|
|
基于时空图卷积神经网络的脑电信号抑郁识别研究
|
Abstract:
抑郁症已成为全球广泛流行的神经心理疾病，但传统的诊断手段因主观性影响，常导致较高的误诊率。鉴于此，开发一种更为客观且高效的抑郁症识别方法显得尤为重要。本研究构建了一种基于时空图卷积神经网络(ST-GCN)的脑电信号抑郁分类模型，将时间序列的脑电信号转化为脑拓扑图，捕捉大脑复杂的空间结构信息。同时，引入时空注意力机制，从时间和空间两个维度上有效提取关键信息。具体而言，时空图卷积神经网络结合了空间图卷积和时间卷积的优势，分别用于捕获脑电信号的空间布局特征和时间动态特性。实验结果显示，在公开的脑电数据集HUSM上，该模型的分类准确率、灵敏度以及特异度优于其他基线模型，充分验证了该模型在抑郁症识别方面的优越性能。
Depression has become a globally widespread neuropsychiatric disorder, but traditional diagnostic methods, due to their subjectivity, often lead to a high rate of misdiagnosis. In light of this, developing a more objective and efficient depression recognition method is particularly important. This study proposes a depression classification model for electroencephalogram (EEG) signals based on Spatio-Temporal Graph Convolutional Neural Network (ST-GCN). This model converts the time series of EEG signals into brain topological graphs, thereby capturing the complex spatial structure information of the brain. Meanwhile, by introducing a spatio-temporal attention mechanism, the model can effectively extract key information from both temporal and spatial dimensions. Specifically, the ST-GCN combines the advantages of spatial graph convolution and temporal convolution, used to capture the spatial layout features and temporal dynamic characteristics of EEG signals, respectively. Experimental results show that on the public EEG dataset HUSM, the model’s classification accuracy, sensitivity, and specificity are superior to other baseline models, fully verifying the superior performance of this model in depression recognition.
| [1] | 黄志强, 钟士江. 机器学习在抑郁症辅助诊断中的应用研究进展[J]. 武警医学, 2024, 35(9): 806-812. |
| [2] | Li, X., La, R., Wang, Y., Niu, J., Zeng, S., Sun, S., et al. (2019) EEG-Based Mild Depression Recognition Using Convolutional Neural Network. Medical & Biological Engineering & Computing, 57, 1341-1352. https://doi.org/10.1007/s11517-019-01959-2 |
| [3] | Saleque, S., Spriha, G., Ishraq Kamal, R., Tabassum Khan, R., Chakrabarty, A. and Parvez, M.Z. (2020) Detection of Major Depressive Disorder Using Signal Processing and Machine Learning Approaches. 2020 15th IEEE Conference on Industrial Electronics and Applications (ICIEA), Kristiansand, 9-13 November 2020, 1032-1037. https://doi.org/10.1109/iciea48937.2020.9248419 |
| [4] | Bandopadhyay, S., Nag, S., Saha, S. and Ghosh, A. (2020) Identification of Major Depressive Disorder: Using Significant Features of EEG Signals Obtained by Random Forest and Ant Colony Optimization Methods. Proceedings of the 2020 4th International Conference on Intelligent Systems, Metaheuristics & Swarm Intelligence, Thimphu Bhutan, 21-22 March 2020, 65-70. https://doi.org/10.1145/3396474.3396480 |
| [5] | Yang, J., Zhang, Z., Fu, Z., Li, B., Xiong, P. and Liu, X. (2023) Cross-Subject Classification of Depression by Using Multiparadigm EEG Feature Fusion. Computer Methods and Programs in Biomedicine, 233, Article ID: 107360. https://doi.org/10.1016/j.cmpb.2023.107360 |
| [6] | Seal, A., Bajpai, R., Agnihotri, J., Yazidi, A., Herrera-Viedma, E. and Krejcar, O. (2021) DeprNet: A Deep Convolution Neural Network Framework for Detecting Depression Using EEG. IEEE Transactions on Instrumentation and Measurement, 70, 1-13. https://doi.org/10.1109/tim.2021.3053999 |
| [7] | Yan, D., Zhao, L., Song, X., Zang, X. and Yang, L. (2022) Automated Detection of Clinical Depression Based on Convolution Neural Network Model. Biomedical Engineering, 67, 131-142. https://doi.org/10.1515/bmt-2021-0232 |
| [8] | Chen, Y., Wang, S. and Guo, J. (2023) Dctnet: Hybrid Deep Neural Network-Based EEG Signal for Detecting Depression. Multimedia Tools and Applications, 82, 41307-41321. https://doi.org/10.1007/s11042-023-14799-y |
| [9] | Soni, S., Seal, A., Yazidi, A. and Krejcar, O. (2022) Graphical Representation Learning-Based Approach for Automatic Classification of Electroencephalogram Signals in Depression. Computers in Biology and Medicine, 145, Article ID: 105420. https://doi.org/10.1016/j.compbiomed.2022.105420 |
| [10] | Zhu, J., Jiang, C., Chen, J., Lin, X., Yu, R., Li, X., et al. (2022) EEG Based Depression Recognition Using Improved Graph Convolutional Neural Network. Computers in Biology and Medicine, 148, Article ID: 105815. https://doi.org/10.1016/j.compbiomed.2022.105815 |
| [11] | Zhang, Y., Liu, X., Tang, P. and Zhang, Z. (2023) SLG-NET: Subgraph Neural Network with Local-Global Braingraph Feature Extraction Modules and a Novel Subgraph Generation Algorithm for Automated Identification of Major Depressive Disorder. In: Luo, B., et al., Eds., Neural Information Processing, Springer Nature, 31-42. https://doi.org/10.1007/978-981-99-8070-3_3 |
| [12] | Cui, W., Sun, M., Dong, Q., Guo, Y., Liao, X. and Li, Y. (2024) A Multiview Sparse Dynamic Graph Convolution-Based Region-Attention Feature Fusion Network for Major Depressive Disorder Detection. IEEE Transactions on Computational Social Systems, 11, 2691-2702. https://doi.org/10.1109/tcss.2023.3291950 |
| [13] | Chen, X., Kong, Y., Chang, H., Gao, Y., Liu, Z., Coatrieux, J., et al. (2024) MGSN: Depression EEG Lightweight Detection Based on Multiscale DGCN and SNN for Multichannel Topology. Biomedical Signal Processing and Control, 92, Article ID: 106051. https://doi.org/10.1016/j.bspc.2024.106051 |
| [14] | Acharya, U.R., Sudarshan, V.K., Adeli, H., Santhosh, J., Koh, J.E.W., Puthankatti, S.D., et al. (2015) A Novel Depression Diagnosis Index Using Nonlinear Features in EEG Signals. European Neurology, 74, 79-83. https://doi.org/10.1159/000438457 |
| [15] | Zhang, X., Li, J., Hou, K., Hu, B., Shen, J., Pan, J., et al. (2020) EEG-Based Depression Detection Using Convolutional Neural Network with Demographic Attention Mechanism. 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Montreal, 20-24 July 2020, 128-133. https://doi.org/10.1109/embc44109.2020.9175956 |
| [16] | Sharma, G., Parashar, A. and Joshi, A.M. (2021) DepHNN: A Novel Hybrid Neural Network for Electroencephalogram (EEG)-Based Screening of Depression. Biomedical Signal Processing and Control, 66, Article ID: 102393. https://doi.org/10.1016/j.bspc.2020.102393 |
| [17] | Chen, T., Guo, Y., Hao, S. and Hong, R. (2022) Exploring Self-Attention Graph Pooling with EEG-Based Topological Structure and Soft Label for Depression Detection. IEEE Transactions on Affective Computing, 13, 2106-2118. https://doi.org/10.1109/taffc.2022.3210958 |
| [18] | Wang, H., Meng, Q., Jin, L. and Hou, H. (2023) AMGCN-L: An Adaptive Multi-Time-Window Graph Convolutional Network with Long-Short-Term Memory for Depression Detection. Journal of Neural Engineering, 20, Article ID: 056038. https://doi.org/10.1088/1741-2552/ad038b |
| [19] | Liu, W., Jia, K. and Wang, Z. (2024) Graph-Based EEG Approach for Depression Prediction: Integrating Time-Frequency Complexity and Spatial Topology. Frontiers in Neuroscience, 18, Article ID: 1367212. https://doi.org/10.3389/fnins.2024.1367212 |
| [20] | Mumtaz, W., Xia, L., Mohd Yasin, M.A., Azhar Ali, S.S. and Malik, A.S. (2017) A Wavelet-Based Technique to Predict Treatment Outcome for Major Depressive Disorder. PLOS ONE, 12, e0171409. https://doi.org/10.1371/journal.pone.0171409 |
| [21] | Ellis, C.A., Lapera Sancho, M., Miller, R.L., et al. (2024) Identifying EEG Biomarkers of Depression with Novel Explainable Deep Learning Architectures. |
| [22] | Mahato, S. and Paul, S. (2019) Classification of Depression Patients and Normal Subjects Based on Electroencephalogram (EEG) Signal Using Alpha Power and Theta Asymmetry. Journal of Medical Systems, 44, 1-8. https://doi.org/10.1007/s10916-019-1486-z |
| [23] | Rafiei, A., Zahedifar, R., Sitaula, C. and Marzbanrad, F. (2022) Automated Detection of Major Depressive Disorder with EEG Signals: A Time Series Classification Using Deep Learning. IEEE Access, 10, 73804-73817. https://doi.org/10.1109/access.2022.3190502 |
