Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Knowledge, attitudes, and practices of Lebanese healthcare professionals toward multidisciplinary spinal cord injury rehabilitation.

Spinal cord series and cases·2026
Same author

Magnetic Resonance Imaging Features in Intramedullary Tumors: A Pictorial Review.

Biomedicines·2026
Same author

Upper Cervical Cord Area as a Biomarker of Conversion to Secondary Progressive Multiple Sclerosis.

Annals of clinical and translational neurology·2026
Same author

Updated French OFSEP recommendations for multiple sclerosis MRI: alignment with the 2024 McDonald criteria.

Journal of neuroradiology = Journal de neuroradiologie·2026
Same author

Subclinical Optic Nerve Involvement in Radiologically Isolated Syndrome: Multimodal Detection and Diagnostic Impact.

Annals of clinical and translational neurology·2026
Same author

French NOMADMUS Cohort Overview: Landscape Evolution of AQP4+NMOSD and MOGAD From 2010 to 2024.

Neurology·2026

Related Experiment Video

Updated: Mar 12, 2026

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms
08:51

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

6.1K

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

Gabriel Kocevar1, Claudio Stamile1, Salem Hannoun2

  • 1CREATIS Centre National de la Recherche Scientifique UMR5220 and Institut National de la Santé et de la Recherche Médicale U1206, INSA-Lyon, Université de Lyon, Université Claude Bernard-Lyon 1 Lyon, France.

Frontiers in Neuroscience
|November 10, 2016
PubMed
Summary

This study presents an automated method using brain connectivity and machine learning to classify Multiple Sclerosis (MS) patients into clinical profiles. The approach accurately distinguishes between different MS types and healthy controls.

Keywords:
MRISVMclassificationdiffusion tensor imaginggraph theorymultiple sclerosisstructural connectivity

More Related Videos

Application of Granger Causality Analysis of the Directed Functional Connection in Alzheimer's Disease and Mild Cognitive Impairment
08:43

Application of Granger Causality Analysis of the Directed Functional Connection in Alzheimer's Disease and Mild Cognitive Impairment

Published on: August 7, 2017

8.5K
Comprehensive Autopsy Program for Individuals with Multiple Sclerosis
09:41

Comprehensive Autopsy Program for Individuals with Multiple Sclerosis

Published on: July 19, 2019

12.1K

Related Experiment Videos

Last Updated: Mar 12, 2026

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms
08:51

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

6.1K
Application of Granger Causality Analysis of the Directed Functional Connection in Alzheimer's Disease and Mild Cognitive Impairment
08:43

Application of Granger Causality Analysis of the Directed Functional Connection in Alzheimer's Disease and Mild Cognitive Impairment

Published on: August 7, 2017

8.5K
Comprehensive Autopsy Program for Individuals with Multiple Sclerosis
09:41

Comprehensive Autopsy Program for Individuals with Multiple Sclerosis

Published on: July 19, 2019

12.1K

Area of Science:

  • Neuroimaging
  • Computational Neuroscience
  • Medical Informatics

Background:

  • Multiple Sclerosis (MS) is a chronic neurological disease with diverse clinical presentations.
  • Accurate classification of MS clinical profiles is crucial for personalized treatment and prognosis.
  • Current classification methods may not fully capture the nuances of disease progression.

Purpose of the Study:

  • To develop and validate a fully automated computer-based method for classifying MS patients into four clinical profiles.
  • To investigate the utility of structural brain connectivity metrics combined with machine learning for MS classification.
  • To demonstrate the power of graph theory metrics and Support Vector Machine (SVM) for characterizing MS phenotypes.

Main Methods:

  • Structural connectivity matrices were derived from T1 and diffusion tensor imaging (DTI) data of 64 MS patients and 26 healthy controls (HC).
  • Global graph metrics (e.g., density, modularity, assortativity, transitivity, characteristic path length, global efficiency) were calculated.
  • A Support Vector Machine (SVM) with a Radial Basis Function (RBF) kernel was employed for classification tasks.

Main Results:

  • MS patients exhibited distinct structural connectivity patterns compared to HC, including greater assortativity and transitivity, and lower global efficiency.
  • The automated method achieved high F-Measures for binary classifications (up to 91.8%) and multi-class classification (up to 75.6%).
  • Modularity, as a single graph metric, also showed strong performance in binary classification tasks (up to 88.9%).

Conclusions:

  • Structural brain connectivity analysis, derived from simple DTI acquisition, provides a robust foundation for automated MS patient classification.
  • The proposed machine learning approach enables accurate differentiation of various clinical profiles of Multiple Sclerosis.
  • This automated method offers a promising tool for enhanced characterization and management of MS patients.