Deep Learning Approach for Screening Autism Spectrum Disorder in Children with Facial Images and Analysis of Ethnoracial Factors in Model Development and Application

Autism spectrum disorder (ASD) is a developmental disability that can cause significant social, communication, and behavioral challenges. Early intervention for children with ASD can help to improve their intellectual ability and reduces autistic symptoms. Multiple clinical researches have suggested...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Angelina Lu, Marek Perkowski
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	autism facial images machine learning deep learning race and ethnicity diagnosis Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571
Acceso en línea:	https://doaj.org/article/d9047919a928451bab78eacf7b447510
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:d9047919a928451bab78eacf7b447510
record_format	dspace
spelling	oai:doaj.org-article:d9047919a928451bab78eacf7b4475102021-11-25T16:57:32ZDeep Learning Approach for Screening Autism Spectrum Disorder in Children with Facial Images and Analysis of Ethnoracial Factors in Model Development and Application10.3390/brainsci111114462076-3425https://doaj.org/article/d9047919a928451bab78eacf7b4475102021-10-01T00:00:00Zhttps://www.mdpi.com/2076-3425/11/11/1446https://doaj.org/toc/2076-3425Autism spectrum disorder (ASD) is a developmental disability that can cause significant social, communication, and behavioral challenges. Early intervention for children with ASD can help to improve their intellectual ability and reduces autistic symptoms. Multiple clinical researches have suggested that facial phenotypic differences exist between ASD children and typically developing (TD) children. In this research, we propose a practical ASD screening solution using facial images through applying VGG16 transfer learning-based deep learning to a unique ASD dataset of clinically diagnosed children that we collected. Our model produced a 95% classification accuracy and 0.95 F1-score. The only other reported study using facial images to detect ASD was based on the Kaggle ASD Facial Image Dataset, which is an internet search-produced, low-quality, and low-fidelity dataset. Our results support the clinical findings of facial feature differences between children with ASD and TD children. The high F1-score achieved indicates that it is viable to use deep learning models to screen children with ASD. We concluded that the racial and ethnic-related factors in deep-learning based ASD screening with facial images are critical to solution viability and accuracy.Angelina LuMarek PerkowskiMDPI AGarticleautismfacial imagesmachine learningdeep learningrace and ethnicitydiagnosisNeurosciences. Biological psychiatry. NeuropsychiatryRC321-571ENBrain Sciences, Vol 11, Iss 1446, p 1446 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	autism facial images machine learning deep learning race and ethnicity diagnosis Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571
spellingShingle	autism facial images machine learning deep learning race and ethnicity diagnosis Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571 Angelina Lu Marek Perkowski Deep Learning Approach for Screening Autism Spectrum Disorder in Children with Facial Images and Analysis of Ethnoracial Factors in Model Development and Application
description	Autism spectrum disorder (ASD) is a developmental disability that can cause significant social, communication, and behavioral challenges. Early intervention for children with ASD can help to improve their intellectual ability and reduces autistic symptoms. Multiple clinical researches have suggested that facial phenotypic differences exist between ASD children and typically developing (TD) children. In this research, we propose a practical ASD screening solution using facial images through applying VGG16 transfer learning-based deep learning to a unique ASD dataset of clinically diagnosed children that we collected. Our model produced a 95% classification accuracy and 0.95 F1-score. The only other reported study using facial images to detect ASD was based on the Kaggle ASD Facial Image Dataset, which is an internet search-produced, low-quality, and low-fidelity dataset. Our results support the clinical findings of facial feature differences between children with ASD and TD children. The high F1-score achieved indicates that it is viable to use deep learning models to screen children with ASD. We concluded that the racial and ethnic-related factors in deep-learning based ASD screening with facial images are critical to solution viability and accuracy.
format	article
author	Angelina Lu Marek Perkowski
author_facet	Angelina Lu Marek Perkowski
author_sort	Angelina Lu
title	Deep Learning Approach for Screening Autism Spectrum Disorder in Children with Facial Images and Analysis of Ethnoracial Factors in Model Development and Application
title_short	Deep Learning Approach for Screening Autism Spectrum Disorder in Children with Facial Images and Analysis of Ethnoracial Factors in Model Development and Application
title_full	Deep Learning Approach for Screening Autism Spectrum Disorder in Children with Facial Images and Analysis of Ethnoracial Factors in Model Development and Application
title_fullStr	Deep Learning Approach for Screening Autism Spectrum Disorder in Children with Facial Images and Analysis of Ethnoracial Factors in Model Development and Application
title_full_unstemmed	Deep Learning Approach for Screening Autism Spectrum Disorder in Children with Facial Images and Analysis of Ethnoracial Factors in Model Development and Application
title_sort	deep learning approach for screening autism spectrum disorder in children with facial images and analysis of ethnoracial factors in model development and application
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/d9047919a928451bab78eacf7b447510
work_keys_str_mv	AT angelinalu deeplearningapproachforscreeningautismspectrumdisorderinchildrenwithfacialimagesandanalysisofethnoracialfactorsinmodeldevelopmentandapplication AT marekperkowski deeplearningapproachforscreeningautismspectrumdisorderinchildrenwithfacialimagesandanalysisofethnoracialfactorsinmodeldevelopmentandapplication
_version_	1718412865906409472

Deep Learning Approach for Screening Autism Spectrum Disorder in Children with Facial Images and Analysis of Ethnoracial Factors in Model Development and Application

Ejemplares similares