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

Long-Term Ravulizumab Efficacy and Safety in AQP4 Antibody-Positive Neuromyelitis Optica Spectrum Disorder: Final CHAMPION-NMOSD Results.

Neurology(R) neuroimmunology & neuroinflammation·2026
Same author

The relationship between cerebellar functional connectivity alterations and hand dexterity impairment in multiple sclerosis.

Journal of neurology·2026
Same author

Mediation Analysis Between Brain Age, Disease-Modifying Factors, and Disability and Cognitive Performance in Multiple Sclerosis.

Neurology·2026
Same author

Altered neurodevelopmental trajectories of brain structure in Tourette syndrome and Chronic Tic Disorders.

medRxiv : the preprint server for health sciences·2026
Same author

MRI end-points for clinical trials in ataxias: recommendations from the Ataxia Global Initiative MRI Biomarkers Working Group.

Nature reviews. Neurology·2026
Same author

Reply to the Letter to the Editor: "The economic sustainability of AI in radiology: will efficiency require substitution?"

European radiology·2026

Related Experiment Video

Updated: Oct 20, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.0K

A Combined Radiomics and Machine Learning Approach to Overcome the Clinicoradiologic Paradox in Multiple Sclerosis.

G Pontillo1,2, S Tommasin3, R Cuocolo4,5

  • 1From the Departments of Advanced Biomedical Sciences (G.P., L.U., E.T., S.C.).

AJNR. American Journal of Neuroradiology
|September 17, 2021
PubMed
Summary

Machine learning models using radiomic and volumetric brain MRI features accurately predict multiple sclerosis disability. This approach enhances understanding beyond conventional imaging for improved patient management.

More Related Videos

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.4K
Magnetic Resonance Imaging of Multiple Sclerosis at 7.0 Tesla
08:51

Magnetic Resonance Imaging of Multiple Sclerosis at 7.0 Tesla

Published on: February 19, 2021

9.3K

Related Experiment Videos

Last Updated: Oct 20, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.0K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.4K
Magnetic Resonance Imaging of Multiple Sclerosis at 7.0 Tesla
08:51

Magnetic Resonance Imaging of Multiple Sclerosis at 7.0 Tesla

Published on: February 19, 2021

9.3K

Area of Science:

  • Neurology
  • Radiology
  • Artificial Intelligence

Background:

  • Conventional MRI explains limited clinical outcome variance in multiple sclerosis (MS).
  • There is a need for advanced imaging analysis to better correlate with disability.
  • Radiomic, volumetric, and connectivity features offer potential for deeper insights.

Purpose of the Study:

  • To evaluate machine learning (ML) models for predicting disability in MS patients.
  • To assess the utility of radiomic, volumetric, and connectivity features from routine brain MRIs.
  • To determine if ML can bridge the gap between imaging and clinical outcomes.

Main Methods:

  • Retrospective analysis of 3T brain MRIs (T1-weighted, T2-FLAIR) from two institutions.
  • Extraction of volumetric, connectivity, and texture (radiomic) features from GM regions.
  • Training and validation of ML models using clinicodemographic and imaging features on split cohorts (n=400 training, n=100 test, n=104 external test).

Main Results:

  • Nine informative variables identified, including age, disease course, and radiomic features from prefrontal cortex, subcortical GM, and cerebellum.
  • ML models achieved high disability prediction accuracy (r ≈ 0.80).
  • Excellent intra- and inter-site generalizability demonstrated (r ≥ 0.73), with algorithm type having minimal impact.

Conclusions:

  • Multidimensional analysis of brain MRIs, incorporating radiomic features and clinical data, is highly informative for MS patient status.
  • This approach shows promise in correlating advanced imaging metrics with clinical disability.
  • ML-driven analysis of routine brain MRIs offers a powerful tool for understanding and potentially managing MS progression.