抑郁症EEG诊断的类脑学习模型

doi:10.3778/j.issn.1002-8331.2209-0077

摘要/Abstract

摘要： 抑郁症是一种全球性精神疾病，传统诊断方法主要依靠量表与医生的主观评估，无法有效识别症状，甚至存在误诊的风险。基于生理信号的深度学习辅助诊断有望改善传统缺乏生理学依据的方法。然而，传统深度学习方法依赖巨大算力，且大多是端到端的网络学习。这些学习方法也缺乏生理可解释性，限制了辅助诊断临床应用。提出一种用于抑郁症脑电图（electroencephalogram，EEG）诊断的类脑学习模型，在功能层面，构建脉冲神经网络对抑郁症与健康个体进行分类，精度超过97.5%，相比深度卷积方法，脉冲方法降低了能耗；在结构层面，利用复杂网络建立脑连接的空间拓扑并分析其图特征，找出了抑郁症个体潜在的脑功能连接异常机制。

关键词: 类脑学习, 脉冲神经网络, 复杂网络特征, 抑郁症, 脑电图

Abstract: Depression is a global mental disease. Conventional diagnostic methods mainly depend on the scale and the subjective assessment of doctors, which cannot guarantee effective identification of symptoms and may have the risk of misdiagnosis. Using physiological signals, deep learning methods are expected to improve those diagnostic methods that lack the support of physiological basis. Traditional deep learning methods, however, rely on huge computing power, and most of them are end-to-end network learning. There also lacks physiological interpretability in those learning methods, limiting the clinical application of auxiliary diagnosis. This paper proposes a brain-inspired learning model for electroencephalogram (EEG) diagnosis of depression. At the functional level, a spiking neural network is constructed to classify depression and healthy individuals with an accuracy of more than 97.5%, which reduces the energy consumption compared to deep convolutional methods. At the structural level, the spatial topology of brain connectivity is established by using complex network and its graph characteristics are analyzed to find out the underlying mechanism of abnormal brain functional connectivity in individuals with depression.

Key words: brain-inspired learning, spiking neural network, complex network feature, depression, electroencephalogram (EEG)

曾昊辰, 胡滨, 关治洪. 抑郁症EEG诊断的类脑学习模型[J]. 计算机工程与应用, 2024, 60(3): 157-164.

ZENG Haochen, HU Bin, GUAN Zhihong. Brain-Inspired Learning Model for EEG Diagnosis of Depression[J]. Computer Engineering and Applications, 2024, 60(3): 157-164.

参考文献

[1] LEMOULT J, GOTLIB I H. Depression: a cognitive perspective[J]. Clinical Psychology Review, 2019, 69: 51-66.
[2] 王凤琴, 柯亨进. 卷积神经网络及其分析在抑郁症判别中的应用[J]. 计算机工程与应用, 2021, 57(5): 245-250.
WANG F Q, KE H J. Application of CNN and its analysis in depression identification[J]. Computer Engineering and Applications, 2021, 57(5): 245-250.
[3] GHAZI D, LECLERC Y. Collecting and analyzing depression notes using IBM social media analytics[C]//Proceedings of the 25th Annual International Conference on Computer Science and Software Engineering, 2015: 271-273.
[4] ACHARYA U R, OH S L, HAGIWARA Y, et al. Automated EEG-based screening of depression using deep convolutional neural network[J]. Computer Methods and Programs in Biomedicine, 2018, 161: 103-113.
[5] UDDIN M Z, DYSTHE K K, F?LSTAD A, et al. Deep learning for prediction of depressive symptoms in a large textual dataset[J]. Neural Computing and Applications, 2022, 34(1): 721-744.
[6] SHAH D, WANG G Y, DOBORJEH M, et al. Deep learning of EEG data in the neucube brain-inspired spiking neural network architecture for a better understanding of depression[C]//International Conference on Neural Information Processing. Cham: Springer, 2019: 195-206.
[7] UYULAN C, ERGüZEL T T, UNUBOL H, et al. Major depressive disorder classification based on different convolutional neural network models: deep learning approach[J]. Clinical EEG and Neuroscience, 2021, 52(1): 38-51.
[8] MUMTAZ W, QAYYUM A. A deep learning framework for automatic diagnosis of unipolar depression[J]. International Journal of Medical Informatics, 2019, 132: 103983.
[9] 许绍显, 廖小飞, 邵志远, 等. 图数据中极大团枚举问题的求解: 研究现状与挑战[J]. 中国科学: 信息科学, 2022, 52(5): 784-803.
XU S X, LIAO X F, SHAO Z Y, et al. Maximal clique enumeration problem on graphs: status and challenges[J]. Scientia Sinica Informationis, 2022, 52(5): 784-803.
[10] 焦李成. 类脑感知与认知的挑战与思考[J]. 智能系统学报, 2022, 17(1): 213-216.
JIAO L C. Challenges and reflections on brain-like perception and cognition[J]. CAAI Transactions on Intelligent Systems, 2022, 17(1): 213-216.
[11] HU B, GUAN Z H, CHEN G, et al. Neuroscience and network dynamics toward brain-inspired intelligence[J]. IEEE Transactions on Cybernetics, 2022, 52(10): 10214-10227.
[12] CAI H, GAO Y, SUN S, et al. Modma dataset: a multi-modal open dataset for mental-disorder analysis[J]. arXiv:2002.09283, 2020.
[13] WANG Z, TONG Y, HENG X. Phase-locking value based graph convolutional neural networks for emotion recognition[J]. IEEE Access, 2019, 7: 93711-93722.
[14] ST?CKL C, MAASS W. Optimized spiking neurons can classify images with high accuracy through temporal coding with two spikes[J]. Nature Machine Intelligence, 2021, 3(3): 230-238.
[15] RUECKAUER B, LUNGU I A, HU Y, et al. Conversion of continuous-valued deep networks to efficient event-driven networks for image classification[J]. Frontiers in Neuroscience, 2017, 11: 682.
[16] KHERADPISHEH S R, MASQUELIER T. Temporal backpropagation for spiking neural networks with one spike per neuron[J]. International Journal of Neural Systems, 2020, 30(6): 2050027.
[17] FRISTON K J. Modalities, modes, and models in functional neuroimaging[J]. Science, 2009, 326(5951): 399-403.
[18] HUMPHRIES M D, GURNEY K, PRESCOTT T J. The brainstem reticular formation is a small-world, not scale-free, network[J]. Proceedings of the Royal Society B: Biological Sciences, 2006, 273(1585): 503-511.
[19] 张驰, 郭媛, 黎明. 人工神经网络模型发展及应用综述[J]. 计算机工程与应用, 2021, 57(11): 57-69.
ZHANG C, GUO Y, LI M. Review of development and application of artificial neural network models[J]. Computer Engineering and Applications, 2021, 57(11): 57-69.
[20] TRAN Y, CRAIG A, CRAIG R, et al. The influence of mental fatigue on brain activity: evidence from a systematic review with meta‐analyses[J]. Psychophysiology, 2020, 57(5): e13554.
[21] HOS?OVECKY M, BABU?IAK B. Brain activity: beta wave analysis of 2D and 3D serious games using EEG[J]. Journal of Applied Mathematics, Statistics and Informatics, 2017, 13(2): 39-53.
[22] MYSIN I, SHUBINA L. From mechanisms to functions: the role of theta and gamma coherence in the intrahippocampal circuits[J]. Hippocampus, 2022, 32(5): 342-358.
[23] SEMKOVSKA M, QUINLIVAN L, O’GRADY T, et al. Cognitive function following a major depressive episode: a systematic review and meta-analysis[J]. The Lancet Psychiatry, 2019, 6(10): 851-861.
[24] ROSSINI P M, DI IORIO R, BENTIVOGLIO M, et al. Methods for analysis of brain connectivity: an IFCN-sponsored review[J]. Clinical Neurophysiology, 2019, 130(10): 1833-1858.
[25] HU L, XIAO M, AI M, et al. Disruption of resting-state functional connectivity of right posterior insula in adolescents and young adults with major depressive disorder[J]. Journal of Affective Disorders, 2019, 257: 23-30.
[26] PADMANABHAN J L, COOKE D, JOUTSA J, et al. A human depression circuit derived from focal brain lesions[J]. Biological Psychiatry, 2019, 86(10): 749-758.
[27] PERRY A, ROBERTS G, MITCHELL P B, et al. Connectomics of bipolar disorder: a critical review, and evidence for dynamic instabilities within interoceptive networks[J]. Molecular Psychiatry, 2019, 24(9): 1296-1318.
[28] MAGLANOC L A, LANDR? N I, JONASSEN R, et al. Data-driven clustering reveals a link between symptoms and functional brain connectivity in depression[J]. Biological Psychiatry: Cognitive Neuroscience and Neuroimaging, 2019, 4(1): 16-26.
[29] MIAO H, ZHONG S, LIU X, et al. Childhood trauma history is linked to abnormal brain metabolism of non-medicated adult patients with major depressive disorder[J]. Journal of Affective Disorders, 2022, 302: 101-109.
[30] FITZGERALD P J, WATSON B O. Gamma oscillations as a biomarker for major depression: an emerging topic[J]. Translational Psychiatry, 2018, 8(1): 1-7.