[1]李征,宋雨.基于脑电时域特征与大脑偏侧化差异表征的抑郁症识别[J].中国医学物理学杂志,2026,43(6):825-831.[doi:DOI:10.3969/j.issn.1005-202X.2026.06.017]
　LI Zheng,SONG Yu.Depression detection based on EEG temporal-domain features and brain lateralization difference representations[J].Chinese Journal of Medical Physics,2026,43(6):825-831.[doi:DOI:10.3969/j.issn.1005-202X.2026.06.017]
点击复制

基于脑电时域特征与大脑偏侧化差异表征的抑郁症识别()

《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]

卷:
43卷
期数:
2026年第6期
页码:
825-831
栏目:
医学信号处理与医学仪器
出版日期:
2026-06-26

文章信息/Info

Title:
Depression detection based on EEG temporal-domain features and brain lateralization difference representations
文章编号:
1005-202X（2026）06-0825-07
作者:
李征1; 宋雨2
1.天津市第五中心医院（北京大学滨海医院）神经内科， 天津 300450； 2.天津理工大学电气工程与自动化学院， 天津 300384
Author(s):
LI Zheng1;  SONG Yu2
1. Department of Neurology, Tianjin Fifth Central Hospital (Peking University Binhai Hospital), Tianjin 300450, China 2. School of Electrical Engineering and Automation, Tianjin University of Technology, Tianjin 300384, China
关键词:
抑郁症; 脑电图; 深度学习; 时-空特征学习
Keywords:
Keywords: depression electroencephalogram deep learning spatio-temporal feature learning
分类号:
R318；R749.4
DOI:
DOI:10.3969/j.issn.1005-202X.2026.06.017
文献标志码:
A
摘要:
针对脑电信号时空特征耦合复杂、传统方法难以有效捕捉大脑偏侧化差异与电极关联信息，限制抑郁症诊断精度与可解释性的问题，提出一种基于MLP-Mixer的时-空特征学习网络。首先，通过权重共享的预训练MLP-Mixer学习各EEG通道内的时间上下文信息；随后，以通道级时间特征为输入，利用MLP-Mixer学习大脑左右半球电极对的差异性特征，来表征大脑偏侧化差异与电极间空间关联；最终输出抑郁症二分类诊断结果。在PRED+CT数据集上的实验结果表明，该模型取得96.14%的平均分类准确率。进一步分析显示，α、β双频段特征对抑郁识别的模型性能优于其余频段，与神经生理机制相互佐证，验证该模型特征提取机制的合理性。
Abstract:
Abstract: To address the challenges posed by the complex spatiotemporal coupling of electroencephalogram (EEG) signals, where traditional methods fail to effectively capture lateralization differences and electrode-specific information, which limits the accuracy and interpretability of depression diagnosis, this study proposes a spatiotemporal feature learning network based on MLP-Mixer. A pre-trained MLP-Mixer with shared weights is first adopted to learn temporal context information within each EEG channel. Subsequently, using channel-level temporal features as input, the MLP-Mixer learns differential features between electrode pairs in the left and right hemispheres to characterize lateralization differences and spatial correlations between electrodes. Finally, the model outputs binary classification results for depression diagnosis. Experimental results on the PRED+CT dataset demonstrate that the proposed model achieves an average classification accuracy of 96.14%. Further analysis indicates that dual-band α and β frequency features outperform features from other frequency bands in terms of model performance for depression detection. This finding is consistent with neurophysiological mechanisms, thereby validating the rationality of the models feature extraction mechanism.

相似文献/References:

[1]郭家梁,等.基于振幅-周期二维分布的脑电复杂度分析[J].中国医学物理学杂志,2016,33(6):633.[doi:10.3969/j.issn.1005-202X.2016.06.019]
[2]周静,吴效明.基于样本熵的睡眠呼吸暂停综合征脑电研究[J].中国医学物理学杂志,2016,33(7):722.[doi:10.3969/j.issn.1005-202X.2016.07.017]
　[J].Chinese Journal of Medical Physics,2016,33(6):722.[doi:10.3969/j.issn.1005-202X.2016.07.017]
[3]刘岩,李幼军,陈萌. 基于固有模态分解和深度学习的抑郁症脑电信号分类分析[J].中国医学物理学杂志,2017,34(9):963.[doi:DOI:10.3969/j.issn.1005-202X.2017.09.021]
　[J].Chinese Journal of Medical Physics,2017,34(6):963.[doi:DOI:10.3969/j.issn.1005-202X.2017.09.021]
[4]苏克阳,曾景阳,谢文钦,等. 近似熵在脑电监测麻醉深度中的应用[J].中国医学物理学杂志,2019,36(1):117.[doi:DOI:10.3969/j.issn.1005-202X.2019.01.023]
　SU Keyang,ZENG Jingyang,XIE Wenqin,et al. Application of EEG approximate entropy in monitoring the depth of anesthesia[J].Chinese Journal of Medical Physics,2019,36(6):117.[doi:DOI:10.3969/j.issn.1005-202X.2019.01.023]
[5]赵彦富,随力,李月如.基于脑电图的脑疲劳检测研究进展[J].中国医学物理学杂志,2019,36(11):1312.[doi:DOI:10.3969/j.issn.1005-202X.2019.11.013]
　ZHAO Yanfu,SUI Li,LI Yueru.Progress on brain fatigue detection based on electroencephalogram[J].Chinese Journal of Medical Physics,2019,36(6):1312.[doi:DOI:10.3969/j.issn.1005-202X.2019.11.013]
[6]赵彦富,随力,李月如.基于脑电图的脑疲劳检测研究进展[J].中国医学物理学杂志,2019,36(11):1312.[doi:DOI:10.3969/j.issn.1005-202X.2019.11.013]
　ZHAO Yanfu,SUI Li,LI Yueru.Progress on brain fatigue detection based on electroencephalogram[J].Chinese Journal of Medical Physics,2019,36(6):1312.[doi:DOI:10.3969/j.issn.1005-202X.2019.11.013]
[7]刘亚,伍倚明,李承炜,等.基于ADS1299的穿戴式脑电检测装置设计[J].中国医学物理学杂志,2019,36(11):1317.[doi:DOI:10.3969/j.issn.1005-202X.2019.11.014]
　LIU Ya,WU Yiming,LI Chengwei,et al.Design of a wearable EEG detection device based on ADS1299[J].Chinese Journal of Medical Physics,2019,36(6):1317.[doi:DOI:10.3969/j.issn.1005-202X.2019.11.014]
[8]李嘉慧,刘建鹏,潘智林,等.精神分裂症患者认知功能损伤的神经生物学基础和电生理表现[J].中国医学物理学杂志,2020,37(1):115.[doi:DOI:10.3969/j.issn.1005-202X.2020.01.021]
　LI Jiahui,LIU Jianpeng,et al.Neurobiological bases and electrophysiological manifestations of cognitive impairments in patients with schizophrenia[J].Chinese Journal of Medical Physics,2020,37(6):115.[doi:DOI:10.3969/j.issn.1005-202X.2020.01.021]
[9]付常洋,王瑜,肖洪兵,等.基于多尺度功能脑网络融合特征的抑郁症分类算法[J].中国医学物理学杂志,2020,37(4):439.[doi:DOI:10.3969/j.issn.1005-202X.2020.04.008]
　FU Changyang,WANG Yu,XIAO Hongbing,et al.Classification of depression using fusion features based on multi-scale functional brain network[J].Chinese Journal of Medical Physics,2020,37(6):439.[doi:DOI:10.3969/j.issn.1005-202X.2020.04.008]
[10]王静,孔令茵,雷炳业,等.抑郁症的脑复杂网络研究进展[J].中国医学物理学杂志,2020,37(6):780.[doi:DOI:10.3969/j.issn.1005-202X.2020.06.023]
　WANG Jing,KONG Lingyin,LEI Bingye,et al.Advances in research on complex brain networks in depression[J].Chinese Journal of Medical Physics,2020,37(6):780.[doi:DOI:10.3969/j.issn.1005-202X.2020.06.023]

备注/Memo

备注/Memo:
【收稿日期】2026-05-10 【基金项目】国家自然科学基金（62103299） 【作者简介】李征，硕士，医师，研究方向：神经病学、睡眠障碍，E-mail: Lizheng199501@163.com 【通信作者】宋雨，博士，教授，研究方向：情感计算、脑机接口控制、医疗机器人，E-mail: sy@email.tjut.edu.cn
更新日期/Last Update: 2026-06-29