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

Seizures: Classification01:13

Seizures: Classification

Epilepsy is primarily characterized by unpredictable seizures, either provoked by an identifiable factor, such as injury or illness, or unprovoked, occurring spontaneously without apparent cause.
Seizures are typically classified into two main categories: focal and generalized seizures.
Focal Seizures
Focal seizures originate from specific regions of the brain. These seizures are further sub-classified into two types:

You might also read

Related Articles

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

Sort by
Same author

Preictal reduction in heart rate variability entropy is associated with functional/dissociative seizures and provides modest discrimination from epileptic seizures.

Epilepsy & behavior : E&B·2026
Same author

Global Socioeconomic Context and Brain Ageing in Epilepsy: an ENIGMA-Epilepsy study.

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

Characterizing Onset Limit and Surgical Outcome Factors in Type II Focal Cortical Dysplasia-Related Epilepsy.

Neurology. Clinical practice·2026
Same author

InnerEye-HS: a disease-agnostic clinical tool for hippocampal segmentation.

Brain communications·2026
Same author

Postmortem MRI reveals distinct structural features in sudden unexpected death in epilepsy.

Epilepsia open·2026
Same author

The heartbeat evoked potential and the prediction of functional seizure semiology.

Brain communications·2026

Related Experiment Video

Updated: May 30, 2026

Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy
12:09

Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy

Published on: August 5, 2014

Automated MR image classification in temporal lobe epilepsy.

Niels K Focke1, Mahinda Yogarajah, Mark R Symms

  • 1Department of Clinical Neurophysiology, Georg-August University Göttingen, Göttingen, Germany. nfocke@uni-goettingen.de

Neuroimage
|August 13, 2011
PubMed
Summary
This summary is machine-generated.

Automated MRI analysis using support vector machines (SVM) accurately identifies temporal lobe epilepsy. This advanced technique aids in diagnosing epilepsy when standard MRI scans appear normal, improving surgical candidate selection.

More Related Videos

Brain Source Imaging in Preclinical Rat Models of Focal Epilepsy using High-Resolution EEG Recordings
08:20

Brain Source Imaging in Preclinical Rat Models of Focal Epilepsy using High-Resolution EEG Recordings

Published on: June 6, 2015

Related Experiment Videos

Last Updated: May 30, 2026

Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy
12:09

Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy

Published on: August 5, 2014

Brain Source Imaging in Preclinical Rat Models of Focal Epilepsy using High-Resolution EEG Recordings
08:20

Brain Source Imaging in Preclinical Rat Models of Focal Epilepsy using High-Resolution EEG Recordings

Published on: June 6, 2015

Area of Science:

  • Neuroimaging
  • Machine Learning in Medicine
  • Epilepsy Research

Background:

  • Magnetic resonance imaging (MRI) is crucial for identifying epilepsy causes, but up to 25% of surgical candidates have unremarkable scans.
  • Subtle or widespread MRI changes can be missed during visual inspection, necessitating automated analysis tools.
  • Support vector machines (SVM) show promise for voxel-based MRI classification in neurological conditions.

Purpose of the Study:

  • To evaluate the feasibility and accuracy of automated SVM-based MRI classification for temporal lobe epilepsy (TLE).
  • To assess the diagnostic performance of SVM using different MRI sequences and analysis methods in TLE patients.
  • To determine if automated classification can aid in presurgical evaluation, especially for cases with subtle or absent visible lesions.

Main Methods:

  • Studied 38 patients with mesial temporal lobe epilepsy (mTLE) and 22 controls using 3T MRI.
  • Acquired 3D T1-weighted, diffusion tensor imaging (DTI), and T2 relaxometry data.
  • Applied SVM analysis with leave-one-out cross-validation and local weighting for classification.

Main Results:

  • SVM achieved high accuracies (90-100%) using gray matter segmentation and (95-97%) using mean diffusivity.
  • Three-way classification accuracies reached 88% and 93%.
  • Automated classification remained highly accurate (>90%) even after removing the hippocampus, demonstrating robustness.

Conclusions:

  • Automated SVM MRI classification demonstrates high diagnostic accuracy for mTLE.
  • Voxel-based MRI analysis with SVM is feasible at the individual subject level for epilepsy.
  • This method can assist in screening MRI scans for epilepsy, particularly when visual inspection yields no findings.