Recent advances in image acquisition and processing techniques, along with the success of novel deep learning architectures, have given the opportunity to develop innovative algorithms capable to provide a better characterization of neurological related diseases. In this work, we introduce a neural network based approach to classify Multiple Sclerosis (MS) patients into four clinical profiles. Starting from their structural connectivity information, obtained by diffusion tensor imaging and represented as a graph, we evaluate the classification performances using unweighted and weighted connectivity matrices. Furthermore, we investigate the role of graph-based features for a better characterization and classification of the pathology. Ninety MS patients (12 clinically isolated syndrome, 30 relapsing-remitting, 28 secondary-progressive, and 20 primary-progressive) along with 24 healthy controls, were considered in this study. This work shows the great performances achieved by neural networks methods in the classification of the clinical profiles. Furthermore, it shows local graph metrics do not improve the classification results suggesting that the latent features created by the neural network in its layers have a much important informative content. Finally, we observe that graph weights representation of brain connections preserve important information to discriminate between clinical forms.

Prediction of Multiple Sclerosis Patient Disability from Structural Connectivity using Convolutional Neural Networks.

Prediction of disability progression in multiple sclerosis patients is a critical component of their management. In particular, one challenge is to identify and characterize a patient profile who may benefit of efficient treatments. However, it is not yet clear whether a particular relation exists between the brain structure and the disability status.This work aims at producing a fully automatic model for the expanded disability status score estimation, given the brain structural connectivity representation of a multiple sclerosis patient. The task is addressed by first extracting the connectivity graph, obtained by combining brain grey matter parcellation and tractography extracted from Diffusion and T1-weighted Magnetic Resonance (MR) images, and then processing it via a convolutional neural network (CNN) in order to compute the predicted score. Experiments show that the herein proposed approach achieves promising results, thus resulting as an important step forward on the road to better predict the evolution of the disease.

Corrigendum: Topological Modification of Brain Networks Organization in Children With High Intelligence Quotient: A Resting-State fMRI Study.

[This corrects the article DOI: 10.3389/fnhum.2019.00241.].

Topological Modification of Brain Networks Organization in Children With High Intelligence Quotient: A Resting-State fMRI Study.

The idea that intelligence is embedded not only in a single brain network, but instead in a complex, well-optimized system of complementary networks, has led to the development of whole brain network analysis. Using graph theory to analyze resting-state functional MRI data, we investigated the brain graph networks (or brain networks) of high intelligence quotient (HIQ) children. To this end, we computed the "hub disruption index κ," an index sensitive to graph network modifications. We found significant topological differences in the integration and segregation properties of brain networks in HIQ compared to standard IQ children, not only for the whole brain graph, but also for each hemispheric graph, and for the homotopic connectivity. Moreover, two profiles of HIQ children, homogenous and heterogeneous, based on the differences between the two main IQ subscales [verbal comprehension index (VCI) and perceptual reasoning index (PRI)], were compared. Brain network changes were more pronounced in the heterogeneous than in the homogeneous HIQ subgroups. Finally, we found significant correlations between the graph networks' changes and the full-scale IQ (FSIQ), as well as the subscales VCI and PRI. Specifically, the higher the FSIQ the greater was the brain organization modification in the whole brain, the left hemisphere, and the homotopic connectivity. These results shed new light on the relation between functional connectivity topology and high intelligence, as well as on different intelligence profiles.

Evidence of axonal damage in cerebellar peduncles without T2-lesions in multiple sclerosis.

BACKGROUND AND AIM: Cerebellar peduncles (CP) can be probed by diffusion tensor imaging (DTI) to evaluate the integrity of cerebellar afferent and efferent networks. Damage to the CP in multiple sclerosis (MS) could lead to serious cognitive and mobility impairment. The aim of this study was to investigate the extent and the clinical impact of CP damage in MS. METHODS: Sixty-eight MS patients were included in this study along with 27 healthy controls (HC) and underwent an MRI on a 1.5T including T1, T2, FLAIR and DTI. Using DTI, the microstructural integrity within the CP regions (superior (SCP), inferior (ICP) and middle (MCP)) was probed while controlling for focal T2-lesions presence or absence. A general linear model was performed to test for associations between clinical scores and DTI metrics for each CP. RESULTS: Significantly decreased fractional anisotropy (FA) and increased radial diffusivity (RD) were found in the CP of all MS patients compared to those of HC, but to a lesser extent in non-lesioned CP than those with lesions. Axial diffusivity (AD) was significantly and similarly increased in both non-lesioned and lesioned CP, but only in the SCP and ICP. Expanded disability status scale (EDSS) significantly correlated with MCP's FA (p < 0.05) and RD (p < 0.05), while MS functional composite (MSFC) significantly correlated with SCP's FA (p < 0.01) and RD (p < 0.01). CONCLUSION: The diffusion changes (FA and RD) measured in lesioned CP are probably directly related to the presence of inflammatory and/or demyelinating lesions. In contrast, the microstructural alterations reflected by AD increase in non-lesioned CP may result either from remote effects of cerebral white matter injury (diaschisis) or primary axonal degeneration, that are associated with cognitive, sensory and motor impairments of MS patients.

A genetic algorithm-based model for longitudinal changes detection in white matter fiber-bundles of patient with multiple sclerosis.

Analysis of white matter (WM) tissue is essential to understand the mechanisms of neurodegenerative pathologies like multiple sclerosis (MS). Recently longitudinal studies started to show how the temporal component is important to investigate temporal diffuse effects of neurodegenerative pathologies. Diffusion tensor imaging (DTI) constitutes one of the most sensitive techniques for the detection and characterization of brain related pathological processes and allows also the reconstruction of WM fibers. The analysis of spatial and temporal pathological changes along the fibers are thus possible by merging quantitative maps with structural information provided by DTI. In this work, we present a new genetic algorithm (GA) based method to analyze longitudinal changes occurring along WM fiber-bundles. In the first part of this paper, we describe the data processing pipeline, including data registration and fiber tract post-processing. In the second part, we focus our attention to the description of our GA model. In the last part, we show the tests we performed on simulated and real MS longitudinal data. Our method reached a high level of precision, recall and F-Measure in the detection of longitudinal pathological alterations occurring along different WM fiber-bundles.

Multiparametric Non-Negative Matrix Factorization for Longitudinal Variations Detection in White-Matter Fiber Bundles.

Processing of longitudinal diffusion tensor imaging (DTI) data is a crucial challenge to better understand pathological mechanisms of complex brain diseases such as multiple sclerosis (MS) where white-matter (WM) fiber bundles are variably altered by inflammatory events. In this study, we propose a new fully automated method to detect longitudinal changes in diffusivity metrics along WM fiber bundles. The proposed method is divided in three main parts: 1) preprocessing of longitudinal diffusion acquisitions, 2) WM fiber-bundle extraction, and 3) application of nonnegative matrix factorization and density-based local outliers algorithms to detect and delineate longitudinal variations appearing in the cross section of the WM fiber bundle. In order to validate our method, we introduce a new model to simulate real longitudinal changes based on a generalized Gaussian probability density function. Moreover, we applied our method on longitudinal data. High level of performances were obtained for the detection of small longitudinal changes along the WM fiber bundles in MS patients.

Hemispheric Differences in White Matter Microstructure between Two Profiles of Children with High Intelligence Quotient vs. Controls: A Tract-Based Spatial Statistics Study.

Objectives: The main goal of this study was to investigate and compare the neural substrate of two children's profiles of high intelligence quotient (HIQ). Methods: Two groups of HIQ children were included with either a homogeneous (Hom-HIQ: n = 20) or a heterogeneous IQ profile (Het-HIQ: n = 24) as defined by a significant difference between verbal comprehension index and perceptual reasoning index. Diffusion tensor imaging was used to assess white matter (WM) microstructure while tract-based spatial statistics (TBSS) analysis was performed to detect and localize WM regional differences in fractional anisotropy (FA), mean diffusivity, axial (AD), and radial diffusivities. Quantitative measurements were performed on 48 regions and 21 fiber-bundles of WM. Results: Hom-HIQ children presented higher FA than Het-HIQ children in widespread WM regions including central structures, and associative intra-hemispheric WM fasciculi. AD was also greater in numerous WM regions of Total-HIQ, Hom-HIQ, and Het-HIQ groups when compared to the Control group. Hom-HIQ and Het-HIQ groups also differed by their hemispheric lateralization in AD differences compared to Controls. Het-HIQ and Hom-HIQ groups showed a lateralization ratio (left/right) of 1.38 and 0.78, respectively. Conclusions: These findings suggest that both inter- and intra-hemispheric WM integrity are enhanced in HIQ children and that neural substrate differs between Hom-HIQ and Het-HIQ. The left hemispheric lateralization of Het-HIQ children is concordant with their higher verbal index while the relative right hemispheric lateralization of Hom-HIQ children is concordant with their global brain processing and adaptation capacities as evidenced by their homogeneous IQ.

Machine Learning Approach for Classifying Multiple Sclerosis Courses by Combining Clinical Data with Lesion Loads and Magnetic Resonance Metabolic Features.

Purpose: The purpose of this study is classifying multiple sclerosis (MS) patients in the four clinical forms as defined by the McDonald criteria using machine learning algorithms trained on clinical data combined with lesion loads and magnetic resonance metabolic features. Materials and Methods: Eighty-seven MS patients [12 Clinically Isolated Syndrome (CIS), 30 Relapse Remitting (RR), 17 Primary Progressive (PP), and 28 Secondary Progressive (SP)] and 18 healthy controls were included in this study. Longitudinal data available for each MS patient included clinical (e.g., age, disease duration, Expanded Disability Status Scale), conventional magnetic resonance imaging and spectroscopic imaging. We extract N-acetyl-aspartate (NAA), Choline (Cho), and Creatine (Cre) concentrations, and we compute three features for each spectroscopic grid by averaging metabolite ratios (NAA/Cho, NAA/Cre, Cho/Cre) over good quality voxels. We built linear mixed-effects models to test for statistically significant differences between MS forms. We test nine binary classification tasks on clinical data, lesion loads, and metabolic features, using a leave-one-patient-out cross-validation method based on 100 random patient-based bootstrap selections. We compute F1-scores and BAR values after tuning Linear Discriminant Analysis (LDA), Support Vector Machines with gaussian kernel (SVM-rbf), and Random Forests. Results: Statistically significant differences were found between the disease starting points of each MS form using four different response variables: Lesion Load, NAA/Cre, NAA/Cho, and Cho/Cre ratios. Training SVM-rbf on clinical and lesion loads yields F1-scores of 71-72% for CIS vs. RR and CIS vs. RR+SP, respectively. For RR vs. PP we obtained good classification results (maximum F1-score of 85%) after training LDA on clinical and metabolic features, while for RR vs. SP we obtained slightly higher classification results (maximum F1-score of 87%) after training LDA and SVM-rbf on clinical, lesion loads and metabolic features. Conclusions: Our results suggest that metabolic features are better at differentiating between relapsing-remitting and primary progressive forms, while lesion loads are better at differentiating between relapsing-remitting and secondary progressive forms. Therefore, combining clinical data with magnetic resonance lesion loads and metabolic features can improve the discrimination between relapsing-remitting and progressive forms.

An automated string-based approach to extracting and characterizing White Matter fiber-bundles.

In this paper, we propose an automated approach to extracting White Matter (WM) fiber-bundles through clustering and model characterization. The key novelties of our approach are: a new string-based formalism, allowing an alternative representation of WM fibers, a new string dissimilarity metric, a WM fiber clustering technique, and a new model-based characterization algorithm. Thanks to these novelties, the complex problem of WM fiber-bundle extraction and characterization reduces to a much simpler and well-known string extraction and analysis problem. Interestingly, while several past approaches extract fiber-bundles by grouping available fibers on the basis of provided atlases (and, therefore, cannot capture possibly existing fiber-bundles nor represented in the atlases), our approach first clusters available fibers once and for all, and then tries to associate obtained clusters with models provided directly and dynamically by users. This more dynamic and interactive way of proceeding can help the detection of fiber-bundles autonomously proposed by our approach and not present in the initial models provided by experts.

Graph Theory-Based Brain Connectivity for Automatic Classification of Multiple Sclerosis Clinical Courses.

Purpose: In this work, we introduce a method to classify Multiple Sclerosis (MS) patients into four clinical profiles using structural connectivity information. For the first time, we try to solve this question in a fully automated way using a computer-based method. The main goal is to show how the combination of graph-derived metrics with machine learning techniques constitutes a powerful tool for a better characterization and classification of MS clinical profiles. Materials and Methods: Sixty-four MS patients [12 Clinical Isolated Syndrome (CIS), 24 Relapsing Remitting (RR), 24 Secondary Progressive (SP), and 17 Primary Progressive (PP)] along with 26 healthy controls (HC) underwent MR examination. T1 and diffusion tensor imaging (DTI) were used to obtain structural connectivity matrices for each subject. Global graph metrics, such as density and modularity, were estimated and compared between subjects' groups. These metrics were further used to classify patients using tuned Support Vector Machine (SVM) combined with Radial Basic Function (RBF) kernel. Results: When comparing MS patients to HC subjects, a greater assortativity, transitivity, and characteristic path length as well as a lower global efficiency were found. Using all graph metrics, the best F-Measures (91.8, 91.8, 75.6, and 70.6%) were obtained for binary (HC-CIS, CIS-RR, RR-PP) and multi-class (CIS-RR-SP) classification tasks, respectively. When using only one graph metric, the best F-Measures (83.6, 88.9, and 70.7%) were achieved for modularity with previous binary classification tasks. Conclusion: Based on a simple DTI acquisition associated with structural brain connectivity analysis, this automatic method allowed an accurate classification of different MS patients' clinical profiles.

A Sensitive and Automatic White Matter Fiber Tracts Model for Longitudinal Analysis of Diffusion Tensor Images in Multiple Sclerosis.

Diffusion tensor imaging (DTI) is a sensitive tool for the assessment of microstructural alterations in brain white matter (WM). We propose a new processing technique to detect, local and global longitudinal changes of diffusivity metrics, in homologous regions along WM fiber-bundles. To this end, a reliable and automatic processing pipeline was developed in three steps: 1) co-registration and diffusion metrics computation, 2) tractography, bundle extraction and processing, and 3) longitudinal fiber-bundle analysis. The last step was based on an original Gaussian mixture model providing a fine analysis of fiber-bundle cross-sections, and allowing a sensitive detection of longitudinal changes along fibers. This method was tested on simulated and clinical data. High levels of F-Measure were obtained on simulated data. Experiments on cortico-spinal tract and inferior fronto-occipital fasciculi of five patients with Multiple Sclerosis (MS) included in a weekly follow-up protocol highlighted the greater sensitivity of this fiber scale approach to detect small longitudinal alterations.