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

Machine learning-driven correction of handgrip strength: a novel biomarker for neurological and health outcomes in the UK Biobank.

Biomedical physics & engineering express·2026
Same author

Prediction of cognitive performance by demographics, sleep, and brain morphometry: machine learning findings from ENIGMA-Sleep Working Group.

Research square·2026
Same author

Quantifying cerebellar signal detectability in MEG and EEG in epilepsy using anatomically informed source modeling.

NeuroImage·2026
Same author

Exposome-wide patterns predict brain health in aging.

Nature communications·2026
Same author

Predicting brain volumes from anthropometric and demographic features: insights from UK biobank neuroimaging data.

Brain structure & function·2026
Same author

Can we predict sleep health based on brain features? A large-scale machine learning study using the UK Biobank.

Brain communications·2026

Related Experiment Video

Updated: Feb 27, 2026

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding
11:25

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

44.2K

Autoreject: Automated artifact rejection for MEG and EEG data.

Mainak Jas1, Denis A Engemann2, Yousra Bekhti1

  • 1LTCI, Télécom ParisTech, Université Paris-Saclay, France.

Neuroimage
|June 25, 2017
PubMed
Summary

Autoreject automates the identification and correction of poor-quality trials in electroencephalography (EEG) and magnetoencephalography (MEG) data. This novel algorithm enhances data reliability and scalability for neuroscience research.

Keywords:
Automated analysisCross-validationElectroencephalogram (EEG)Human Connectome Project (HCP)Magnetoencephalography (MEG)PreprocessingStatistical learning

More Related Videos

A Multimodal Imaging- and Stimulation-based Method of Evaluating Connectivity-related Brain Excitability in Patients with Epilepsy
08:23

A Multimodal Imaging- and Stimulation-based Method of Evaluating Connectivity-related Brain Excitability in Patients with Epilepsy

Published on: November 13, 2016

11.8K
Cortical Source Analysis of High-Density EEG Recordings in Children
09:32

Cortical Source Analysis of High-Density EEG Recordings in Children

Published on: June 30, 2014

22.0K

Related Experiment Videos

Last Updated: Feb 27, 2026

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding
11:25

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

44.2K
A Multimodal Imaging- and Stimulation-based Method of Evaluating Connectivity-related Brain Excitability in Patients with Epilepsy
08:23

A Multimodal Imaging- and Stimulation-based Method of Evaluating Connectivity-related Brain Excitability in Patients with Epilepsy

Published on: November 13, 2016

11.8K
Cortical Source Analysis of High-Density EEG Recordings in Children
09:32

Cortical Source Analysis of High-Density EEG Recordings in Children

Published on: June 30, 2014

22.0K

Area of Science:

  • Neuroscience
  • Signal Processing
  • Biomedical Engineering

Background:

  • Magnetoencephalography (MEG) and electroencephalography (EEG) are crucial for studying brain activity.
  • Manual identification and correction of artifacts in M/EEG data are time-consuming and subjective.
  • Automated preprocessing methods are needed to improve efficiency and reliability in large-scale neuroscience studies.

Purpose of the Study:

  • To develop and validate an automated algorithm, Autoreject, for unified rejection and repair of bad trials in M/EEG signals.
  • To provide a scalable and reliable solution for M/EEG data preprocessing.
  • To minimize the need for human inspection in M/EEG data analysis.

Main Methods:

  • Utilized cross-validation and a robust evaluation metric to determine optimal peak-to-peak thresholds for artifact detection.
  • Extended the method to estimate sensor-wise thresholds for identifying trial-specific bad sensors.
  • Implemented automated trial repair through interpolation or exclusion based on the number of bad sensors.

Main Results:

  • Autoreject successfully automated the preprocessing of M/EEG data, including artifact rejection and repair.
  • Extensive validation on four public datasets with over 200 subjects demonstrated comparable or superior performance to state-of-the-art methods.
  • The algorithm enabled full automation of MEG data preprocessing for the Human Connectome Project (HCP) dataset.

Conclusions:

  • Autoreject offers a fully automated, robust, and scalable solution for M/EEG artifact handling.
  • The algorithm significantly reduces the manual effort required for M/EEG data preprocessing.
  • Autoreject enhances the reliability and efficiency of neuroscience research by streamlining data analysis pipelines.