Related Concept Videos
You might also read
Related Articles
Articles linked to this work by shared authors, journal, and citation graph.
Sort by
Same author
A New Approach for Multimodal Usage of Gene Expression and Its Image Representation for the Detection of Alzheimer's Disease.
Biomolecules·2023
Same author
Prediction of Alzheimer's Disease by a Novel Image-Based Representation of Gene Expression.
Genes·2022
Same journal
"Don't Promise Something You can't Deliver:" Caregivers' Advice for Improving Services to Adolescents and Young Adults with Autism.
Autism research and treatment·2023
Same journal
An Overview of the Available Intervention Strategies for Postural Balance Control in Individuals with Autism Spectrum Disorder.
Autism research and treatment·2022
Same journal
Balance and Vestibular Deficits in Pediatric Patients with Autism Spectrum Disorder: An Underappreciated Clinical Aspect.
Autism research and treatment·2022
Same journal
Severity of Child Autistic Symptoms and Parenting Stress in Mothers of Children with Autism Spectrum Disorder in Japan and USA: Cross-Cultural Differences.
Autism research and treatment·2022
Same journal
Effectiveness and Adverse Effects of Risperidone in Children with Autism Spectrum Disorder in a Naturalistic Clinical Setting at a University Hospital in Oman.
Autism research and treatment·2022
Same journal
Exploring a Role for Parental Mental Health in Perception and Reports of Pain on Behalf of Children with Autism Spectrum Disorder.
Autism research and treatment·2021
Related Experiment Video
Updated: Jul 7, 2025

14:27
Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
Published on: June 26, 2013
15.7K
Autism Spectrum Disorder Detection by Hybrid Convolutional Recurrent Neural Networks from Structural and Resting
Emel Koc1, Habil Kalkan2, Semih Bilgen1
1Istanbul Okan University, Istanbul, Türkiye.
Autism Research and Treatment
|December 28, 2023
Summary
This study enhances autism spectrum disorder (ASD) diagnosis using machine learning and neuroimaging. Hybrid neural networks achieved 96% accuracy by combining structural and functional MRI data.
Area of Science:
- Neuroscience
- Artificial Intelligence
- Medical Imaging
Background:
- Autism spectrum disorder (ASD) diagnosis relies on behavioral and cognitive assessments.
- Accurate diagnosis is crucial for early intervention and effective treatment.
- Neuroimaging offers objective biomarkers for understanding brain differences in ASD.
Purpose of the Study:
- To improve the accuracy of autism spectrum disorder (ASD) diagnosis.
- To leverage multiple neuroimaging modalities and machine learning for classification.
- To identify key brain connectivity features associated with ASD.
Main Methods:
- Utilized structural MRI (s-MRI) and resting-state functional MRI (rs-f-MRI) data from the ABIDE repository.
- Applied machine learning algorithms, including hybrid convolutional recurrent neural networks (CNNs/RNNs).
- Employed early, late, and cross-fusion strategies to integrate multimodal imaging data.
Main Results:
- Hybrid CNN-RNN models outperformed individual CNN or RNN models.
- Achieved a diagnostic accuracy of 96% by fusing s-MRI and rs-f-MRI data.
- Identified significant functional and anatomical connectivity metrics for ASD classification.
Conclusions:
- Multimodal neuroimaging combined with advanced ML significantly enhances ASD diagnostic accuracy.
- Hybrid neural networks offer a promising approach for objective ASD diagnosis.
- This method provides a more robust diagnostic tool compared to previous approaches.

