CNNG: A Convolutional Neural Networks With Gated Recurrent Units for Autism Spectrum Disorder Classification

Wenjing Jiang; Shuaiqi Liu; Hong Zhang; Xiuming Sun; Shui-Hua Wang; Jie Zhao; Jingwen Yan

doi:10.3389/fnagi.2022.948704

CNNG: A Convolutional Neural Networks With Gated Recurrent Units for Autism Spectrum Disorder Classification

Front Aging Neurosci. 2022 Jul 5:14:948704. doi: 10.3389/fnagi.2022.948704. eCollection 2022.

Authors

Wenjing Jiang^{1

2}, Shuaiqi Liu^{1

2}, Hong Zhang^{1

2}, Xiuming Sun³, Shui-Hua Wang⁴, Jie Zhao^{1

2}, Jingwen Yan⁵

Affiliations

¹ College of Electronic and Information Engineering, Hebei University, Baoding, China.
² Machine Vision Technological Innovation Center of Hebei, Baoding, China.
³ School of Mathematics and Information Science, Zhangjiakou University, Zhangjiakou, China.
⁴ School of Computer Science and Technology, Henan Polytechnic University, Jiaozuo, China.
⁵ School of Engineering, Shantou University, Shantou, China.

Abstract

As a neurodevelopmental disorder, autism spectrum disorder (ASD) severely affects the living conditions of patients and their families. Early diagnosis of ASD can enable the disease to be effectively intervened in the early stage of development. In this paper, we present an ASD classification network defined as CNNG by combining of convolutional neural network (CNN) and gate recurrent unit (GRU). First, CNNG extracts the 3D spatial features of functional magnetic resonance imaging (fMRI) data by using the convolutional layer of the 3D CNN. Second, CNNG extracts the temporal features by using the GRU and finally classifies them by using the Sigmoid function. The performance of CNNG was validated on the international public data-autism brain imaging data exchange (ABIDE) dataset. According to the experiments, CNNG can be highly effective in extracting the spatio-temporal features of fMRI and achieving a classification accuracy of 72.46%.

Keywords: ABIDE; ASD classification; CNN; CNNG; spatio-temporal features.