Identifying Autism-Related Neurobiomarkers Using Hybrid Deep Learning Models

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autore principale: Chen, Ashley
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909977289949184
author Chen, Ashley
author_facet Chen, Ashley
contents Autism spectrum disorder (ASD) has been associated with structural alterations across cortical and subcortical regions. Quantitative neuroimaging enables large-scale analysis of these neuroanatomical patterns. This project used structural MRI (T1-weighted) data from the publicly available ABIDE I dataset (n = 1,112) to classify ASD and control participants using a hybrid model. A 3D convolutional neural network (CNN) was trained to learn neuroanatomical feature representations, which were then passed to a support vector machine (SVM) for final classification. Gradient-weighted class activation mapping (Grad-CAM) was applied to the CNN to visualize the brain regions that contributed most to the model predictions. The Grad-CAM difference maps showed strongest relevance along cortical boundary regions, with additional emphasis in midline frontal-temporal-parietal areas, which is broadly consistent with prior ASD neuroimaging findings.
format Preprint
id arxiv_https___arxiv_org_abs_2510_13841
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Identifying Autism-Related Neurobiomarkers Using Hybrid Deep Learning Models
Chen, Ashley
Neurons and Cognition
Machine Learning
68T07, 68T45
I.2.6; I.5.4; J.3
Autism spectrum disorder (ASD) has been associated with structural alterations across cortical and subcortical regions. Quantitative neuroimaging enables large-scale analysis of these neuroanatomical patterns. This project used structural MRI (T1-weighted) data from the publicly available ABIDE I dataset (n = 1,112) to classify ASD and control participants using a hybrid model. A 3D convolutional neural network (CNN) was trained to learn neuroanatomical feature representations, which were then passed to a support vector machine (SVM) for final classification. Gradient-weighted class activation mapping (Grad-CAM) was applied to the CNN to visualize the brain regions that contributed most to the model predictions. The Grad-CAM difference maps showed strongest relevance along cortical boundary regions, with additional emphasis in midline frontal-temporal-parietal areas, which is broadly consistent with prior ASD neuroimaging findings.
title Identifying Autism-Related Neurobiomarkers Using Hybrid Deep Learning Models
topic Neurons and Cognition
Machine Learning
68T07, 68T45
I.2.6; I.5.4; J.3
url https://arxiv.org/abs/2510.13841