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

Bridging Global Attention and Local Hierarchies: A Robust Hybrid Ensemble Framework With Multi-Perspective Explainability for Automated HER2-IHC Scoring.

Technology in cancer research & treatment·2026

Same author

Hybrid GA-DQL approach for efficient task mapping of IoT applications in fog computing framework.

Scientific reports·2026

Same author

Explainable Split-Learning-Based Framework for Accurate Pulmonary Nodule Classification.

Bioengineering (Basel, Switzerland)·2026

Same author

Resilient and decentralized demand-side management in smart grids using blockchain.

Scientific reports·2026

Same author

Correction: Multiclass Classification of Renal Tumor Subtypes: Addressing Diagnostic Challenges Using a Texture-Informed Deep Hybrid CNN-Transformer.

Journal of imaging informatics in medicine·2026

Same author

3D Adversarial Segmentation of Kidney-Transplant Across Multiple MRI Sequences Using Probabilistic and Anatomical Priors.

Diagnostics (Basel, Switzerland)·2026

Search research articles

Related Experiment Video

Updated: Oct 20, 2025

Dynamic Inter-subject Functional Connectivity Reveals Moment-to-Moment Brain Network Configurations Driven by Continuous or Communication Paradigms

Dynamic Inter-subject Functional Connectivity Reveals Moment-to-Moment Brain Network Configurations Driven by Continuous or Communication Paradigms

Published on: March 21, 2019

A CNN Deep Local and Global ASD Classification Approach with Continuous Wavelet Transform Using Task-Based FMRI.

Reem Haweel^1,2, Noha Seada¹, Said Ghoniemy¹

¹Faculty of Computer and Information Sciences, University of Ain Shams, Cairo 11566, Egypt.

Sensors (Basel, Switzerland)

|September 10, 2021

Summary

This study introduces a novel computer-aided diagnosis (CAD) framework using deep learning and fMRI data to identify autism spectrum disorder (ASD) in toddlers. The system achieved high accuracy, offering potential for personalized diagnosis and treatment.

Keywords:

ASD CNN CWT autism computer-aided diagnosis deep learning

More Related Videos

Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy

Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy

Published on: August 5, 2014

Localizing Function-specific Targets for Transcranial Magnetic Stimulation in the Absence of Navigation Equipment

Localizing Function-specific Targets for Transcranial Magnetic Stimulation in the Absence of Navigation Equipment

Published on: May 23, 2025

Related Experiment Videos

Last Updated: Oct 20, 2025

Dynamic Inter-subject Functional Connectivity Reveals Moment-to-Moment Brain Network Configurations Driven by Continuous or Communication Paradigms

Dynamic Inter-subject Functional Connectivity Reveals Moment-to-Moment Brain Network Configurations Driven by Continuous or Communication Paradigms

Published on: March 21, 2019

Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy

Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy

Published on: August 5, 2014

Localizing Function-specific Targets for Transcranial Magnetic Stimulation in the Absence of Navigation Equipment

Localizing Function-specific Targets for Transcranial Magnetic Stimulation in the Absence of Navigation Equipment

Published on: May 23, 2025

Area of Science:

Neuroscience
Medical Imaging
Artificial Intelligence

Background:

Autism spectrum disorder (ASD) is characterized by social and communication deficits.
Current ASD diagnosis relies on observational tools like the Autism Diagnostic Observation Schedule.
Objective, technology-driven diagnostic methods using brain imaging and machine learning are needed.

Purpose of the Study:

To propose a novel computer-aided diagnosis (CAD) framework for identifying ASD in toddlers.
To utilize task-based functional magnetic resonance imaging (fMRI) and deep learning for objective ASD assessment.
To develop a system for personalized diagnosis and treatment planning.

Main Methods:

A CAD framework employing Convolutional Neural Networks (CNNs) was developed to classify 50 ASD and 50 typically developing toddlers.
Task-based fMRI data, specifically responses to a speech task, were analyzed.
Techniques included spatial dimensionality reduction, region of interest selection, clustering, and continuous wavelet transform for feature extraction.

Main Results:

Local diagnosis on specific brain regions (cingulate gyri, superior temporal gyrus, auditory cortex, angular gyrus) achieved accuracies from 71% to 80% via four-fold cross-validation.
A fused global diagnosis reached 86% accuracy, with 82% sensitivity and 92% specificity.
A brain map illustrating ASD severity levels per brain area was generated.

Conclusions:

The proposed CAD framework demonstrates significant potential for accurate and objective ASD diagnosis in toddlers.
fMRI coupled with deep learning can identify discriminant features for ASD.
The generated brain maps can aid in personalized diagnostic and therapeutic strategies for ASD.