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

2.5K
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:
2.5K

You might also read

Related Articles

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

Sort by
Same author

Bayesian Uncertainty-aware Deep Learning with noisy labels: Tackling annotation ambiguity in EEG seizure detection.

PloS one·2026
Same author

The evolving role of artificial intelligence in ophthalmology: basic science, translation, and clinical integration.

Current opinion in ophthalmology·2026
Same author

LLM-Powered Cross-Modal Alignment for Explainable Seizure Detection from EEG.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention·2026
Same author

BiSCoT: Behavior-Informed Subgroup-Consistent Connectome Template for Interpretable Brain Network Analysis.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention·2026
Same author

Learning Explainable Imaging-Genetics Associations Related to a Neurological Disorder.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention·2026
Same author

GAMing the Brain: Investigating the Cross-modal Relationships between Functional Connectivity and Structural Features using Generalized Additive Models.

Machine learning in clinical neuroimaging : 7th international workshop, MLCN 2024, held in conjunction with MICCAI 2024, Marrakesh, Morocco, October 10, 2024, proceedings. MLCN (Workshop) (7th : 2024 : Marrakesh, Morocco)·2026

Related Experiment Video

Updated: May 6, 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

18.0K

A DEEP LEARNING FRAMEWORK TO CHARACTERIZE NOISY LABELS IN EPILEPTOGENIC ZONE LOCALIZATION USING FUNCTIONAL

Naresh Nandakumar1, David Hsu2, Raheel Ahmed3

  • 1Department of Electrical and Computer Engineering, Johns Hopkins University, USA.

Proceedings. IEEE International Symposium on Biomedical Imaging
|October 28, 2024
PubMed
Summary
This summary is machine-generated.

This study introduces a novel deep learning framework to accurately pinpoint the epileptogenic zone (EZ) in epilepsy patients, even with noisy post-operative imaging data. The method improves seizure localization by accounting for uncertainties in ground truth labels.

Keywords:
Dynamic Functional ConnectivityEpilepsyNoisy LabelsSemi-supervised 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

11.1K
Network Analysis of Foramen Ovale Electrode Recordings in Drug-resistant Temporal Lobe Epilepsy Patients
09:32

Network Analysis of Foramen Ovale Electrode Recordings in Drug-resistant Temporal Lobe Epilepsy Patients

Published on: December 18, 2016

12.3K

Related Experiment Videos

Last Updated: May 6, 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

18.0K
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

11.1K
Network Analysis of Foramen Ovale Electrode Recordings in Drug-resistant Temporal Lobe Epilepsy Patients
09:32

Network Analysis of Foramen Ovale Electrode Recordings in Drug-resistant Temporal Lobe Epilepsy Patients

Published on: December 18, 2016

12.3K

Area of Science:

  • Neuroscience
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Resting-state functional MRI (rs-fMRI) is a key tool for localizing the epileptogenic zone (EZ) in drug-resistant focal epilepsy.
  • Clinical datasets with precise EZ labels are limited, often relying on noisy resection area data as ground truth.
  • This noise arises because resection areas typically exceed the actual EZ tissue boundaries.

Purpose of the Study:

  • To develop a mathematical framework for characterizing and handling noisy labels in EZ localization using rs-fMRI.
  • To improve the accuracy of EZ localization in epilepsy patients by addressing label uncertainty.

Main Methods:

  • A multi-task deep learning framework was developed to simultaneously predict EZ localization and the probability of label noise.
  • The framework was trained on simulated data from the Human Connectome Project.
  • Evaluation was performed on both simulated and a real-world clinical epilepsy dataset.

Main Results:

  • The proposed framework demonstrated superior EZ localization performance compared to existing methods.
  • This improved accuracy was observed on both simulated and clinical datasets.
  • The method effectively identifies noisy labels, contributing to more reliable localization predictions.

Conclusions:

  • The developed mathematical framework and multi-task deep learning approach effectively address noisy labels in EZ localization.
  • This method offers a significant advancement for identifying the epileptogenic zone, crucial for surgical planning in epilepsy.
  • The findings suggest a more robust and accurate approach to rs-fMRI-based EZ localization in clinical practice.