《计算机应用研究》|Application Research of Computers

基于独立成分分析功能连接的抑郁症分类研究

Independent component analysis based functional connectivity for classification of depression

免费全文下载 (已被下载 次)  
获取PDF全文
作者 茂旭,杨剑,杨阳
机构 1.北京工业大学 a.信息学部;b.北京未来网络科技高精尖创新中心,北京 100124;2.磁共振成像脑信息学北京市重点实验室,北京 100124;3.脑信息智慧服务北京市国际科技合作基地,北京 100124
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2018)06-1641-04
DOI 10.3969/j.issn.1001-3695.2018.06.009
摘要 已有的功能连接研究大多根据脑图谱构建全脑功能连接,但目前可选用的脑图谱种类有限,且采用不同脑图谱的分析结果可能存在一定的差异。针对上述问题,利用独立成分分析方法研究了抑郁症辅助诊断问题。首先利用组独立成分分析提取独立成分并构建全脑功能连接网络,然后采用BoostFS(boosting feature selection)方法进行特征选择,最后应用多元模式分析方法对20名抑郁症患者和21名健康被试进行分类。实验分类准确率达到95.12%,错分了一名抑郁症患者和一名健康被试。进一步分析表明,具有较强分辨能力的脑网络为感觉运动网络、默认网络和视觉网络,与已有基于脑图谱的研究结果基本一致,从而说明了基于独立成分分析方法的合理性,使其可能成为抑郁症辅助诊断的一种新方法。
关键词 功能磁共振成像;抑郁症;全脑功能连接;独立成分分析
基金项目 国家“973”计划资助项目(2014CB744600)
国家自然科学基金资助项目(61420106005)
北京市自然科学基金资助项目(4164080)
本文URL http://www.arocmag.com/article/01-2018-06-009.html
英文标题 Independent component analysis based functional connectivity for classification of depression
作者英文名 Mao Xu, Yang Jian, Yang Yang
机构英文名 1.a.FacultyofInformationTechnology,b.BeijingFutureNetworkTechnologyHighTechInnovationCenter,BeijingUniversityofTechnology,Beijing100124,China;2.BeijingKeyLaboratoryofMagneticResonanceImaging&BrainInformatics,Beijing100124,China;3.BeijingInternationalCollaborationBaseonBrainInformatics&WisdomServices,Beijing100124,China
英文摘要 Previous functional connectivity studies usually utilize brain atlas to construct whole-brain functional connectivity network.However, available brain atlas is limited and the results using different brain atlas might be different.In order to overcome the problems above, this paper investigated the computer aided diagnosis of depression using independent component analysis method.Firstly, it extracted independent components to construct whole-brain functional connectivity network, and then used BoostFS method for feature selection.Finally, it employed multivariate pattern analysis method to classify 20 depressed patients and 21 healthy controls.The classification accuracy of the proposed method was up to 95.12%(only one healthy control subject and one depressed patient were classified incorrectly).Further analysis demonstrates that the most discriminative brain networks are sensorimotor network, default mode network and visual network, which is consistent with the existing results of brain atlas.This indicates that the proposed independent component analysis based method is reasonable, and it might be a new method for the diagnosis of depression.
英文关键词 functional magnetic resonance imaging; depression; whole-brain functional connectivity; independent component analysis
参考文献 查看稿件参考文献
  [1] Wise T, Cleare A J, Herane A, et al. Diagnostic and therapeutic utility of neuroimaging in depression:an overview[J] . Neuropsychiatric Disease & Treatment, 2014, 10(8):1509-1522.
[2] Craddock R C, Holtzheimer P E, Hu Xiaoping, et al. Disease state prediction from resting state functional connectivity[J] . Magnetic Resonance in Medicine, 2009, 62(6):1619-1628.
[3] Anand A, Li Yu, Wang Yang, et al. Resting state corticolimbic connectivity abnormalities in unmedicated bipolar disorder and unipolar depression[J] . Psychiatry Research, 2009, 171(3):189-198. [4] Frodl T, Scheuerecker J, Albrecht J, et al. Neuronal correlates of emotional processing in patients with major depression[J] . World Journal of Biological Psychiatry, 2009, 10(3):202-208.
[5] Greicius M D, Flores B H, Menon V, et al. Resting-state functional connectivity in major depression:abnormally increased contributions from subgenual cingulate cortex and thalamus[J] . Biological Psychiatry, 2007, 62(5):429-437.
[6] Sheline Y I, Price J L, Yan Zhizi, et al. Resting-state functional MRI in depression unmasks increased connectivity between networks via the dorsal nexus[J] . Proceedings of the National Academy of Sciences, 2010, 107(24):11020-11025.
[7] Zhou Yuan, Yu Chunshui, Zheng Hua, et al. Increased neural resources recruitment in the intrinsic organization in major depression[J] . Journal of Affective Disorders, 2010, 121(3):220-230.
[8] Zeng Lingli, Shen Hui, Liu Li, et al. Identifying major depression using whole-brain functional connectivity:a multivariate pattern analysis[J] . Brain, 2012, 135(5):1498-1507.
[9] Wang Jinhui, Wang Liang, Zang Yufeng, et al. Parcellation-dependent small-world brain functional networks:a resting-state fMRI study[J] . Human Brain Mapping, 2009, 30(5):1511-1523.
[10] Zalesky A, Fornito A, Harding I H, et al. Whole-brain anatomical networks:does the choice of nodes matter?[J] . NeuroImage, 2010, 50(3):970-983.
[11] Calhoun V D, Adali T, Pearlson G D, et al. A method for making group inferences from functional MRI data using independent component analysis[J] . Human Brain Mapping, 2001, 14(3):140-151.
[12] McKeown M J, Sejnowski T J. Independent component analysis of fMRI data:examining the assumptions[J] . Human Brain Mapping, 1998, 6(5-6):368-372.
[13] Allen E A, Erhardt E B, Damaraju E, et al. A baseline for the multivariate comparison of resting-state networks[J] . Frontiers in Systems Neuroscience, 2011, 5(5):2.
[14] Himberg J, Hyvrinen A, Esposito F. Validating the independent components of neuroimaging time series via clustering and visualization[J] . NeuroImage, 2004, 22(3):1214-1222.
[15] Viola P, Jones M. Robust real-time face detection[J] . International Journal of Computer Vision, 2004, 57(2):137-154.
[16] Mantini D, Perrucci M G, Gratta C D, et al. Electrophysiological signatures of resting state networks in the human brain[J] . Proceedings of the National Academy of Sciences, 2007, 104(32):13170-13175.
[17] Desseilles M, Balteau E, Sterpenich V, et al. Abnormal neural filtering of irrelevant visual information in depression[J] . Journal of Neuroscience, 2009, 47(5):1395-1403.
收稿日期 2017/1/16
修回日期 2017/3/2
页码 1641-1644,1699
中图分类号 TP391.4
文献标志码 A