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

Detour ahead: possible causes of corticospinal tract truncation in upper motor neuron-predominant amyotrophic lateral sclerosis.

Brain communications·2025
Same author

Modeling ALS with Patient-Derived iPSCs: Recent Advances and Future Potentials.

Brain sciences·2025
Same author

Neurophysiologic Innovations in ALS: Enhancing Diagnosis, Monitoring, and Treatment Evaluation.

Brain sciences·2025
Same author

Graph theory network analysis reveals widespread white matter damage in brains of patients with classic ALS.

Amyotrophic lateral sclerosis & frontotemporal degeneration·2024
Same author

Nanoplastics and Neurodegeneration in ALS.

Brain sciences·2024
Same author

Describing and characterising variability in ALS disease progression.

Amyotrophic lateral sclerosis & frontotemporal degeneration·2023

Related Experiment Video

Updated: Jul 30, 2025

A Quick Phenotypic Neurological Scoring System for Evaluating Disease Progression in the SOD1-G93A Mouse Model of ALS
06:49

A Quick Phenotypic Neurological Scoring System for Evaluating Disease Progression in the SOD1-G93A Mouse Model of ALS

Published on: October 6, 2015

19.8K

Quantitative Brain MRI Metrics Distinguish Four Different ALS Phenotypes: A Machine Learning Based Study.

Venkateswaran Rajagopalan1, Krishna G Chaitanya1, Erik P Pioro2,3

  • 1Department of Electrical and Electronics Engineering, Birla Institute of Technology and Science Pilani, Hyderabad Campus, Hyderabad 500078, India.

Diagnostics (Basel, Switzerland)
|May 13, 2023
PubMed
Summary

Machine learning analysis of MRI scans accurately classified amyotrophic lateral sclerosis (ALS) phenotypes. White matter MRI metrics were key to distinguishing subtypes, offering new diagnostic potential for this neurodegenerative disease.

Keywords:
ALS phenotypesMRIRandom Forestmachine learningneural network

More Related Videos

Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases
09:33

Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases

Published on: July 28, 2013

28.5K
Whole-brain Segmentation and Change-point Analysis of Anatomical Brain MRI—Application in Premanifest Huntington's Disease
09:06

Whole-brain Segmentation and Change-point Analysis of Anatomical Brain MRI—Application in Premanifest Huntington's Disease

Published on: June 9, 2018

12.2K

Related Experiment Videos

Last Updated: Jul 30, 2025

A Quick Phenotypic Neurological Scoring System for Evaluating Disease Progression in the SOD1-G93A Mouse Model of ALS
06:49

A Quick Phenotypic Neurological Scoring System for Evaluating Disease Progression in the SOD1-G93A Mouse Model of ALS

Published on: October 6, 2015

19.8K
Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases
09:33

Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases

Published on: July 28, 2013

28.5K
Whole-brain Segmentation and Change-point Analysis of Anatomical Brain MRI—Application in Premanifest Huntington's Disease
09:06

Whole-brain Segmentation and Change-point Analysis of Anatomical Brain MRI—Application in Premanifest Huntington's Disease

Published on: June 9, 2018

12.2K

Area of Science:

  • Neuroscience
  • Radiology
  • Machine Learning

Background:

  • Amyotrophic lateral sclerosis (ALS) diagnosis requires identifying both lower motor neuron (LMN) and upper motor neuron (UMN) degeneration.
  • Currently, no equivalent to electromyography exists for assessing UMN dysfunction, and MRI is mainly used to rule out other conditions.
  • Distinct pathological processes may underlie different ALS clinical/radiological phenotypes, potentially reflected in unique MRI signatures.

Purpose of the Study:

  • To investigate if machine learning (ML) can stratify ALS patients into distinct phenotypes using MRI measures.
  • To identify which MRI-derived attributes (white matter, grey matter, or non-imaging) are most effective in classifying ALS phenotypes.
  • To explore the potential of ML-based MRI analysis for a more nuanced understanding of ALS pathology.

Main Methods:

  • Acquired T1-, T2-, PD-weighted, and diffusion tensor (DT) brain MRI scans from 15 neurological controls and 91 ALS patients across four phenotypes.
  • Extracted 101 white matter (WM) attributes, 10 grey matter (GM) attributes, and 10 non-imaging attributes (demographic and clinical).
  • Employed classification and regression trees, Random Forest (RF), and artificial neural networks for classification, with RF showing the best performance.

Main Results:

  • The Random Forest algorithm achieved high accuracy (70-94%) in classifying the four identified ALS phenotypes.
  • White matter (WM) metrics were found to be the most dominant features for phenotype classification, outperforming GM and clinical measures.
  • WM measures from both hemispheres were important, but appeared to be differentially affected by the neurodegenerative process in ALS.

Conclusions:

  • Machine learning, particularly the RF algorithm, can effectively stratify ALS patients into distinct phenotypes using MRI data.
  • White matter integrity measures derived from MRI are crucial biomarkers for differentiating ALS subtypes.
  • These findings suggest that distinct pathological processes in ALS may have unique MRI signatures, warranting further longitudinal investigation.