1(School of Science, Xihua University, Chengdu 610039, China) 2(School of Computer Science and Software Engineering, Xihua University, Chengdu 610039, China) 3(Key Laboratory for Neuroinformation of Ministry of Education, University of Electronic Science and Technology of China,Chengdu 610054, China)
Abstract：Brain network analysis plays important roles in studying the cognitive activity of brain, including exploring the information processing mode of the brain and assisting the diagnosis of mental diseases. In recent years, brain network research methods based on multivariate datasets have attracted great attention. Canonical correlation analysis (CCA), as a data-driven multivariate statistical method, can effectively capture the implicit relationship between multivariate data and is widely used in brain network research. This article reviewed the roles of CCA in the brain network research, specific application modes, and advantages and limitations. Firstly, the algorithm principles of traditional CCA and its common variants were summarized. Next, the research status of CCA-based analysis methods in the brain network construction, brain network analysis, and brain network marker identification were described. At last, the methods of brain network research based on CCA were summarized and the future research directions were discussed.
[1] 柯铭, 崔吉平, 刘光耀. 青少年肌阵挛癫痫患者的大尺度脑网络研究 [J]. 中国生物医学工程学报, 2022, 41(3): 282-289. [2] Bressler SL, Menon V. Large-scale brain networks in cognition: emerging methods and principles [J]. Trends in cognitive sciences, 2010, 14(6): 277-290. [3] Bullmore E, Sporns O. Complex brain networks: graph theoretical analysis of structural and functional systems [J]. Nature Reviews Neuroscience, 2009, 10(3): 186-198. [4] 张道强, 接标. 基于机器学习的脑网络分析方法及应用 [J]. 数据采集与处理, 2015, 30(1): 68-76. [5] 张涛, 江晨阳, 李梦晨, 等. 运动想象的大尺度动态功能网络连接 [J].中国生物医学工程学报, 2019, 38(4): 409-416. [6] 黄晓霞, 何红霞. 基于偏相关系数的脑功能连接分析 [J]. 计算机应用与软件, 2017, 34(9): 103-107. [7] Jiang Lin, Li Fali, Chen Baodan, et al. The task-dependent modular covariance networks unveiled by multiple-way fusion-based analysis [J]. International Journal of Neural Systems, 2022, 32(7):2250035. [8] Hotelling H. Relations between two sets of variates [M]//Breakthroughs in statistics: methodology and distribution. New York: Springer-Verlag, 1992: 162-190. [9] Zhuang Xiaowei, Yang Zhengshi, Cordes D. A technical review of canonical correlation analysis for neuroscience applications [J]. Human Brain Mapping, 2020, 41(13): 3807-3833. [10] Tsvetanov KA, Henson RN, Tyler LK, et al. Extrinsic and intrinsic brain network connectivity maintains cognition across the lifespan despite accelerated decay of regional brain activation [J]. The Journal of Neuroscience, 2016, 36(11): 3115-3126. [11] Lin HY, Cocchi L, Zalesky A, et al. Brain-behavior patterns define a dimensional biotype in medication-naïve adults with attention-deficit hyperactivity disorder [J]. Psychological Medicine, 2018, 48(14): 2399-2408. [12] Lai PL, Fyfe C. Kernel and nonlinear canonical correlation analysis [J]. International Journal of Neural Systems, 2000, 10(5): 365-377. [13] Andrew G, Arora R, Bilmes J, et al. Deep canonical correlation analysis[C]// Proceedings of the 30th International Conference on Machine Learning. New York: ACM Press, 2013: 1247-1255. [14] Hardoon DR, Shawe-Taylor J. Sparse canonical correlation analysis [J]. Machine Learning, 2011, 83(3): 331-353. [15] Leurgans SE, Moyeed RA, Silverman BW. Canonical correlation analysis when the data are curves [J]. Journal of the Royal Statistical Society: Series B (Methodological), 1993, 55(3): 725-740. [16] Tuzhilina E, Tozzi L, Hastie T. Canonical correlation analysis in high dimensions with structured regularization [J]. Statistical Modelling, 2023, 23(3): 203-227. [17] Kettenring JR. Canonical analysis of several sets of variables [J]. Biometrika, 1971, 58(3): 433-451. [18] Van De Geer JP. Linear relations amongk sets of variables [J]. Psychometrika, 1984, 49(1): 79-94. [19] Horst P. Relations amongm sets of measures [J]. Psychometrika, 1961, 26(2): 129-149. [20] Akaho S. A kernel method for canonical correlation analysis [OL]. https://arxiv.org/pdf/cs/0609071.pdf, 2007-02-14/2023-08-14. [21] 姜云卢, 邓罡, 文诗涵, 等. 高维稳健典型相关分析研究与应用 [J]. 系统科学与数学, 2021, 41(10): 2965-2976. [22] Hardoon DR, Szedmak S, Shawe-Taylor J. Canonical correlation analysis: An overview with application to learning methods [J]. Neural Computation, 2004, 16(12): 2639-2664. [23] Hsieh WW. Nonlinear canonical correlation analysis by neural networks [J]. Neural Networks, 2000, 13(10): 1095-1105. [24] Yang Xinghao, Liu Weifeng, Liu Wei, et al. A survey on canonical correlation analysis [J]. IEEE Transactions on Knowledge and Data Engineering, 2019, 33(6): 2349-2368. [25] Luo Yao, Tao Dacheng, Ramamohanarao K, et al. Tensor canonical correlation analysis for multi-view dimension reduction [J]. IEEE Transactions on Knowledge and Data Engineering, 2015, 27(11): 3111-3124. [26] Benton A, Khayrallah H, Gujral B, et al. Deep generalized canonical correlation analysis [EB/OL]. https://arxiv.org/pdf/1702.02519.pdf, 2017-06-15/2023-08-14. [27] Somandepalli K, Kumar N, Travadi R, et al. Multimodal representation learning using deep multiset canonical correlation [EB/OL]. https://arxiv.org/pdf/1904.01775.pdf, 2019-04-03/2023-08-14. [28] Vinod HD. Canonical ridge and econometrics of joint production [J]. Journal of Econometrics, 1976, 4(2): 147-166. [29] Sriperumbudur BK, Torres DA, Lanckriet GRG. Sparse eigen methods by dc programming [C]//Proceedings of the 24th International Conference on Machine Learning. New York: ACM Press, 2007: 831-838. [30] Witten DM, Tibshirani R, Hastie T. A penalized matrix decomposition, with applications to sparse principal components and canonical correlation analysis [J]. Biostatistics, 2009, 10(3): 515-334. [31] Lin Dongdong, Zhang Jigang, Li Jingyao, et al. Group sparse canonical correlation analysis for genomic data integration [J]. BMC Bioinformatics, 2013, 14(1): 1-16. [32] Vaerenbergh SV. Kernel methods for nonlinear identification, equalization and separation of signals[D]. Cantabria: Universidad de Cantabria, 2010. [33] González I, Déjean S, Martin PG, et al. CCA: An R package to extend canonical correlation analysis [J]. Journal of Statistical Software, 2008, 23(12): 1-14. [34] Karatzoglou A, Smola A, Hornik K, et al. Kernlab-an S4 package for kernel methods in R [J]. Journal of Statistical Software, 2004, 11(9): 1-20. [35] Pedregosa F, Varoquaux G, Gramfort A, et al. Scikit-learn: Machine learning in python [J]. The Journal of machine Learning Research, 2011, 12:2825-2830. [36] Bilenko NY, Gallant JL. Pyrcca: Regularized kernel canonical correlation analysis in python and its applications to neuroimaging [J]. Frontiers in Neuroinformatics, 2016, 10:49. [37] Songdechakraiwut T, Shen Li, Chung M. Topological learning and its application to multimodal brain network integration [C]//Medical Image Computing and Computer Assisted Intervention-MICCAI. Berlin: Springer-Verlag, 2021: 166-176. [38] 汪成林, 曾卫明, 时莹超. 基于典型相关的脑功能网络构建方法 [J]. 计算机系统应用, 2014, 23(10): 217-222. [39] Kang Jian, Bowman FD, Mayberg H, et al. A depression network of functionally connected regions discovered via multi-attribute canonical correlation graphs [J]. NeuroImage, 2016, 141:431-441. [40] Ai Qingsong, Chen Anqi, Chen Kun, et al. Feature extraction of four-class motor imagery eeg signals based on functional brain network [J]. Journal of Neural Engineering, 2019, 16(2): 026032. [41] Yi Chanlin, Chen Chunli, Jiang Lin, et al. Constructing eeg large-scale cortical functional network connectivity based on brain atlas by s estimator [J]. IEEE Transactions on Cognitive and Developmental Systems, 2020, 13(4): 769-778. [42] Yu Qingbao, Du Yuhui, Chen Jiayu, et al. Application of graph theory to assess static and dynamic brain connectivity: Approaches for building brain graphs [J]. Proceedings of the IEEE, 2018, 106(5): 886-906. [43] Sui Jing, Pearlson G, Caprihan A, et al. Discriminating schizophrenia and bipolar disorder by fusing fMRI and DTI in a multimodal CCA+ joint ICA model [J]. NeuroImage, 2011, 57(3): 839-855. [44] Zhu Qin, Yang Jing, Xu Bingliang, et al. Multimodal brain network jointly construction and fusion for diagnosis of epilepsy [J]. Frontiers in Neuroscience, 2021, 15: 734711. [45] Vaiana M, Muldoon SF. Multilayer brain networks [J]. Journal of Nonlinear Science, 2020, 30(5): 2147-2169. [46] 黄嘉爽, 接标, 丁卫平, 等. 脑网络分析方法及其应用 [J]. 数据采集与处理, 2021, 36(4): 648-663. [47] Tian Ye, Zalesky A, Bousman C, et al. Insula functional connectivity in schizophrenia: subregions, gradients, and symptoms [J]. Biological Psychiatry: Cognitive Neuroscience and Neuroimaging, 2019, 4(4): 399-408. [48] Wang Qing, He Canan, Wang Zan, et al. Dynamic connectivity alteration facilitates cognitive decline in Alzheimer′s disease spectrum [J]. Brain Connectivity, 2021, 11(3): 213-224. [49] Taquet M, Smith SM, Prohl AK, et al. A structural brain network of genetic vulnerability to psychiatric illness [J]. Molecular Psychiatry, 2021, 26(6): 2089-2100. [50] Tozzi L, Tuzhilina E, Glasser MF, et al. Relating whole-brain functional connectivity to self-reported negative emotion in a large sample of young adults using group regularized canonical correlation analysis [J]. NeuroImage, 2021, 237:118137. [51] Mcpherson BC, Pestilli F. A single mode of population covariation associates brain networks structure and behavior and predicts individual subjects’ age [J]. Communications Biology, 2021, 4(1): 1-16. [52] Smith SM, Nichols TE, Vidaurre D, et al. A positive-negative mode of population covariation links brain connectivity, demographics and behavior [J]. Nature NEuroscience, 2015, 18(11): 1565-1567. [53] Mihalik A, Ferreira FS, Rosa MJ, et al. Brain-behaviour modes of covariation in healthy and clinically depressed young people [J]. Scientific Reports, 2019, 9(1): 1-11. [54] Sui Jing, Adali T, Yu Qingbao, et al. A review of multivariate methods for multimodal fusion of brain imaging data [J]. Journal of Neuroscience Methods, 2012, 204(1): 68-81. [55] Hu Wenxing, Meng Xianghe, Bai Yuntong, et al. Interpretable multimodal fusion networks reveal mechanisms of brain cognition [J]. IEEE Transactions on Medical Imaging, 2021, 40(5): 1474-1483. [56] Fu Zening, Iraji A, Caprihan A, et al. In search of multimodal brain alterations in Alzheimer′s and Binswanger′s disease [J]. NeuroImage: Clinical, 2020, 26:101937. [57] Sui Jing, Pearlson GD, Du Yuhui, et al. In search of multimodal neuroimaging biomarkers of cognitive deficits in schizophrenia [J]. Biological Psychiatry, 2015, 78(11): 794-804. [58] He Hao, Sui Jing, Du Yuhui, et al. Co-altered functional networks and brain structure in unmedicated patients with bipolar and major depressive disorders [J]. Brain Structure and Function, 2017, 222(9): 4051-4064. [59] Liu Shengfeng, Wang Haiying, Song Ming, et al. Linked 4-way multimodal brain differences in schizophrenia in a large chinese han population [J]. Schizophrenia Bulletin, 2019, 45(2): 436-449. [60] Xia CH, Ma Zongming, Ciric R, et al. Linked dimensions of psychopathology and connectivity in functional brain networks [J]. Nature Communications, 2018, 9(1): 1-14. [61] Guo Tao, Guan Xiaojun, Zhou Cheng, et al. Clinically relevant connectivity features define three subtypes of parkinson′s disease patients [J]. Human Brain Mapping, 2020, 41(14): 4077-4092. [62] Yu Meichen, Linn KA, Shinohara RT, et al. Childhood trauma history is linked to abnormal brain connectivity in major depression [J]. Proceedings of the National Academy of Sciences, 2019, 116(17): 8582-8590. [63] Wang Haimei, Jiang Xiao, De Leone R, et al. Extracting bold signals based on time-constrained multiset canonical correlation analysis for brain functional network estimation and classification [J]. Brain Research, 2022, 1775:147745. [64] Yahata N, Morimoto J, Hashimoto R, et al. A small number of abnormal brain connections predicts adult autism spectrum disorder [J]. Nature COmmunications, 2016, 7(1): 1-12. [65] Lisowska A, Rekik I, Abbvie AsA, et al. Joint pairing and structured mapping of convolutional brain morphological multiplexes for early dementia diagnosis [J]. Brain Connectivity, 2019, 9(1): 22-36.
