Spatial–temporal graph convolutional network for Alzheimer classification based on brain functional connectivity imaging of electroencephalogram

Abstract

Functional connectivity of the human brain, representing statistical dependence of information flow between cortical regions, significantly contributes to the study of the intrinsic brain network and its functional mechanism. To fully explore its potential in the early diagnosis of Alzheimer's disease (AD) using electroencephalogram (EEG) recordings, this article introduces a novel dynamical spatial-temporal graph convolutional neural network (ST-GCN) for better classification performance. Different from existing studies that are based on either topological brain function characteristics or temporal features of EEG, the proposed ST-GCN considers both the adjacency matrix of functional connectivity from multiple EEG channels and corresponding dynamics of signal EEG channel simultaneously. Different from the traditional graph convolutional neural networks, the proposed ST-GCN makes full use of the constrained spatial topology of functional connectivity and the discriminative dynamic temporal information represented by the 1D convolution. We conducted extensive experiments on the clinical EEG data set of AD patients and Healthy Controls. The results demonstrate that the proposed method achieves better classification performance (92.3%) than the state-of-the-art methods. This approach can not only help diagnose AD but also better understand the effect of normal ageing on brain network characteristics before we can accurately diagnose the condition based on resting-state EEG.

Electroencephalography and mild cognitive impairment research: A scoping review and bibliometric analysis (ScoRBA)

“…This model not only helps detect AD but also helps better understand the impact of natural aging on brain network features. It achieved better classification performance than state-of-the-art methods [46] .…”

“…This model can learn complex patterns from raw EEG signals and achieve high classification accuracy. A recent study by Shan et al [46] proposed a novel dynamical spatio-temporal graph, CNN, to fully exploit the constrained spatial topology of functional connectivity and the discriminative dynamic temporal information represented by 1D convolution. The model outperformed cutting-edge approaches in terms of classification performance by 92.3%.…”

EEG Conformer: Convolutional Transformer for EEG Decoding and Visualization

“…Sakhavi et al [28] used CNN to learn temporal information from the filter bank CSP features and select architecture parameters for each subject. Shan et al [29] leveraged the cross-channel topological connectivity by introducing graphs to spatialtemporal CNN. Hong et al [30] extracted subject-invariant features via CNN in an adversarial learning-driven domain adaptation framework.…”

A novel spatiotemporal graph convolutional network framework for functional connectivity biomarkers identification of Alzheimer’s disease

“…Therefore, we propose a novel model called spatiotemporal graph convolution combined with gradient-based class activation mapping (STGC-GCAM) to identify imaging biomarkers for AD and its stages. In this model, spatial–temporal GCN (ST-GCN) obtains disease diagnostic features by integrating spatiotemporal information from the brain’s functional connection network [ 26 ]. Specifically, spatial convolutions operate on the spatial dimension, while temporal convolutions operate on the temporal dimension [ 27 ].…”