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

Gestational weight gain and maternal immediate perinatal and postpartum outcomes in low and middle income countries: individual participant data meta-analyses.

BMJ medicine·2026
Same author

Rutin-Doped Hybrid Nanoparticles: Effect of the Molecular Doping Density on <i>T</i><sub>1</sub> Relaxivity and Their Application in Targeted Magnetic Resonance Imaging of Malignant Tumors.

Nano letters·2026
Same author

CT-based Node-RADS classification in the assessment of rectal cancer: diagnostic performance and postoperative prognostic stratification.

BMC cancer·2026
Same author

Clinical features and gastrointestinal bleeding risk factors in IgA vasculitis patients: a retrospective study in a large volume centre.

Clinical and experimental rheumatology·2026
Same author

A dual-functional PEG-tyrosine hydrogel with photothermal effect and antioxidant capacity for cancer therapy and tissue regeneration.

Regenerative biomaterials·2026
Same author

ATP2B4 driven chromatin compaction exacerbates pancreatic cancer radiotherapy resistance.

Cell death discovery·2026

Related Experiment Video

Updated: Sep 25, 2025

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging
11:28

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

Published on: June 30, 2018

11.8K

A Graph Fourier Transform Based Bidirectional Long Short-Term Memory Neural Network for Electrophysiological Source

Meng Jiao1,2, Guihong Wan3,4, Yaxin Guo1

  • 1School of Systems and Enterprises, Stevens Institute of Technology, Hoboken, NJ, United States.

Frontiers in Neuroscience
|May 2, 2022
PubMed
Summary

This study introduces a novel Graph Fourier Transform based Bidirectional Long-Short Term Memory neural network for electrophysiological source imaging (ESI). The method accurately reconstructs brain activity, outperforming existing algorithms for both synthetic and real patient data.

Keywords:
BiLSTMelectroencephalographygraph Fourier transforminverse problemsource localization

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

15.5K
Author Spotlight: Advancing Pediatric Epilepsy Surgery in Children Through Novel Biomarkers and Enhanced Localization
09:57

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

Published on: September 20, 2024

2.8K

Related Experiment Videos

Last Updated: Sep 25, 2025

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging
11:28

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

Published on: June 30, 2018

11.8K
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

15.5K
Author Spotlight: Advancing Pediatric Epilepsy Surgery in Children Through Novel Biomarkers and Enhanced Localization
09:57

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

Published on: September 20, 2024

2.8K

Area of Science:

  • Neuroscience
  • Biomedical Engineering
  • Signal Processing

Background:

  • Electrophysiological source imaging (ESI) reconstructs cortical activity from EEG/MEG signals.
  • ESI is ill-posed, requiring regularization for unique solutions.
  • Reconstructing extended sources is challenging, often using total variation regularization.

Purpose of the Study:

  • To develop a novel method for electrophysiological source imaging (ESI).
  • To improve the reconstruction of focally extended brain sources.
  • To enhance the accuracy of localizing brain activity, including epileptogenic zones.

Main Methods:

  • Utilized Graph Fourier Transform (GFT) to decompose the source space into frequency subspaces.
  • Employed a Bidirectional Long-Short Term Memory (BiLSTM) neural network.
  • Learned mapping between low-frequency GFT components and EEG signals for source reconstruction.

Main Results:

  • The proposed GFT-BiLSTM method demonstrated superior performance compared to benchmark algorithms on synthetic data across various SNRs.
  • Real-world data experiments confirmed the method's accuracy in localizing the epileptogenic zone in epilepsy patients.
  • GFT's low-frequency components effectively acted as a spatial low-pass filter for extended source reconstruction.

Conclusions:

  • The GFT-BiLSTM approach offers a significant advancement in electrophysiological source imaging.
  • This method provides accurate reconstruction and localization of extended brain sources.
  • The technique shows promise for clinical applications, such as epilepsy diagnosis.