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

Autism Spectrum Disorder01:19

Autism Spectrum Disorder

34
Autism spectrum disorder (ASD) is a neurodevelopmental condition marked by persistent deficits in social communication and interaction alongside restrictive and repetitive behaviors or interests. ASD is sometimes accompanied by intellectual impairment.
These core symptoms manifest differently among individuals, ranging from mild to severe. The disorder's complexity extends beyond its clinical presentation, encompassing a diverse range of biological, cognitive, and sociocultural influences.
34

You might also read

Related Articles

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

Sort by
Same author

Observer-based secure [Formula: see text] control for networked control systems with multiple disturbances, actuator failures, and deception attacks under adaptive event-triggered mechanism.

Scientific reports·2026
Same author

Predictive modeling for physicochemical properties of β-lactam antibiotics through eigenvalue based topological indices and non linear regression techniques.

Scientific reports·2026
Same author

A Comparative Study Between Clinical Optical Coherence Tomography (OCT) Analysis and Artificial Intelligence-Based Quantitative Evaluation in the Diagnosis of Diabetic Macular Edema.

Vision (Basel, Switzerland)·2025
Same author

Improving Voice Spoofing Detection Through Extensive Analysis of Multicepstral Feature Reduction.

Sensors (Basel, Switzerland)·2025
Same author

Beyond accuracy: The need for explainable AI in biomedical voice technology.

Computers in biology and medicine·2025
Same author

Application of Wavelet Analysis and Paraconsistent Feature Extraction in the Classification of Voice Pathologies.

Journal of voice : official journal of the Voice Foundation·2025

Related Experiment Video

Updated: May 10, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.6K

A multi-filter deep transfer learning framework for image-based autism spectrum disorder detection.

Rodrigo Colnago Contreras1,2,3, Monique Simplicio Viana4, Victor José Souza Bernardino5

  • 1Department of Science and Technology, Institute of Science and Technology, Federal University of São Paulo (UNIFESP), São José dos Campos, SP, 12247-014, Brazil. contreras@unifesp.br.

Scientific Reports
|April 24, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces a novel computational framework for early Autism Spectrum Disorder (ASD) detection using facial image analysis. The approach enhances deep learning models, significantly improving diagnostic accuracy for autism.

Keywords:
Autism spectrum disorder detectionDeep transfer learningMachine learningPattern recognitionSignal processing

More Related Videos

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping
07:11

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping

Published on: December 8, 2023

1.3K
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.2K

Related Experiment Videos

Last Updated: May 10, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.6K
Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping
07:11

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping

Published on: December 8, 2023

1.3K
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.2K

Area of Science:

  • Computational neuroscience
  • Medical image analysis
  • Machine learning for healthcare

Background:

  • Autism Spectrum Disorder (ASD) affects global population, characterized by social communication deficits and repetitive behaviors.
  • Early ASD detection is critical for effective therapeutic interventions, but traditional diagnostic methods are often subjective.
  • Advancements in computer vision offer potential for automated ASD detection, particularly through facial feature analysis.

Purpose of the Study:

  • To propose a novel computational framework for enhancing deep learning models in recognizing facial characteristics associated with ASD.
  • To address challenges in image-based ASD detection, including limited data, variable image conditions, and high-dimensional features.
  • To improve the accuracy and efficiency of automated ASD detection systems.

Main Methods:

  • Developed a framework integrating data augmentation, multi-filtering, histogram equalization, and two-stage dimensionality reduction.
  • Applied the framework to pre-trained and frozen deep learning models (e.g., ResNet-50, ViTSwin) for image pattern recognition.
  • Utilized a benchmark facial dataset comprising autistic and non-autistic individuals for experimental validation.

Main Results:

  • The proposed framework improved classification accuracy by up to 10.5% for ResNet-50 (from 79.5% to 90.0%) compared to baseline models.
  • Transformer-based models like ViTSwin achieved up to 93.5% accuracy, demonstrating the framework's robustness.
  • Consistent improvements were observed across various architectures and configurations, confirmed by ablation studies.

Conclusions:

  • The integrated framework significantly enhances deep learning-based approaches for automated ASD detection.
  • The method offers a lightweight, deterministic pipeline without requiring fine-tuning of pre-trained networks.
  • This approach shows promise as a tool for assisting in earlier and more accurate autism diagnosis.