Spectral Brain Graph Neural Network for Prediction of Anxiety in Children with Autism Spectrum Disorder

TL;DR

This study introduces SpectBGNN, a spectral graph neural network that leverages spectral features from fMRI data to predict anxiety levels in children with ASD, outperforming existing models.

Contribution

The paper presents a novel spectral GNN model that effectively uses spectral features for predicting anxiety in ASD children, highlighting the importance of spectral analysis in brain network modeling.

Findings

Spectral features like FFT and PSD outperform correlation features in prediction.

Adding spectral filtering layers improves model performance.

SpectBGNN outperforms CPM, GAT, and BrainGNN in predicting MASC-2 scores.

Abstract

Children with Autism Spectrum Disorder (ASD) frequently exhibit comorbid anxiety, which contributes to impairment and requires treatment. Therefore, it is critical to investigate co-occurring autism and anxiety with functional imaging tools to understand the brain mechanisms of this comorbidity. Multidimensional Anxiety Scale for Children, 2nd edition (MASC-2) score is a common tool to evaluate the daily anxiety level in autistic children. Predicting MASC-2 score with Functional Magnetic Resonance Imaging (fMRI) data will help gain more insights into the brain functional networks of children with ASD complicated by anxiety. However, most of the current graph neural network (GNN) studies using fMRI only focus on graph operations but ignore the spectral features. In this paper, we explored the feasibility of using spectral features to predict the MASC-2 total scores. We proposed SpectBGNN, a graph-based network, which uses spectral features and integrates graph spectral filtering layers to extract hidden information. We experimented with multiple spectral analysis algorithms and compared the performance of the SpectBGNN model with CPM, GAT, and BrainGNN on a dataset consisting of 26 typically developing and 70 ASD children with 5-fold cross-validation. We showed that among all spectral analysis algorithms tested, using the Fast Fourier Transform (FFT) or Welch's Power Spectrum Density (PSD) as node features performs significantly better than correlation features, and adding the graph spectral filtering layer significantly increases the network's performance.