[1]徐信毅,李斌,朱耿,等.基于时空图卷积神经网络的精神分裂症识别[J].中国医学物理学杂志,2024,41(2):227-232.[doi:DOI:10.3969/j.issn.1005-202X.2024.02.016]
　XU Xinyi,LI Bin,ZHU Geng,et al.Spatial-temporal graph convolutional neural network for schizophrenia recognition[J].Chinese Journal of Medical Physics,2024,41(2):227-232.[doi:DOI:10.3969/j.issn.1005-202X.2024.02.016]
点击复制

基于时空图卷积神经网络的精神分裂症识别()
分享到：

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

卷:
41卷
期数:
2024年第2期
页码:
227-232
栏目:
医学信号处理与医学仪器
出版日期:
2024-03-13

文章信息/Info

Title:
Spatial-temporal graph convolutional neural network for schizophrenia recognition
文章编号:
1005-202X（2024）02-0227-06
作者:
徐信毅1; 李斌2; 朱耿3; 周宇星1; 林萍1; 李晓欧1; 2; 3
1.上海理工大学健康与科学工程学院， 上海 200093； 2.上海市杨浦区精神卫生中心， 上海 200093； 3.上海健康医学院医疗器械学院， 上海 201318
Author(s):
XU Xinyi1;  LI Bin2;  ZHU Geng3;  ZHOU Yuxing1;  LIN Ping1;  LI Xiaoou1;  2;  3
1. School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China 2. Shanghai Yangpu District Mental Health Center, Shanghai 200093, China 3. School of Medical Instruments, Shanghai University of Medicine and Health Sciences, Shanghai 201318, China
关键词:
精神分裂症; 时频特征; 空频特征; 图神经网络
Keywords:
Keywords: schizophrenia temporal-frequency characteristic spatial-frequency characteristic graph neural network
分类号:
R318；TP183
DOI:
DOI:10.3969/j.issn.1005-202X.2024.02.016
文献标志码:
A
摘要:
提出一种基于时空图卷积神经网络的精神分裂症患者分类方法，与过往仅分析脑电中的时频特征而忽略各脑区之间空间特征的主流方法不同，模型主要通过用不同通道之间小波相干系数构成的邻接矩阵和脑电序列进行图卷积的方式获取其中的空频特征，再通过一维时间卷积获取其中的时频特征，经过多次卷积后将处理过的矩阵扁平化后输入分类模型。实验结果表明本文方法在公开数据集Zenodo上的分类准确率达96.32%，证明本文方法的有效性，也证明融合时频、空频特征对精神分裂症诊断的优势。
Abstract:
Abstract: A spatial-temporal convolutional neural network-based method is proposed for schizophrenia classification. Unlike the mainstream methods that only analyze the temporal frequency features in EEG and ignore the spatial features between brain regions, the model mainly obtains the spatial-frequency features by convolving the adjacency matrix composed of wavelet coherence coefficients between different channels and EEG sequences, and then extracts the temporal-frequency features through one-dimensional temporal convolution. The processed matrix is flattened after multiple convolutions and input to the classification model. Experimental results show that the method has a classification accuracy of 96.32% on the publicly available dataset Zenodo, demonstrating its effectiveness and exhibiting the advantages of fusing temporal-frequency and spatial-frequency features for schizophrenia diagnosis.

相似文献/References:

[1]杨勇哲,黄飚,冀泓锞,等.精神分裂症的磁共振影像学研究进展[J].中国医学物理学杂志,2016,33(8):848.[doi:10.3969/j.issn.1005-202X.2016.08.019]
　[J].Chinese Journal of Medical Physics,2016,33(2):848.[doi:10.3969/j.issn.1005-202X.2016.08.019]
[2]张越,杨勇哲,吴逢春,等.基于多模态磁共振影像的精神分裂症患者多特征分类研究[J].中国医学物理学杂志,2017,34(1):99.[doi:10.3969/j.issn.1005-202X.2017.01.020]
　[J].Chinese Journal of Medical Physics,2017,34(2):99.[doi:10.3969/j.issn.1005-202X.2017.01.020]
[3]张娜,王瑜,周文,等. 正则化多任务学习在精神分裂症核磁共振成像图像分类中的应用[J].中国医学物理学杂志,2018,35(7):790.[doi:DOI:10.3969/j.issn.1005-202X.2018.07.010]
　ZHANG Na,WANG Yu,ZHOU Wen,et al. Application of regularized multi-task learning in schizophrenia MRI data classification[J].Chinese Journal of Medical Physics,2018,35(2):790.[doi:DOI:10.3969/j.issn.1005-202X.2018.07.010]
[4]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(2):115.[doi:DOI:10.3969/j.issn.1005-202X.2020.01.021]
[5]李刚,韩德鹏,刘强伟,等.基于典型相关稀疏自编码器的精神分裂症的分类[J].中国医学物理学杂志,2020,37(3):391.[doi:DOI:10.3969/j.issn.1005-202X.2020.03.025]
　LI Gang,HAN Depeng,LIU Qiangwei,et al.Classification of schizophrenia based on deep canonically correlated sparse autoencoder[J].Chinese Journal of Medical Physics,2020,37(2):391.[doi:DOI:10.3969/j.issn.1005-202X.2020.03.025]
[6]谢忠翔,武杰,项华中.基于稀疏表示变量选择方法的影像遗传学数据分析[J].中国医学物理学杂志,2020,37(5):584.[doi:10.3969/j.issn.1005-202X.2020.05.010]
　XIE Zhongxiang,WU Jie,XIANG Huazhong.Sparse representation-based variable selection algorithm for analysis of imaging genetics data[J].Chinese Journal of Medical Physics,2020,37(2):584.[doi:10.3969/j.issn.1005-202X.2020.05.010]

备注/Memo

备注/Memo:
【收稿日期】2023-10-26 【基金项目】上海市科委地方院校能力建设项目（22010502400）；上海健康医学院精神卫生临床研究中心项目（20MC2020005）；上海市杨浦区技术委员会卫生健康委员会科研项目（YPM202114） 【作者简介】徐信毅，硕士研究生，研究方向：生物医学信号处理，E-mail: 1254841987@qq.com 【通信作者】李晓欧，博士，教授，研究方向：人体智能感知技术与穿戴式医疗器械，E-mail: bradyli@163.com
更新日期/Last Update: 2024-02-27