Autism spectrum disorder detection using facial images: A performance comparison of pretrained convolutional neural networks

Autism spectrum disorder (ASD) is a complex psychological syndrome characterized by persistent difficulties in social interaction, restricted behaviours, speech, and nonverbal communication. The impacts of this disorder and the severity of symptoms vary from person to person. In most cases, symptoms...

Full description

Saved in:
Bibliographic Details
Published in:Healthcare technology letters Vol. 11; no. 4; pp. 227 - 239
Main Authors: Ahmad, Israr, Rashid, Javed, Faheem, Muhammad, Akram, Arslan, Khan, Nafees Ahmad, Amin, Riaz ul
Format: Journal Article
Language:English
Published: England John Wiley & Sons, Inc 01.08.2024
John Wiley and Sons Inc
Wiley
Subjects:
Accuracy
Autism
Behavior
biomedical imaging
Children & youth
computer based training
convolutional neural nets
Deep learning
Disease
Emotions
health care
image classification
image processing
learning (artificial intelligence)
Letter
medical computing
medical disorders
Mental disorders
Mental health
Mutation
neural nets
Neural networks
Questionnaires
Social interaction
Themed : Big Data and Artificial Intelligence in Healthcare
United States > US
image processing
medical disorders
image classification
computer based training
biomedical imaging
convolutional neural nets
learning (artificial intelligence)
medical computing
health care
neural nets
ISSN:2053-3713, 2053-3713
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Autism spectrum disorder (ASD) is a complex psychological syndrome characterized by persistent difficulties in social interaction, restricted behaviours, speech, and nonverbal communication. The impacts of this disorder and the severity of symptoms vary from person to person. In most cases, symptoms of ASD appear at the age of 2 to 5 and continue throughout adolescence and into adulthood. While this disorder cannot be cured completely, studies have shown that early detection of this syndrome can assist in maintaining the behavioural and psychological development of children. Experts are currently studying various machine learning methods, particularly convolutional neural networks, to expedite the screening process. Convolutional neural networks are considered promising frameworks for the diagnosis of ASD. This study employs different pre‐trained convolutional neural networks such as ResNet34, ResNet50, AlexNet, MobileNetV2, VGG16, and VGG19 to diagnose ASD and compared their performance. Transfer learning was applied to every model included in the study to achieve higher results than the initial models. The proposed ResNet50 model achieved the highest accuracy, 92%, compared to other transfer learning models. The proposed method also outperformed the state‐of‐the‐art models in terms of accuracy and computational cost. Experts are currently studying various machine learning methods, particularly convolutional neural networks, to expedite the screening process. Convolutional neural networks are considered promising frameworks for the diagnosis of ASD. This study employs different pre‐trained convolutional neural networks such as ResNet34, ResNet50, AlexNet, MobileNetV2, VGG16, and VGG19 to diagnose ASD and compared their performance. The proposed ResNet50 model achieved the highest accuracy, 92%, compared to other transfer learning models.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2053-3713
2053-3713
DOI:10.1049/htl2.12073