Kyoung-Won Park  Seok-Jun Bu  Sung-Bae Cho

10.5626/JOK.2022.49.5.354

autism spectrum disorder dynamic connectivity 4D functional magnetic resonance imaging Deep Learning

Considering a hypothesis that abnormalities in the superior temporal sulcus (STS) connected with visual cortex regions can be a critical sign of ASD, autism spectrum disorder, a model is required to exploit the brain functional connectivity between the STS and visual cortex to reinforce the neurobiological evidence. This paper proposes a deep learning model comprising attention and convolutional recurrent neural networks that can select and extract the time-series pattern of dynamic connectivity between the two regions within the brain based on observations. By integration of the extracted autism disorder features from dynamic connectivity through attention with the structure containing interlayer connections to preserve the functional connectivity loss within a neural network, the model extracts the connectivity between the STS and visual cortex, leading to an increase in generalization performance. A 10-fold cross-validation to compare the performance shows that the proposed model outperforms the state-of-the-art models by achieving an improvement of 4.90% in the ASD classification. Additionally, we use the proposed method to diagnose ASD by visualizing dynamic brain connectivity of the neural network layers.