Related Experiment Video
Updated: May 10, 2026
14:27
Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
Published on: June 26, 2013
Quantum convolution searched binary neural networks based autism spectrum disorder detection using MRI images in
G Mervin George1, N Kumareshan2
1Research scholar, Department of Electronics and Communication Engineering, Sri Eshwar College of Engineering, Coimbatore, Tamil Nadu, India.
Psychiatry Research. Neuroimaging
|May 8, 2026
Summary
A new cloud-based AI model, FPTO_QCSBNN, enhances Autism Spectrum Disorder (ASD) detection using MRI scans. This system achieves over 91% accuracy in identifying ASD, improving diagnostic speed and efficiency.
Area of Science:
- Neuroimaging
- Artificial Intelligence
- Medical Diagnostics
Background:
- Autism Spectrum Disorder (ASD) is a complex neurodevelopmental condition.
- Diagnosing ASD is challenging due to symptom heterogeneity.
- Neuroimaging techniques like MRI aid in detecting brain abnormalities associated with ASD.
Purpose of the Study:
- To propose a novel cloud-based model for improved Autism Spectrum Disorder (ASD) detection.
- To leverage advanced AI for analyzing neuroimaging data efficiently.
- To enhance the accuracy and speed of ASD diagnosis.
Main Methods:
- A cloud-based system simulated for neuroimage analysis and storage.
- Pre-processing techniques including Mid-Point filter, Region of Interest (ROI) extraction, and gamma correction.
- A novel Fractional Painting Training Based Optimization trained Quantum Convolution Searched Binary Neural Network (FPTO_QCSBNN) model for ASD detection.
Main Results:
- The FPTO_QCSBNN model achieved high performance metrics.
- Attained an accuracy of 91.37%.
- Demonstrated a True Positive Rate (TPR) of 91.32% and a True Negative Rate (TNR) of 91.89%.
Conclusions:
- The developed FPTO_QCSBNN model shows significant potential for accurate ASD detection.
- Cloud-based systems offer scalable storage and faster diagnosis for neuroimaging analysis.
- This approach can aid in overcoming the diagnostic challenges posed by ASD heterogeneity.