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

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

Histone delactylation shapes epigenetic landscapes and therapeutic stratification in hepatocellular carcinoma.

iLIVER·2026

Same author

Heterogeneity of hepatic macrophages in MASLD/MASH: Lipid-associated programs, molecular mechanisms, spatial niches, and therapeutic implications.

iLIVER·2026

Same author

Air pollution and the risk of schizophrenia: current evidence, mechanisms, and future directions.

Reviews in the neurosciences·2026

Same author

Fatty Acid Degradation (FAD) Subtype-Informed Treatment Allocation in Unresectable Hepatocellular Carcinoma (FAD-HCC-01): Protocol for a Prospective Multicentre Proof-of-Concept Study.

Journal of hepatocellular carcinoma·2026

Same author

Intratumoral Proton Density Fat Fraction Predicts the Outcome of HAIC Combined With PD-1 Inhibitors in Advanced Hepatocellular Carcinoma.

Cancer medicine·2026

Same author

β-catenin mutation reprograms ketone body metabolism to drive hepatocellular carcinoma metastasis and resistance to ketogenic therapy via transcriptional activation of OXCT1.

Cell death & disease·2026

Same journal

Evaluation of an open-face 8-channel transmit 64-channel receive 7T head coil for neuroimaging.

Frontiers in neuroscience·2026

Same journal

Acoustic stimulation in pain management: neurobiological mechanisms and clinical applications-a narrative review.

Frontiers in neuroscience·2026

Same journal

Local brain connectome parameters across the spectrum of clinical cognitive decline.

Frontiers in neuroscience·2026

Same journal

Body mass index affects EEG microstate dynamics through blood viscosity in high-altitude environments.

Frontiers in neuroscience·2026

Same journal

Disrupted glymphatic function and its relationship with sleep and cognitive impairment in ME/CFS assessed via DTI-ALPS.

Frontiers in neuroscience·2026

Same journal

Neuromorphic-inspired multi-view global-local fusion for IR-UWB radar dynamic gesture recognition.

Frontiers in neuroscience·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Sep 4, 2025

Studying Brain Function in Children Using Magnetoencephalography

Studying Brain Function in Children Using Magnetoencephalography

Published on: April 8, 2019

Graph Empirical Mode Decomposition-Based Data Augmentation Applied to Gifted Children MRI Analysis.

Xuning Chen¹, Binghua Li¹, Hao Jia¹

¹Department of Artificial Intelligence, Nankai University, Tianjin, China.

Frontiers in Neuroscience

|July 22, 2022

Summary

This summary is machine-generated.

This study introduces graph empirical mode decomposition (GEMD) for data augmentation in MRI analysis, significantly improving the classification accuracy of gifted children from 55.7% to 78% and achieving up to 93.3%.

Keywords:

BrainNetCNN GEMD MRI gifted children structural connectivity

More Related Videos

Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques

Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques

Published on: June 30, 2020

Cortical Source Analysis of High-Density EEG Recordings in Children

Cortical Source Analysis of High-Density EEG Recordings in Children

Published on: June 30, 2014

Related Experiment Videos

Last Updated: Sep 4, 2025

Studying Brain Function in Children Using Magnetoencephalography

Studying Brain Function in Children Using Magnetoencephalography

Published on: April 8, 2019

Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques

Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques

Published on: June 30, 2020

Cortical Source Analysis of High-Density EEG Recordings in Children

Cortical Source Analysis of High-Density EEG Recordings in Children

Published on: June 30, 2014

Area of Science:

Neuroscience
Machine Learning
Medical Imaging

Background:

Distinguishing gifted children from controls using structural connectivity (SC) from MRI data is challenging.
Limited dataset sizes can degrade deep neural network performance for classification tasks.
Previous feature extraction methods show promise but face data limitations.

Purpose of the Study:

To propose and evaluate a novel data augmentation method using graph empirical mode decomposition (GEMD) for enhancing MRI-based classification of gifted children.
To improve the accuracy of deep neural networks in distinguishing gifted children from normal controls.
To address the issue of limited sample sizes in neuroimaging datasets.

Main Methods:

Structural connectivity (SC) data from MRI scans were analyzed.
A data augmentation technique using graph empirical mode decomposition (GEMD) was developed to generate artificial samples.
Intrinsic mode functions (IMFs) were obtained by decomposing training samples and then randomly recombined.
The augmented dataset was used to train a deep neural network (BrainNetCNN) for classification.
Feature selection methods were also explored to identify key brain region features.

Main Results:

Data augmentation with GEMD improved average classification performance from 55.7% to 78%.
A state-of-the-art classification accuracy of 93.3% was achieved using GEMD in specific cases.
Classification accuracy improved to 93.1% when using specific features extracted from brain regions.
The GEMD method effectively increased the sample size and boosted classification accuracy for the gifted children dataset.

Conclusions:

The proposed GEMD data augmentation method is effective in enhancing classification accuracy for limited neuroimaging datasets.
GEMD significantly improves the performance of deep neural networks in distinguishing gifted children based on MRI structural connectivity.
Combining GEMD with feature selection offers a powerful approach for accurate neuroimaging-based classification.