Spatial Temporal Graph Convolution with Graph Structure Self-learning for Early MCI Detection
This work addresses the problem of early Alzheimer's disease diagnosis for medical researchers by improving detection accuracy with a novel graph learning approach, though it is incremental in combining existing techniques.
The paper tackled early mild cognitive impairment detection by proposing a spatial temporal graph convolutional network that directly uses BOLD time series as features and learns optimal brain topology adaptively, achieving state-of-the-art results on the ADNI database.
Graph neural networks (GNNs) have been successfully applied to early mild cognitive impairment (EMCI) detection, with the usage of elaborately designed features constructed from blood oxygen level-dependent (BOLD) time series. However, few works explored the feasibility of using BOLD signals directly as features. Meanwhile, existing GNN-based methods primarily rely on hand-crafted explicit brain topology as the adjacency matrix, which is not optimal and ignores the implicit topological organization of the brain. In this paper, we propose a spatial temporal graph convolutional network with a novel graph structure self-learning mechanism for EMCI detection. The proposed spatial temporal graph convolution block directly exploits BOLD time series as input features, which provides an interesting view for rsfMRI-based preclinical AD diagnosis. Moreover, our model can adaptively learn the optimal topological structure and refine edge weights with the graph structure self-learning mechanism. Results on the Alzheimer's Disease Neuroimaging Initiative (ADNI) database show that our method outperforms state-of-the-art approaches. Biomarkers consistent with previous studies can be extracted from the model, proving the reliable interpretability of our method.