GM-VGG-Net: A Gray Matter-Based Deep Learning Network for Autism Classification

<b>Background:</b> Around 1 in 59 individuals is diagnosed with Autism Spectrum Disorder (ASD), according to CDS statistics. Conventionally, ASD has been diagnosed using functional brain regions, regions of interest, or multi-tissue-based training in artificial intelligence models. The o...

Full description

Saved in:
Bibliographic Details
Main Authors: Ebenezer Daniel, Anjalie Gulati, Shraya Saxena, Deniz Akay Urgun, Biraj Bista
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Diagnostics
Subjects:
Online Access:https://www.mdpi.com/2075-4418/15/11/1425
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850129324245516288
author Ebenezer Daniel
Anjalie Gulati
Shraya Saxena
Deniz Akay Urgun
Biraj Bista
author_facet Ebenezer Daniel
Anjalie Gulati
Shraya Saxena
Deniz Akay Urgun
Biraj Bista
author_sort Ebenezer Daniel
collection DOAJ
description <b>Background:</b> Around 1 in 59 individuals is diagnosed with Autism Spectrum Disorder (ASD), according to CDS statistics. Conventionally, ASD has been diagnosed using functional brain regions, regions of interest, or multi-tissue-based training in artificial intelligence models. The objective of the exhibit study is to develop an efficient deep learning network for identifying ASD using structural magnetic resonance imaging (MRI)-based brain scans. <b>Methods:</b> In this work, we developed a VGG-based deep learning network capable of diagnosing autism using whole brain gray matter (GM) tissues. We trained our deep network with 132 MRI T1 images from normal controls and 140 MRI T1 images from ASD patients sourced from the Autism Brain Imaging Data Exchange (ABIDE) dataset. <b>Results:</b> The number of participants in both ASD and normal control (CN) subject groups was not statistically different (<i>p</i> = 0.23). The mean age of the CN subject group was 14.62 years (standard deviation: 4.34), and the ASD group had mean age of 14.89 years (standard deviation: 4.29). Our deep learning model accomplished a training accuracy of 97% and a validation accuracy of 96% over 50 epochs without overfitting. <b>Conclusions:</b> To the best of our knowledge, this is the first study to use GM tissue alone for diagnosing ASD using VGG-Net.
format Article
id doaj-art-5fe3a345168241558b01d9d1f0eb07cd
institution OA Journals
issn 2075-4418
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Diagnostics
spelling doaj-art-5fe3a345168241558b01d9d1f0eb07cd2025-08-20T02:33:02ZengMDPI AGDiagnostics2075-44182025-06-011511142510.3390/diagnostics15111425GM-VGG-Net: A Gray Matter-Based Deep Learning Network for Autism ClassificationEbenezer Daniel0Anjalie Gulati1Shraya Saxena2Deniz Akay Urgun3Biraj Bista4Department of Diagnostic Radiology, City of Hope National Medic and Center, Duarte, CA 91010, USADepartment of Radiology, Henry Ford Hospital, Detroit, MI 48202, USADepartment of Health and Exercise Science, La Sierra University, Riverside, CA 92505, USADepartment of Diagnostic Radiology, City of Hope National Medic and Center, Duarte, CA 91010, USADepartment of Diagnostic Radiology, City of Hope National Medic and Center, Duarte, CA 91010, USA<b>Background:</b> Around 1 in 59 individuals is diagnosed with Autism Spectrum Disorder (ASD), according to CDS statistics. Conventionally, ASD has been diagnosed using functional brain regions, regions of interest, or multi-tissue-based training in artificial intelligence models. The objective of the exhibit study is to develop an efficient deep learning network for identifying ASD using structural magnetic resonance imaging (MRI)-based brain scans. <b>Methods:</b> In this work, we developed a VGG-based deep learning network capable of diagnosing autism using whole brain gray matter (GM) tissues. We trained our deep network with 132 MRI T1 images from normal controls and 140 MRI T1 images from ASD patients sourced from the Autism Brain Imaging Data Exchange (ABIDE) dataset. <b>Results:</b> The number of participants in both ASD and normal control (CN) subject groups was not statistically different (<i>p</i> = 0.23). The mean age of the CN subject group was 14.62 years (standard deviation: 4.34), and the ASD group had mean age of 14.89 years (standard deviation: 4.29). Our deep learning model accomplished a training accuracy of 97% and a validation accuracy of 96% over 50 epochs without overfitting. <b>Conclusions:</b> To the best of our knowledge, this is the first study to use GM tissue alone for diagnosing ASD using VGG-Net.https://www.mdpi.com/2075-4418/15/11/1425deep learningVGG Netautism identificationABIDE datasetbrain imaging
spellingShingle Ebenezer Daniel
Anjalie Gulati
Shraya Saxena
Deniz Akay Urgun
Biraj Bista
GM-VGG-Net: A Gray Matter-Based Deep Learning Network for Autism Classification
Diagnostics
deep learning
VGG Net
autism identification
ABIDE dataset
brain imaging
title GM-VGG-Net: A Gray Matter-Based Deep Learning Network for Autism Classification
title_full GM-VGG-Net: A Gray Matter-Based Deep Learning Network for Autism Classification
title_fullStr GM-VGG-Net: A Gray Matter-Based Deep Learning Network for Autism Classification
title_full_unstemmed GM-VGG-Net: A Gray Matter-Based Deep Learning Network for Autism Classification
title_short GM-VGG-Net: A Gray Matter-Based Deep Learning Network for Autism Classification
title_sort gm vgg net a gray matter based deep learning network for autism classification
topic deep learning
VGG Net
autism identification
ABIDE dataset
brain imaging
url https://www.mdpi.com/2075-4418/15/11/1425
work_keys_str_mv AT ebenezerdaniel gmvggnetagraymatterbaseddeeplearningnetworkforautismclassification
AT anjaliegulati gmvggnetagraymatterbaseddeeplearningnetworkforautismclassification
AT shrayasaxena gmvggnetagraymatterbaseddeeplearningnetworkforautismclassification
AT denizakayurgun gmvggnetagraymatterbaseddeeplearningnetworkforautismclassification
AT birajbista gmvggnetagraymatterbaseddeeplearningnetworkforautismclassification