کنفرانس مهندسی برق ایران

صفحه اصلی / سی و سومین کنفرانس بین المللی مهندسی برق

Identification of autism spectrum disorder based on combined analysis of structural and functional connectivity

نویسندگان :

Samane Pirmoradian¹ Farzaneh Shayegh² Jalal Zahabi³

1- دانشگاه صنعتی اصفهان 2- دانشگاه اصفهان 3- دانشگاه صنعتی اصفهان

کلمات کلیدی :

Graph signal processing (GSP)،Graph Fourier Transform (GFT،Autism Spectrum Disorder (ASD

چکیده :

Abstract—The Graph Fourier Transform (GFT), a key method in Graph Signal Processing (GSP), allows for the simultaneous analysis of brain's structural and functional connectivity. In this study, we apply GFT to process time-series data from functional Magnetic Resonance Imaging (fMRI) mapped onto a graph constructed from Diffusion Tensor Imaging (DTI). The goal is to identify distinguishing features between healthy individuals and those with Autism Spectrum Disorder (ASD). The structural connection matrix is extracted for each individual brain from its DTI image. The proposed method achieves 75% accuracy, 80% sensitivity, and 70% specificity in classification tasks, demonstrating its potential in identifying biomarkers for ASD. The results of this research serve as an initial step towards the combined use of structural and functional brain data in identifying ASD, demonstrating promising potential.