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

Thyroid hormones and energy metabolism in amyotrophic lateral sclerosis.

Brain communications·2026
Same author

Innate immune signaling as a potential pathomechanistic biomarker for distinct subtypes in amyotrophic lateral sclerosis.

Amyotrophic lateral sclerosis & frontotemporal degeneration·2026
Same author

Disruption of the angiopoietin-like system connects lipid homeostasis and hypothalamic dysfunction in ALS.

BMC medicine·2026
Same author

Accuracy of clinical diagnosis in neurodegenerative diseases - a study of 455 autopsy cases.

Journal of neurology·2026
Same author

Additive value of early-phase β-Amyloid-PET for the differential diagnosis of non-Alzheimer's disease dementia.

NeuroImage. Clinical·2026
Same author

Proceedings of the 12<sup>th</sup> International Meeting on Neuroacanthocytosis, Cohen Syndrome, and Other VPS13-Related Disorders.

Tremor and other hyperkinetic movements (New York, N.Y.)·2026

Related Experiment Video

Updated: Mar 7, 2026

Cross-Modal Multivariate Pattern Analysis
13:51

Cross-Modal Multivariate Pattern Analysis

Published on: November 9, 2011

20.6K

Predicting primary progressive aphasias with support vector machine approaches in structural MRI data.

Sandrine Bisenius1, Karsten Mueller1, Janine Diehl-Schmid2

  • 1Max Planck Institute for Human Cognitive and Brain Sciences & Clinic for Cognitive Neurology, University Hospital Leipzig, Germany.

Neuroimage. Clinical
|February 24, 2017
PubMed
Summary
This summary is machine-generated.

Structural MRI and machine learning accurately identify primary progressive aphasia (PPA) subtypes. Support vector machine classification of grey matter density maps aids early diagnosis of PPA variants.

Keywords:
Grey matterMulti-centerPrimary progressive aphasiaSupport vector machine classificationWhole brain approach

More Related Videos

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

49.5K
Whole-brain Segmentation and Change-point Analysis of Anatomical Brain MRI&#8212;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

12.7K

Related Experiment Videos

Last Updated: Mar 7, 2026

Cross-Modal Multivariate Pattern Analysis
13:51

Cross-Modal Multivariate Pattern Analysis

Published on: November 9, 2011

20.6K
Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

49.5K
Whole-brain Segmentation and Change-point Analysis of Anatomical Brain MRI&#8212;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

12.7K

Area of Science:

  • Neuroimaging
  • Neurology
  • Machine Learning

Background:

  • Primary progressive aphasia (PPA) presents with distinct language deficits and brain atrophy patterns.
  • Accurate early diagnosis of PPA subtypes is crucial for patient management.

Purpose of the Study:

  • To evaluate the efficacy of structural magnetic resonance imaging (sMRI) data using support vector machine (SVM) classification for early diagnosis of PPA subtypes.
  • To compare whole-brain versus disease-specific regions-of-interest (ROI) approaches for SVM classification.

Main Methods:

  • Voxel-based morphometry (VBM) was used to analyze grey matter density from sMRI scans of 44 PPA patients (16 nonfluent/agrammatic, 17 semantic, 11 logopenic) and 20 controls.
  • SVM classification was applied to whole-brain and meta-analysis-based ROI grey matter maps to discriminate PPA subtypes from controls and from each other.

Main Results:

  • Whole-brain SVM achieved high accuracy (91-97%) in distinguishing PPA subtypes from healthy controls.
  • SVM accurately discriminated semantic variant PPA from nonfluent/agrammatic (78%) and logopenic (95%) variants.
  • Discrimination between nonfluent/agrammatic and logopenic variants showed lower accuracy (55%).
  • Key brain regions identified by SVM classification corresponded to areas of atrophy in PPA patients.

Conclusions:

  • SVM classification of multi-center sMRI data enables highly accurate prediction of PPA subtypes.
  • This approach holds promise for clinical application in early PPA diagnosis.
  • Both whole-brain and ROI approaches demonstrated comparable accuracies due to the specific neural networks involved in PPA.