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

Search research articles

Related Experiment Video

Updated: Jun 18, 2026

Brain Mapping Using a Graphene Electrode Array

Brain Mapping Using a Graphene Electrode Array

Published on: October 20, 2023

Hierarchical sparse spatiotemporal graph neural network for brain graph classification.

Jiaqi Cui^1,2, Yuxin Li¹, Xiran Qu¹

¹School of Computer Science, Northwestern Polytechnical University, Xi'an, China.

|June 17, 2026

Summary

This summary is machine-generated.

Related Concept Videos

Neural Circuits

Neural Circuits

Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...

You might also read

Related Articles

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

Sort by

Same author

Passing the Baton: Succession Planning and Mentorship for Cancer Control in Low- and Middle-Income Countries.

Cancer control : journal of the Moffitt Cancer Center·2026

Same author

Goose astrovirus genotype 2 induces autophagy in goose renal tubular epithelial cells requiring the ERK2 signaling pathway: Pharmacological evidence for a pro-viral role of autophagy.

Poultry science·2026

Same author

Structural Remodeling of Phage φPNJ-6 Hoc Promotes Adhesion to the Intestinal Epithelium.

Transboundary and emerging diseases·2026

Same author

Huanglian wendan decoction attenuates hepatic inflammation and lipogenesis via inhibition of the NF-κB/HDAC1/SREBP-1c axis.

Journal of ethnopharmacology·2026

Same author

DOGT: Double-Order Graph Transformers With Adaptive Node-Group Learning.

IEEE transactions on neural networks and learning systems·2026

Same author

Repurposing the MEK inhibitor binimetinib as a dual anti-inflammatory and antifibrotic agent in pulmonary fibrosis.

Journal of thoracic disease·2026

Same journal

Bioactive carbon dots from peony seed meal for nanomedicine via circular economy.

iScience·2026

Same journal

Genetic ablation of <i>Sfxn5</i> induces mitochondrial dysfunction and precipitates lethal metabolic crisis in mice.

iScience·2026

Same journal

Expansion, functional diversification, and gene fusion events in the Ato protein family.

iScience·2026

Same journal

The pro-inflammatory cytokines IFN-α and TNF-α inhibit organoid-derived extravillous trophoblast invasion.

iScience·2026

Same journal

Urbanization compound pathways of global lung cancer incidence risk under proximal and distal interactions.

iScience·2026

Same journal

Capsid and integrase play essential apposing roles in viral ribonucleoprotein assembly during HIV-1 core morphogenesis.

iScience·2026

See all related articles

This study introduces GLNSTGNN, a novel method for brain graph classification using resting-state fMRI. It improves the identification of neurological conditions by accurately selecting brain regions and analyzing their connections.

Area of Science:

Neuroscience
Machine Learning
Medical Imaging

Background:

Resting-state fMRI (rs-fMRI) is crucial for understanding brain function and identifying neurological disorders.
Accurate classification of brain graphs is essential for personalized medicine and neurological condition diagnosis.
Existing methods struggle with sparse feature selection in complex spatiotemporal brain data.

Purpose of the Study:

To develop a hierarchical sparse spatiotemporal graph neural network (STGNN) named GLNSTGNN for brain graph classification.
To enhance the selection of informative features from rs-fMRI data for improved diagnostic accuracy.
To capture both spatial dependencies and temporal dynamics in brain activity for robust analysis.

Main Methods:

Implemented a GroupLassoNet-based hierarchical sparsity approach for feature selection.

Keywords:

computational bioinformatics neuroscience

Related Experiment Videos

Last Updated: Jun 18, 2026

Brain Mapping Using a Graphene Electrode Array

Brain Mapping Using a Graphene Electrode Array

Published on: October 20, 2023

Combined spatial graph convolution on functional connectivity with temporal convolution on BOLD signals.

Evaluated GLNSTGNN on two large rs-fMRI datasets (1,956 participants, 200 ROIs).

Main Results:

GLNSTGNN demonstrated superior discriminative performance compared to baseline methods.
The model achieved consistent selection of informative Regions of Interest (ROIs).
Interpretable subnetwork-level patterns were identified, enhancing understanding of brain connectivity.

Conclusions:

Integrating hierarchical sparsity with spatiotemporal graph learning offers a practical framework for brain graph classification.
GLNSTGNN provides a robust and interpretable method for analyzing rs-fMRI data.
This approach supports the identification of neurological conditions and personalized brain analysis.