基于混合双线性模型的抑郁症辅助诊断

贾建; 孙新娜; 张瑞

doi:10.16152/j.cnki.xdxbzr.2024-02-001

您当前的位置：

首页 >

文章列表页 >

基于混合双线性模型的抑郁症辅助诊断

人工智能情感计算 | 更新时间：2024-04-19

- 基于混合双线性模型的抑郁症辅助诊断
- Assisted diagnosis of depression based on hybrid bilinear model
- 西北大学学报（自然科学版） 2024年54卷第2期页码：145-155
- 作者机构：
  
  1.西北大学　数学学院，陕西　西安　710127
  2.西北大学　医学大数据研究中心，陕西　西安　710127
- 作者简介：
  
  贾建，男，博士，教授，从事模式识别和智能信息处理研究，jiajian@nwu.edu.cn。
- 基金信息：
  
  国家自然科学基金面上项目(12071369);国家自然科学基金青年项目(62006189);陕西省重点研发计划资助项目(2019ZDLSF02-09-02);陕西数理基础科学研究项目(22JSZ008)
- DOI：10.16152/j.cnki.xdxbzr.2024-02-001
  中图分类号： TP391.4
- 纸质出版日期：2024-04-25，
  
  收稿日期：2023-09-28，
扫描看全文
贾建, 孙新娜, 张瑞. 基于混合双线性模型的抑郁症辅助诊断[J]. 西北大学学报（自然科学版）, 2024,54(2):145-155.

JIA Jian, SUN Xinna, ZHANG Rui. Assisted diagnosis of depression based on hybrid bilinear model[J]. Journal of Northwest University (Natural Science Edition), 2024,54(2):145-155.
贾建, 孙新娜, 张瑞. 基于混合双线性模型的抑郁症辅助诊断[J]. 西北大学学报（自然科学版）, 2024,54(2):145-155. DOI： 10.16152/j.cnki.xdxbzr.2024-02-001.

JIA Jian, SUN Xinna, ZHANG Rui. Assisted diagnosis of depression based on hybrid bilinear model[J]. Journal of Northwest University (Natural Science Edition), 2024,54(2):145-155. DOI： 10.16152/j.cnki.xdxbzr.2024-02-001.

摘要

抑郁症作为常见的慢性精神障碍疾病，其致病原因复杂且康复率较低。基于头皮脑电图提出一种使用混合双线性深度学习网络完成抑郁症辅助诊断的方法。首先，将卷积神经网络提取得到的空间特征和卷积长短时记忆网络提取得到的时空特征通过双线性方法融合成二阶混合特征，构建时空特征混合双线性模型；然后，使用脑电信号各频段的功能连接矩阵进行训练，并用不同的功能连接度量方法分析脑电信号各频段与抑郁症功能连接之间的关系；最后，在MODMA公开数据集上应用此方法。实验结果表明，使用二阶混合特征的混合双线性模型在Beta频段相关性功能连接矩阵上取得99.38%的准确率，说明了Beta频段相关性功能连接矩阵的二阶混合特征在抑郁症辅助诊断中的有效性，与其他方法相比，所提方法达到了较高的准确率，具有较好的应用前景。

Abstract

Depression

as a common chronic mental disorder

has complex causes and low recovery rates. A method for assisting the diagnosis of depression using a hybrid bilinear deep learning network based on scalp electroencephalography is proposed. Firstly

the spatial features extracted by the convolutional neural network and the spatiotemporal features extracted by the convolutional long short-term memory network are fused into second-order hybrid features through bilinear methods to construct a hybrid bilinear model. Then

the functional connectivity matrices of each frequency band of EEG signals are used to train the model

and different functional connectivity measurement methods are used to analyze the relationship between the functional connectivity of each frequency band of EEG signals and depression. Finally

this method is applied on the MODMA dataset. The experimental results showed that the hybrid bilinear model using second-order hybrid features achieved an accuracy of 99.38% on the Beta frequency band correlation functional connectivity matrix

which indicates the effectiveness of the second-order hybrid features of the Beta frequency band correlation functional connectivity matrix in the auxiliary diagnosis of depression. Compared with other methods

the proposed method achieves higher accuracy and has high application prospects.

关键词

抑郁症功能连接卷积长短时记忆网络双线性二阶特征

Keywords

depressionfunctional connectionconvolutional long-short term memorybilinearsecond-order

references

ASARNOW L D. Depression and sleep: What has the treatment research revealed and could the HPA axis be a potential mechanism？[J]. Current Opinion in Psychology, 2020, 34: 112-116.

LIANG A D, ZHAO S G, SONG J, et al. Treatment effect of exercise intervention for female college students with depression: Analysis of electroencephalogram microstates and power spectrum[J]. Sustainability, 2021, 13(12): 6822.

FU Y, ZHANG J, LI Y, et al. A novel pipeline leveraging surface-based features of small subcortical structures to classify individuals with autism spectrum disorder[J]. Progress in Neuro-Psychopharmacology & Biological Psychiatry, 2021, 104: 109989.

李斯卉, 吕可嘉, 潘敏, 等. 一种新的基于脑电信号相似性分析的癫痫性发作自动检测方法[J]. 西北大学学报(自然科学版), 2019, 49(2): 309-317.

LI S H, LYU K J, PAN M, et al. A new similarity analysis of EEG signals for automatic epileptic seizure detection [J]. Journal of Northwest University, 2019, 49(2): 309-317.

DE AGUIAR NETO F S, ROSA J L G. Depression biomarkers using non-invasive EEG: A review[J]. Neuroscience and Biobehavioral Reviews, 2019, 105: 83-93.

MILJEVIC A, BAILEY N W, MURPHY O W, et al. Alterations in EEG functional connectivity in individuals with depression: A systematic review[J]. Journal of Affective Disorders, 2023, 328: 287-302.

KAISER M. A tutorial in connectome analysis: Topological and spatial features of brain networks[J]. NeuroImage, 2011, 57(3): 892-907.

高越, 傅湘玲, 欧阳天雄, 等基于时空自适应图卷积神经网络的脑电信号情绪识别[J]. 计算机科学, 2022, 49(4): 30-36.

GAO Y, FU X L, OUYANG T X, et al. EEG emotion recognition based on spatiotemporal self-adaptive graph convolutional neural network[J]. Computer Science, 2022, 49(4): 30-36.

ZHANG M H, ZHOU H Y, LIU L Q, et al. Randomized EEG functional brain networks in major depressive disorders with greater resilience and lower rich-club coefficient[J]. Clinical Neurophysiology, 2018, 129(4): 743-758.

STAM C J, NOLTE G, DAFFERTSHOFER A. Phase lag index: Assessment of functional connectivity from multi channel EEG and MEG with diminished bias from common sources[J]. Human Brain Mapping, 2007, 28(11): 1178-1193.

LIU W Y, ZHANG C, WANG X Y, et al. Functional connectivity of major depression disorder using ongoing EEG during music perception[J]. Clinical Neurophysiology, 2020, 131(10): 2413-2422.

BASHIVAN P, RISH I, YEASIN M, et al. Learning representations from EEG with deep recurrent-convolutional neural networks[EB/OL]. (2016-02-29)[2023-07-15]. https://arxiv.org/abs/1511.06448https://arxiv.org/abs/1511.06448.

YIN Y Q, ZHENG X W, HU B, et al. EEG emotion recognition using fusion model of graph convolutional neural networks and LSTM[J]. Applied Soft Computing, 2021, 100: 106954.

杨炳新, 郭艳蓉, 郝世杰, 等. 基于数据增广和模型集成策略的图神经网络在抑郁症识别上的应用[J]. 计算机科学, 2022, 49(7): 57-63.

YANG B X, GUO Y R, HAO S J, et al. Application of graph neural network based on data augmentation and model ensemble in depression recognition[J]. Computer Science, 2022, 49(7): 57-63.

SARKAR A, SINGH A, CHAKRABORTY R. A deep learning-based comparative study to track mental depression from EEG data[J]. Neuroscience Informatics, 2022, 2(4): 100039.

SHARMA G, PARASHAR A, JOSHI A M. DepHNN: A novel hybrid neural network for electroencephalogram (EEG)-based screening of depression[J]. Biomedical Signal Processing and Control, 2021, 66: 102393.

SONG X W, YAN D D, ZHAO L L, et al. LSDD-EEGNet: An efficient end-to-end framework for EEG-based depression detection[J]. Biomedical Signal Processing and Control, 2022, 75: 103612.

WU Z Y, ZHONG X W, LIN G H, et al. Resting-state electroencephalography of neural oscillation and functional connectivity patterns in late-life depression[J]. Journal of Affective Disorders, 2022, 316: 169-176.

CAI H S, GAO Y, SUN S T, et al. MODMA dataset: A multi-modal open dataset for mental-disorder analysis[EB/OL]. (2020-03-05)[2023-07-15]. http://arxiv.org/abs/2002.09283http://arxiv.org/abs/2002.09283.

ZHANG B T, YAN G H, YANG Z F, et al. Brain functional networks based on resting-state EEG data for major depressive disorder analysis and classification[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2021, 29: 215-229.

KROENKE K, SPITZER R L. The PHQ-9: A new depression diagnostic and severity measure[J]. Psychiatric Annals, 2002, 32(9): 509-515.

SPITZER R L, KROENKE K, WILLIAMS J B W, et al. A brief measure for assessing generalized anxiety disorder: The GAD-7[J]. Archives of Internal Medicine, 2006, 166(10): 1092-1097.

ZHANG B T, ZHOU W Y, CAI H S, et al. Ubiquitous depression detection of sleep physiological data by using combination learning and functional networks[J]. IEEE Access, 2020, 8: 94220-94235.

DELORME A, MAKEIG S. EEGLAB: An open source toolbox for analysis of single-trial EEG dynamics including independent component analysis[J]. Journal of Neuroscience Methods, 2004, 134(1): 9-21.

MOVAHED R A, JAHROMI G P, SHAHYAD S, et al. A major depressive disorder classification framework based on EEG signals using statistical, spectral, wavelet, functional connectivity, and nonlinear analysis[J]. Journal of Neuroscience Methods, 2021, 358: 109209.

FRASCHINI M, DEMURU M, CROBE A, et al. The effect of epoch length on estimated EEG functional connectivity and brain network organisation[J]. Journal of Neural Engineering, 2016, 13(3): 036015.

LI Y J, CAO D, WEI L, et al. Abnormal functional connectivity of EEG gamma band in patients with depression during emotional face processing[J]. Clinical Neurophysiology, 2015, 126(11): 2078-2089.

LIN T Y, ROYCHOWDHURY A, MAJI S. Bilinear CNN models for fine-grained visual recognition[C]//2015 IEEE International Conference on Computer Vision (ICCV). Santiago: IEEE, 2015: 1449-1457.

ZHANG X W, LI J L, HOU K C, et al. EEG-based depression detection using convolutional neural network with demographic attention mechanism[C]//2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). Montreal: IEEE, 2020: 128-133.

SHI X J, CHEN Z R, WANG H, et al. Convolutional LSTM Network: A machine learning approach for precipitation nowcasting[C]//Proceedings of the 28th International Conference on Neural Information Processing Systems(NeurlPS). Montreal: ACM, 2015: 802-810.

DAVIS J, GOADRICH M. The relationship between Precision-Recall and ROC curves[C]//Proceedings of the 23rd International Conference on Machine Learning(ICML). Pittsburgh: ACM, 2006:233-240.

SUN S T, LI J X, CHEN H Y, et al. A study of resting-state EEG biomarkers for depression recognition[EB/OL]. (2020-02-23)[2023-07-15]. https://arxiv.org/abs/2002.11039https://arxiv.org/abs/2002.11039.

SHEN J, ZHANG X W, HUANG X, et al. An optimal channel selection for EEG-based depression detection via kernel-target alignment[J]. IEEE Journal of Biomedical and Health Informatics, 2021, 25(7): 2545-2556.

SONI S, SEAL A, YAZIDI A, et al. Graphical representation learning-based approach for automatic classification of electroencephalogram signals in depression[J]. Computers in Biology and Medicine, 2022, 145: 105420.

YANG L J, WEI X G, LIU F R, et al. Automatic feature learning model combining functional connectivity network and graph regularization for depression detection[J]. Biomedical Signal Processing and Control, 2023, 82: 104520.

YANG L J, WANG Y X, ZHU X R, et al. A gated temporal-separable attention network for EEG-based depression recognition[J]. Computers in Biology and Medicine, 2023, 157: 106782.

LEUCHTER A F, COOK I A, HUNTER A M, et al. Resting-state quantitative electroencephalography reveals increased neurophysiologic connectivity in depression[J]. PLoS One, 2012, 7(2): e32508.

TAS C, CEBI M, TAN O, et al. EEG power, cordance and coherence differences between unipolar and bipolar depression[J]. Journal of Affective Disorders, 2015, 172: 184-190.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据