[1]计亚荣,王瑜,付常洋,等.基于典型相关分析与双模态数据融合的抑郁症辅助诊断[J].中国医学物理学杂志,2021,38(10):1316-1320.[doi:DOI:10.3969/j.issn.1005-202X.2021.10.024]
 JI Yarong,WANG Yu,FU Changyang,et al.Aided diagnosis of major depressive disorder based on canonical correlation analysis and bimodal data fusion[J].Chinese Journal of Medical Physics,2021,38(10):1316-1320.[doi:DOI:10.3969/j.issn.1005-202X.2021.10.024]
点击复制

基于典型相关分析与双模态数据融合的抑郁症辅助诊断()
分享到:

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

卷:
38卷
期数:
2021年第10期
页码:
1316-1320
栏目:
医学人工智能
出版日期:
2021-10-27

文章信息/Info

Title:
Aided diagnosis of major depressive disorder based on canonical correlation analysis and bimodal data fusion
文章编号:
1005-202X(2021)10-1316-05
作者:
计亚荣王瑜付常洋肖洪兵邢素霞
北京工商大学人工智能学院, 北京 100048
Author(s):
JI Yarong WANG Yu FU Changyang XIAO Hongbing XING Suxia
School of Artificial Intelligence, Beijing Technology and Business University, Beijing 100048, China
关键词:
抑郁症功能磁共振成像结构磁共振成像数据融合典型相关分析
Keywords:
Keywords: major depressive disorder functional magnetic resonance imaging structural magnetic resonance imaging data fusion canonical correlation analysis data
分类号:
R318;TP181
DOI:
DOI:10.3969/j.issn.1005-202X.2021.10.024
文献标志码:
A
摘要:
为了充分提取抑郁症患者的磁共振影像信息,提高抑郁症的诊断准确率,本研究将功能磁共振图像与结构磁共振图像作为研究对象,提出一种双模态数据融合的抑郁症分类算法。首先构建4种不同尺度的功能脑网络,提取功能磁共振图像的数据特征,然后使用迁移学习处理的三维密集连接卷积神经网络,提取结构磁共振图像的数据特征,接着使用典型相关分析方法融合两种特征,最后使用支持向量机对融合特征进行分类,从而将受试者识别为健康者或抑郁症患者。实验结果表明,本文提出的方法可获得89.56%的分类准确率与95.48%的召回率,与单模态数据分类相比,基于双模态数据的分类方法具有更好的分类性能。此外,典型相关分析法可以有效融合双模态的图像特征。
Abstract:
Abstract: In order to fully extract the magnetic resonance imaging (MRI) information of patients with major depressive disorder for improving the diagnostic accuracy of the disease, taking functional MRI data and structural MRI data as the research objects, a bimodal data fusion algorithm is proposed for the classification of major depressive disorder. After extracting the functional MRI data features by 4 kinds of functional brain networks with different scales, and obtaining the structural MRI data features by three-dimensional densely connected convolutional neural network processed by transfer learning, canonical correlation analysis method is used to fuse the two kinds of features, and finally support vector machine is utilized to classify the fusion features, thereby identifying the subjects as healthy or depressed. The experimental results show that the proposed method can obtain a classification accuracy of 89.56% and a recall rate of 95.48%. Compared with classification methods based on unimodal data, the classification algorithm based on bimodal data fusion has better classification performance. In addition, canonical correlation analysis is effective to fuse bimodal image features.

相似文献/References:

[1]夏丽坤,江桂华,汪天悦,等.基于局部一致性方法的广泛性焦虑障碍患者静息态功能磁共振成像[J].中国医学物理学杂志,2016,33(1):30.[doi:DOI:10.3969/j.issn.1005-202X.2016.01.007]
 [J].Chinese Journal of Medical Physics,2016,33(10):30.[doi:DOI:10.3969/j.issn.1005-202X.2016.01.007]
[2]梁思,董涛,王慧,等.一种基于功能磁共振的味觉刺激装置的设计与验证[J].中国医学物理学杂志,2016,33(1):76.[doi:10.3969/j.issn.1005-202X.2016.01.017]
[3]陈东太郎,曾卫明.基于功能磁共振成像分析不同眼睛状态下低频振幅比[J].中国医学物理学杂志,2016,33(6):588.[doi:10.3969/j.issn.1005-202X.2016.06.011]
[4]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]
[5]刘迎军,董健卫,杨志景,等.Hurst指数在功能磁共振成像静息态数据中的应用[J].中国医学物理学杂志,2016,33(8):783.[doi:10.3969/j.issn.1005-202X.2016.08.006]
 [J].Chinese Journal of Medical Physics,2016,33(10):783.[doi:10.3969/j.issn.1005-202X.2016.08.006]
[6]刘迎军,杨志景,李淑龙.静息态功能磁共振成像数据中几个常用指标的相关性[J].中国医学物理学杂志,2017,34(1):26.[doi:10.3969/j.issn.1005-202X.2017.01.006]
 [J].Chinese Journal of Medical Physics,2017,34(10):26.[doi:10.3969/j.issn.1005-202X.2017.01.006]
[7]魏明翔,高维佳,焦青,等. 青少年双相障碍缓解相患者功能磁共振成像低频振幅研究[J].中国医学物理学杂志,2017,34(3):314.[doi:10.3969/j.issn.1005-202X.2017.03.019]
 [J].Chinese Journal of Medical Physics,2017,34(10):314.[doi:10.3969/j.issn.1005-202X.2017.03.019]
[8]付令,武杰.独立成分分析在视觉运动核磁共振数据处理中的应用[J].中国医学物理学杂志,2017,34(7):676.[doi:10.3969/j.issn.1005-202X.2017.07.005]
 [J].Chinese Journal of Medical Physics,2017,34(10):676.[doi:10.3969/j.issn.1005-202X.2017.07.005]
[9]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(10):963.[doi:DOI:10.3969/j.issn.1005-202X.2017.09.021]
[10]陈浩然,高维佳,焦青,等.青少年双相障碍缓解相患者功能磁共振成像局域一致性研究[J].中国医学物理学杂志,2018,35(1):47.[doi:DOI:10.3969/j.issn.1005-202X.2018.01.010]
 CHEN Haoran,GAO Weijia,JIAO Qing,et al. Regional homogeneity in euthymic patients with pediatric bipolar disorder: a resting-state functional magnetic resonance imaging study[J].Chinese Journal of Medical Physics,2018,35(10):47.[doi:DOI:10.3969/j.issn.1005-202X.2018.01.010]
[11]段逸凡,王瑜,付常洋,等.基于双模态磁共振成像和决策层融合的抑郁症辅助诊断[J].中国医学物理学杂志,2022,39(3):378.[doi:DOI:10.3969/j.issn.1005-202X.2022.03.019]
 DUAN Yifan,WANG Yu,FU Changyang,et al.Auxiliary diagnosis of depression based on bimodal magnetic resonance imaging and decision level fusion[J].Chinese Journal of Medical Physics,2022,39(10):378.[doi:DOI:10.3969/j.issn.1005-202X.2022.03.019]
[12]郭朝晖,王瑜,马慧鋆,等.基于迁移学习和3D-WGMobileNet的青年抑郁症辅助诊断[J].中国医学物理学杂志,2024,41(4):455.[doi:DOI:10.3969/j.issn.1005-202X.2024.04.010]
 GUO Zhaohui,WANG Yu,MA Huijun,et al.Diagnosis of youth depression based on transfer learning and 3D-WGMobileNet[J].Chinese Journal of Medical Physics,2024,41(10):455.[doi:DOI:10.3969/j.issn.1005-202X.2024.04.010]

备注/Memo

备注/Memo:
【收稿日期】2021-04-09 【基金项目】北京市自然科学基金-北京市教育委员会科技计划重点项目(KZ202110011015) 【作者简介】计亚荣,硕士,主要从事图像处理、机器学习方面的研究,E-mail: 2470214219@qq.com 【通信作者】王瑜,博士,教授,主要从事图像处理与模式识别的研究,E-mail: wangyu@btbu.edu.cn
更新日期/Last Update: 2021-10-29