Deep CNN Architectures for Autism Spectrum Disorder Detection in Neuroimaging Data
DOI:
https://doi.org/10.47392/IRJAEH.2025.0290Keywords:
Autism Spectrum Disorder (ASD), Convolutional Neural Networks (CNNs)Abstract
Autism Spectrum Disorder (ASD) creates neurological developmental difficulties which lead to problems with social contact and communication abilities and repetitive patterns of conduct. Detection of ASD needs to happen early and accurately because this enables prompt support services. This research demonstrates deep Convolutional Neural Networks (CNNs) for ASD detection through TensorFlow which stands as one of the most popular deep learning frameworks. A framework built with a complete dataset which includes neuroimaging information and behavioral evaluations with genetic factors trains a CNN model effectively to detect ASD patterns. By designing its framework systematically, the model operates to find complex features in its input data while this process boosts diagnostic performance. The deep CNN method achieves better ASD classification than established strategies while utilizing TensorFlow as its implementation platform according to initial tests. The research demonstrates deep learning techniques enable better early ASD detection which benefits both healthcare professionals and ASD research scientists in their field of work.
Downloads
Downloads
Published
Issue
Section
License
Copyright (c) 2025 International Research Journal on Advanced Engineering Hub (IRJAEH)

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.