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

Detection and cross-organ characterization of physiological response to microplastic stress in Panax ginseng based on hyperspectral imaging assisted with machine learning.

Talanta·2026
Same author

Correction to "High-Accuracy and Resolution Fluorescence Intensity Ratio Thermometer for Real-Time Temperature Monitoring in a Lithium-Ion Battery".

Inorganic chemistry·2026
Same author

Organoids glimpse: the nexus for diverse tumor heterogeneity.

Frontiers in cell and developmental biology·2026
Same author

Adolescent Development in Context: Longitudinal Temporal Dynamics Between Childhood Maltreatment, Uncertainty Stress, and Exploratory Behavior.

Developmental science·2026
Same author

A Network Approach to Understanding Early-Life Adversity: Linking Threat, Deprivation, and Unpredictability to Adolescent Developmental Outcomes.

Journal of interpersonal violence·2026
Same author

Patient-derived cell lines unveil COL1A2 as a predictor of docetaxel resistance in breast cancer.

Frontiers in oncology·2026

Related Experiment Video

Updated: May 30, 2025

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

15.6K

Identifying autism spectrum disorder based on machine learning for multi-site fMRI.

Li Kang1, Mubin Chen1, Jianjun Huang1

  • 1College of Electronics and Information Engineering, Shenzhen University, Shenzhen, China; the Guangdong Key Laboratory of Intelligent Information Processing, Shenzhen, China.

Journal of Neuroscience Methods
|January 28, 2025
PubMed
Summary

This study introduces a machine learning method for autism spectrum disorder (ASD) identification using multi-site fMRI data. The approach improves diagnostic accuracy by addressing data heterogeneity, achieving up to 93% accuracy in single-site and 83.5% in multi-site classifications.

Keywords:
Autism spectrum disorderClassificationFMRIGlass brainMachine learning

More Related Videos

Using Informational Connectivity to Measure the Synchronous Emergence of fMRI Multi-voxel Information Across Time
07:12

Using Informational Connectivity to Measure the Synchronous Emergence of fMRI Multi-voxel Information Across Time

Published on: July 1, 2014

12.2K
Probing the Brain in Autism Using fMRI and Diffusion Tensor Imaging
12:21

Probing the Brain in Autism Using fMRI and Diffusion Tensor Imaging

Published on: September 12, 2011

25.1K

Related Experiment Videos

Last Updated: May 30, 2025

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

15.6K
Using Informational Connectivity to Measure the Synchronous Emergence of fMRI Multi-voxel Information Across Time
07:12

Using Informational Connectivity to Measure the Synchronous Emergence of fMRI Multi-voxel Information Across Time

Published on: July 1, 2014

12.2K
Probing the Brain in Autism Using fMRI and Diffusion Tensor Imaging
12:21

Probing the Brain in Autism Using fMRI and Diffusion Tensor Imaging

Published on: September 12, 2011

25.1K

Area of Science:

  • Neuroscience
  • Machine Learning
  • Medical Imaging

Background:

  • Autism spectrum disorder (ASD) is a neurodevelopmental condition marked by social and behavioral challenges.
  • Early diagnosis of ASD is crucial for effective intervention and treatment planning.
  • Analyzing multi-site neuroimaging data for ASD is challenging due to data heterogeneity and volume.

Purpose of the Study:

  • To propose a novel machine learning technique for multi-site autism identification.
  • To address data heterogeneity and improve classification accuracy in autism diagnosis.
  • To develop a robust method for analyzing large, multi-site fMRI datasets.

Main Methods:

  • fMRI data were transformed into glass brain datasets and features extracted using LeNet5.
  • Subject-level partial correlation matrices were constructed, followed by feature selection for multi-site dataset construction.
  • A novel Split-Merge-Split (SMS) partitioning method was employed to reduce inter-site data variability and enhance classification with MLP.

Main Results:

  • The proposed method demonstrated enhanced recognition accuracy on both single-site and multi-site datasets.
  • Highest single-site classification accuracy reached 93% at the OHSU site.
  • Multi-site classification accuracy achieved 83.5%.

Conclusions:

  • The developed machine learning approach effectively identifies autism spectrum disorder using multi-site fMRI data.
  • The Split-Merge-Split method successfully mitigates data heterogeneity, improving diagnostic accuracy.
  • This technique offers a promising solution for large-scale, multi-site neuroimaging studies in autism research.