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

VIVIE: Virtually Integrated Ventricular Intervention Environment and its effectiveness as a teaching and learning tool.

International journal of computer assisted radiology and surgery·2026
Same author

Pharmacologic Therapies for Patent Ductus Arteriosus in Extremely Preterm Infants.

JAMA network open·2026
Same author

Hippocampal volume for prediction of working memory performance in patients with infantile hydrocephalus.

Journal of neurosurgery. Pediatrics·2026
Same author

Neonatal cyanosis: exploring the complexity of coexisting congenital methemoglobinaemia and pulmonary hypertension.

BMJ case reports·2026
Same author

Association of NOS3 rs1799983 Polymorphism with Cognitive Function in Patients with First Episode Depression.

Clinical psychopharmacology and neuroscience : the official scientific journal of the Korean College of Neuropsychopharmacology·2026
Same author

Subcortical morphological alterations and volume loss in infantile hydrocephalus: A surface- and volume-based analysis.

Neuroimage. Reports·2026

Related Experiment Video

Updated: Jun 6, 2025

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms
08:51

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

5.6K

Predicting cortical-thalamic functional connectivity using functional near-infrared spectroscopy and graph

Lingkai Tang1, Lilian M N Kebaya2,3,4, Homa Vahidi2

  • 1Biomedical Engineering, Faculty of Engineering, Western University, London, ON, N6A 3K7, Canada.

Scientific Reports
|November 30, 2024
PubMed
Summary

Researchers developed a machine learning method using functional near-infrared spectroscopy (fNIRS) to predict brain connectivity between the cortex and thalamus. This approach enables subcortical activity detection from cortical fNIRS data, aiding clinical brain monitoring.

Keywords:
Functional connectivityFunctional magnetic resonance imagingFunctional near-infrared spectroscopyGraph convolutional networkMachine learning

More Related Videos

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
Cerebral Blood Flow-Based Resting State Functional Connectivity of the Human Brain using Optical Diffuse Correlation Spectroscopy
07:13

Cerebral Blood Flow-Based Resting State Functional Connectivity of the Human Brain using Optical Diffuse Correlation Spectroscopy

Published on: May 27, 2020

6.6K

Related Experiment Videos

Last Updated: Jun 6, 2025

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms
08:51

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

5.6K
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
Cerebral Blood Flow-Based Resting State Functional Connectivity of the Human Brain using Optical Diffuse Correlation Spectroscopy
07:13

Cerebral Blood Flow-Based Resting State Functional Connectivity of the Human Brain using Optical Diffuse Correlation Spectroscopy

Published on: May 27, 2020

6.6K

Area of Science:

  • Neuroscience
  • Biomedical Engineering
  • Machine Learning

Background:

  • Functional near-infrared spectroscopy (fNIRS) measures cortical hemodynamic activity but cannot access subcortical structures like the thalamus.
  • The thalamus is crucial for several functional brain networks, making its connectivity assessment important for understanding brain function.

Purpose of the Study:

  • To develop and validate a machine learning approach for predicting cortical-thalamic functional connectivity using only cortical fNIRS data.
  • To assess the performance of graph convolutional networks (GCN) compared to conventional machine learning methods for this prediction task.

Main Methods:

  • Applied graph convolutional networks (GCN) to two datasets (healthy adults, neonates with early brain injuries) using fNIRS connectivity data.
  • Trained GCN models using functional magnetic resonance imaging (fMRI) connectivity data as the ground truth.
  • Investigated the impact of incorporating inter-subject connections and noise resilience within GCN models.

Main Results:

  • GCN models significantly outperformed support vector machines and feedforward neural networks in both binary classification and regression of connection strengths.
  • Incorporating inter-subject connections improved GCN model performance.
  • GCN models demonstrated resilience to noise present in fNIRS data.

Conclusions:

  • It is feasible to predict subcortical activity, specifically cortical-thalamic connectivity, from cortical fNIRS recordings using machine learning.
  • This approach could expand the clinical utility of fNIRS for monitoring brain activity in critically ill patients, including neonates.