Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Seizures: Classification

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:

Classification of Signals

Classification of Signals

In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...

You might also read

Related Articles

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

Sort by

Same author

Virtual Responsive Neurostimulation Implantation: From Intracranial Connectivity to Optimized Lead Placement.

medRxiv : the preprint server for health sciences·2026

Same author

Responsive stimulation of the thalamus for idiopathic generalized epilepsy: Results of the randomized controlled NAUTILUS trial through 18 months.

Epilepsia·2026

Same author

Postapproval Study for Brain-Responsive Neurostimulation for Drug-Resistant Focal Epilepsy: Three-Year Efficacy and Interim Safety Results.

Neurology·2026

Same author

Using vision transformers for electrographic seizure classification to aid physician review of intracranial electroencephalography recordings.

Frontiers in human neuroscience·2025

Same author

AI-Driven Electrographic Seizure Classification and Seizure Onset Detection Using Image- and Time-Series-Based Approaches.

IEEE transactions on bio-medical engineering·2025

Same author

Chronic thalamic recordings for idiopathic generalized epilepsy and Lennox-Gastaut syndrome: Ictal and interictal electrophysiological findings.

Epilepsia open·2025

Search research articles

Related Experiment Video

Updated: Oct 28, 2025

Computer-based Multitaper Spectrogram Program for Electroencephalographic Data

Computer-based Multitaper Spectrogram Program for Electroencephalographic Data

Published on: November 13, 2019

A High Accuracy Electrographic Seizure Classifier Trained Using Semi-Supervised Labeling Applied to a Large

Wade Barry¹, Sharanya Arcot Desai¹, Thomas K Tcheng¹

¹NeuroPace, Inc., Mountain View, CA, United States.

Frontiers in Neuroscience

|July 15, 2021

Summary

This study shows electroencephalography (ECoG) spectrogram images can train reliable seizure classifiers. Even with data from 10 patients, deep learning models achieved 88% accuracy, improving with more data.

Keywords:

ECoG labeling big data electrographic seizure classifier epilepsy semi-supervised labeling

More Related Videos

Author Spotlight: Advancing Pediatric Epilepsy Surgery in Children Through Novel Biomarkers and Enhanced Localization

Author Spotlight: Advancing Pediatric Epilepsy Surgery in Children Through Novel Biomarkers and Enhanced Localization

Published on: September 20, 2024

Author Spotlight: Unraveling Seizure Dynamics and Novel Therapeutics for Status Epilepticus Using CMOS High-Density Microelectrode Array Systems

Author Spotlight: Unraveling Seizure Dynamics and Novel Therapeutics for Status Epilepticus Using CMOS High-Density Microelectrode Array Systems

Published on: September 27, 2024

Related Experiment Videos

Last Updated: Oct 28, 2025

Computer-based Multitaper Spectrogram Program for Electroencephalographic Data

Computer-based Multitaper Spectrogram Program for Electroencephalographic Data

Published on: November 13, 2019

Author Spotlight: Advancing Pediatric Epilepsy Surgery in Children Through Novel Biomarkers and Enhanced Localization

Author Spotlight: Advancing Pediatric Epilepsy Surgery in Children Through Novel Biomarkers and Enhanced Localization

Published on: September 20, 2024

Author Spotlight: Unraveling Seizure Dynamics and Novel Therapeutics for Status Epilepticus Using CMOS High-Density Microelectrode Array Systems

Author Spotlight: Unraveling Seizure Dynamics and Novel Therapeutics for Status Epilepticus Using CMOS High-Density Microelectrode Array Systems

Published on: September 27, 2024

Area of Science:

Medical Informatics
Computational Neuroscience
Machine Learning in Medicine

Background:

Electroencephalography (ECoG) is crucial for diagnosing epilepsy, but manual analysis is time-consuming.
Developing automated seizure detection methods can improve diagnostic efficiency and accuracy.
Cross-patient generalization remains a challenge for electrographic seizure classifiers.

Purpose of the Study:

To evaluate the efficacy of using ECoG spectrogram images for training robust cross-patient electrographic seizure classifiers.
To determine the relationship between the amount of training data and classifier performance.
To assess the speed and efficiency of ECoG data labeling using unsupervised clustering techniques.

Main Methods:

ECoG time-series data from 113 patients were converted into RGB spectrogram images.
Unsupervised spectrogram image clustering accelerated manual labeling by an estimated 5x.
Five Convolutional Neural Network (CNN) architectures, including ResNet50, were trained and validated on ECoG spectrograms.
Cross-validation was performed using five data folds, each with distinct patient sets for training, validation, and testing.

Main Results:

Classification accuracy and F1 scores increased with model complexity, reaching 95.7% with a ResNet50-based CNN.
The best model demonstrated 93.5% agreement with an independent expert.
Sufficient accuracy (88%) was achieved with spectrograms from just 10 patients, while >90% accuracy required data from at least 30 patients.

Conclusions:

ECoG spectrogram images are effective for training reliable cross-patient seizure classifiers.
Deep learning models, particularly complex CNNs like ResNet50, show high performance in automated seizure detection.
The study highlights the potential for efficient data labeling and reduced data requirements for developing accurate electrographic seizure detection systems.