Exploring Adaptive Graph Topologies and Temporal Graph Networks for EEG-Based Depression Detection
Open Access
- 29 September 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Systems and Rehabilitation Engineering
- Vol. 31 (15344320) , 3947-3957
Abstract
In recent years, Graph Neural Networks (GNNs) based on deep learning techniques have achieved promising results in EEG-based depression detection tasks but still have some limitations. Firstly, most existing GNN-based methods use pre-computed graph adjacency matrices, which ignore the differences in brain networks between individuals. Additionally, methods based on graph-structured data do not consider the temporal dependency information of brain networks. To address these issues, we propose a deep learning algorithm that explores adaptive graph topologies and temporal graph networks for EEG-based depression detection. Specifically, we designed an Adaptive Graph Topology Generation (AGTG) module that can adaptively model the real-time connectivity of the brain networks, revealing differences between individuals. In addition, we designed a Graph Convolutional Gated Recurrent Unit (GCGRU) module to capture the temporal dynamical changes of brain networks. To further explore the differential features between depressed and healthy individuals, we adopt Graph Topology-based Max-Pooling (GTMP) module to extract graph representation vectors accurately. We conduct a comparative analysis with several advanced algorithms on both public and our own datasets. The results reveal that our final model achieves the highest Area Under the Receiver Operating Characteristic Curve (AUROC) on both datasets, with values of 83% and 99%, respectively. Furthermore, we perform extensive validation experiments demonstrating our proposed method’s effectiveness and advantages. Finally, we present a comprehensive discussion on the differences in brain networks between healthy and depressed individuals based on the outputs of our final model’s AGTG and GTMP modules.Keywords
Funding Information
- National Natural Science Foundation of China (62102133)
- Kaifeng Science and Technology Major Project (21ZD011)
- Jiangxi Province Science and Technology Fund (20232BCJ25026)
- Jiangxi Province applied research and cultivation program fund project (20212BAG70025)
- Ji'An Finance and Science Foundation (20211085454, 20222151704, 20222151746)
This publication has 45 references indexed in Scilit:
- Alterations of neural network organisation during rapid eye movement sleep and slow-wave sleep in major depression: Implications for diagnosis, classification, and treatmentPsychiatry Research: Neuroimaging, 2019
- SAE+LSTM: A New Framework for Emotion Recognition From Multi-Channel EEGFrontiers in Neurorobotics, 2019
- Multiple Dissociations Between Comorbid Depression and Anxiety on Reward and Punishment Processing: Evidence From Computationally Informed EEGComputational Psychiatry, 2019
- EEGNet: a compact convolutional neural network for EEG-based brain–computer interfacesJournal of Neural Engineering, 2018
- Deep learning with convolutional neural networks for EEG decoding and visualizationHuman Brain Mapping, 2017
- Discernibility matrix based dimensionality reduction for EEG signal2016
- Deep Residual Learning for Image Recognition2016
- Microstates in resting-state EEG: Current status and future directionsNeuroscience & Biobehavioral Reviews, 2015
- FASTER: Fully Automated Statistical Thresholding for EEG artifact RejectionJournal of Neuroscience Methods, 2010
- Neurophysiological Architecture of Functional Magnetic Resonance Images of Human BrainCerebral Cortex, 2005