基于瞬时转变率模型的脑网络状态观测算法
|
摘要
针对K-means等聚类方法在脑网络状态观测中稳定性和鲁棒性较差的缺点,提出了一种基于瞬时转变率模型的脑网络状态观测算法。通过对状态转换临界点进行分组统计和分析,计算每一个临界时间点的状态瞬时转变率,在此基础上构建脑网络状态观测算法,并使用区间估计方法对状态转换的观测效果进行估计和验证。在脑网络数据库样本中的实验结果显示,与K-means等脑网络状态聚类观测算法相比,该算法在不同条件下的聚类稳定性更好,对样本差异的适应性更强,受参数选择的影响更小,能直观地观测到脑网络状态转换趋势。
Aiming at the poor stability and robustness in brain network state observation in clustering methods such as K-means, we propose a brain network state observation algorithm based on instantaneous transition rate model. The algorithm calculates the instantaneous state transition rate of each critical time point by group statistics and analysis. Based on this, we construct a brain network state observation model, and estimate and verify the state transition observation effect by the interval estimation method. Experimental results of the brain network database samples show that compared with the K-means and other brain network state clustering observation algorithms, the proposed algorithm has better cluster stability under different conditions and is more adaptable to individual sample differences. It is less affected by parameter selection and can visually observe the trend of brain network state transition.
Aiming at the poor stability and robustness in brain network state observation in clustering methods such as K-means, we propose a brain network state observation algorithm based on instantaneous transition rate model. The algorithm calculates the instantaneous state transition rate of each critical time point by group statistics and analysis. Based on this, we construct a brain network state observation model, and estimate and verify the state transition observation effect by the interval estimation method. Experimental results of the brain network database samples show that compared with the K-means and other brain network state clustering observation algorithms, the proposed algorithm has better cluster stability under different conditions and is more adaptable to individual sample differences. It is less affected by parameter selection and can visually observe the trend of brain network state transition.
引文
[1] Logothetis N K,Pauls J,Augath M,et al.Neurophysiological investigation of the basis of the fMRI signal[J].Nature,2001,412(6843):150-157.
[2] Greicius M D,Krasnow B,Reiss A L,et al.Functional connectivity in the resting brain:A network analysis of the default mode hypothesis[J].Proceedings of the National Academy of Sciences of the United States of America,2003,100(1):253-258.
[3] Di X,Cohel S,Kim E H,et al.Task vs.rest—Different network configurations between the coactivation and the resting-state brain networks[J].Frontiers in Human Neuroscience,2013,7:Article 493.
[4] Tagliazucchi E,von Wenger F,Morzelewski A,et al.Dynamic BOLD functional connectivity in humans and its electrophysiological correlates[J].Frontiers in Human Neuroscience,2012,6:Article 339.
[5] Fox M D,Snyder A Z,Vincent J L,et al.The human brain is intrinsically organized into dynamic,anticorrelated functional networks[J].Proceedings of the National Academy of Sciences of the United States of America,2005,102(27):9673-9678.
[6] Ou J L,Xie L,Jin C F,et al.Characterizing and differentiating brain state dynamics via hidden Markov models[J].Brain Topography,2015,28(5):666-679.
[7] Suk H I,Wee C Y,Lee S W,et al.State-space model with deep learning for functional dynamics estimation in resting-state fMRI[J].NeuroImage,2016,129:292-307.
[8] Zhang Xin,Hu Xin-tao,Guo Lei.Characterization of motor-related task brain states based on dynamic functional connectivity[J].Journal of Computer Applications,2015,35(7):1933-1938.(in Chinese)
[9] Querne L,Berquin P,Vernierhauvette M P,et al.Dysfunction of the attentional brain network in children with developmental coordination disorder:A fMRI study[J].Brain Research,2008,1244(4):89-102.
[10] Allen E A,Damaraju E,Plis S M,et al.Tracking whole-brain connectivity dynamics in the resting state[J].Cerebral Cortex,2014,24(3):663-676.
[11] Li Xian-zhe,Zeng Wei-ming,Shi Yu-hu,et al.Resting state fMRI data classification method based on K-means algorithm optimized by rough set[C]//Proc of International Conference on Intelligence Science,2017:84-92.
[12] Billings J C W,Medda A,Berman G,et al.Functional connectivity metrics for wavelet clustering of rs-fMRI data[C]//Proc of Conference on Signals,Systems & Computers,2016:1296-1299.
[13] Wang X,Ren Y S,Zhang W S.Depression disorder classification of fMRI data using sparse low-rank functional brain network and graph-based features[J].Computational and Mathematical Methods in Medicine,2017:Article ID3609821.
[14] Cheng H W,Fan Y.Semi-supervised clustering for parcellating brain regions based on resting state fMRI data[C]//Proc of SPIE-The International Society for Optical Engineering,2014:903427.
[15] Xie Yuan-wei.Functional network based on fMRI and connectivity association pattern[D].Lanzhou:Lanzhou University,2017.(in Chinese)
[16] Ma Fu-min,Lu Rui-qiang,Zhang Teng-fei.Rough K-means clustering based on local density adaptive measure[J].Computer Engineering & Science,2018,40(1):184-190.(in Chinese)
[17] Vijay K,Selvakumar K.Brain FMRI clustering using interaction K-means algorithm with PCA[C]//Proc of International Conference on Communications and Signal Processing,2015:909-913.
[18] FCP classic data sharing samples[DB/OL].[2018-05-23].http://fcon_1000.projects.nitrc.org/fcpClassic/FcpTable.html.
[19] Brain Imaging & Analysis Center.Python/FSL resting state pipeline[DB/OL].[2018-05-23].https://wiki.biac.duke.edu/biac:analysis:resting_pipeline.
[20] Tzouriomazoyer N,Landeau B,Papathanassiou D,et al.Automated anatomical labeling of activations in SPM using a macroscopic anatomical parcellation of the MNI MRI single-subject brain[J].NeuroImage,2002,15(1):273-289.
[21] Benesty J,Chen J,Huang Y,et al.Pearson correlation coefficient[M]//Noise Reduction in Speech Processing.Berlin:Springer Berlin Heidelberg,2009:1-4.
[22] Hinton G E.Visualizing high-dimensional data using t-SNE[J].Journal of Machine Learning Research,2008,9(2):2579-2605.
[23] Kuckartz U,R?diker S,Kollewe T,et al.t-Test:zwei Mittelwerte vergleichen[M]//Statistik.Wiesbaden:VS Verlag für Sozialwissenschaften,2010:147-166.
[8] 张欣,胡新韬,郭雷.基于动态功能连接的运动任务大脑状态表达[J].计算机应用,2015,35(7):1933-1938.
[15] 谢元伟.fMRI功能网络与连接关联模式[D].兰州:兰州大学,2017.
[16] 马福民,逯瑞强,张腾飞.基于局部密度自适应度量的粗糙K-means聚类算法[J].计算机工程与科学,2018,40(1):184-190.
[2] Greicius M D,Krasnow B,Reiss A L,et al.Functional connectivity in the resting brain:A network analysis of the default mode hypothesis[J].Proceedings of the National Academy of Sciences of the United States of America,2003,100(1):253-258.
[3] Di X,Cohel S,Kim E H,et al.Task vs.rest—Different network configurations between the coactivation and the resting-state brain networks[J].Frontiers in Human Neuroscience,2013,7:Article 493.
[4] Tagliazucchi E,von Wenger F,Morzelewski A,et al.Dynamic BOLD functional connectivity in humans and its electrophysiological correlates[J].Frontiers in Human Neuroscience,2012,6:Article 339.
[5] Fox M D,Snyder A Z,Vincent J L,et al.The human brain is intrinsically organized into dynamic,anticorrelated functional networks[J].Proceedings of the National Academy of Sciences of the United States of America,2005,102(27):9673-9678.
[6] Ou J L,Xie L,Jin C F,et al.Characterizing and differentiating brain state dynamics via hidden Markov models[J].Brain Topography,2015,28(5):666-679.
[7] Suk H I,Wee C Y,Lee S W,et al.State-space model with deep learning for functional dynamics estimation in resting-state fMRI[J].NeuroImage,2016,129:292-307.
[8] Zhang Xin,Hu Xin-tao,Guo Lei.Characterization of motor-related task brain states based on dynamic functional connectivity[J].Journal of Computer Applications,2015,35(7):1933-1938.(in Chinese)
[9] Querne L,Berquin P,Vernierhauvette M P,et al.Dysfunction of the attentional brain network in children with developmental coordination disorder:A fMRI study[J].Brain Research,2008,1244(4):89-102.
[10] Allen E A,Damaraju E,Plis S M,et al.Tracking whole-brain connectivity dynamics in the resting state[J].Cerebral Cortex,2014,24(3):663-676.
[11] Li Xian-zhe,Zeng Wei-ming,Shi Yu-hu,et al.Resting state fMRI data classification method based on K-means algorithm optimized by rough set[C]//Proc of International Conference on Intelligence Science,2017:84-92.
[12] Billings J C W,Medda A,Berman G,et al.Functional connectivity metrics for wavelet clustering of rs-fMRI data[C]//Proc of Conference on Signals,Systems & Computers,2016:1296-1299.
[13] Wang X,Ren Y S,Zhang W S.Depression disorder classification of fMRI data using sparse low-rank functional brain network and graph-based features[J].Computational and Mathematical Methods in Medicine,2017:Article ID3609821.
[14] Cheng H W,Fan Y.Semi-supervised clustering for parcellating brain regions based on resting state fMRI data[C]//Proc of SPIE-The International Society for Optical Engineering,2014:903427.
[15] Xie Yuan-wei.Functional network based on fMRI and connectivity association pattern[D].Lanzhou:Lanzhou University,2017.(in Chinese)
[16] Ma Fu-min,Lu Rui-qiang,Zhang Teng-fei.Rough K-means clustering based on local density adaptive measure[J].Computer Engineering & Science,2018,40(1):184-190.(in Chinese)
[17] Vijay K,Selvakumar K.Brain FMRI clustering using interaction K-means algorithm with PCA[C]//Proc of International Conference on Communications and Signal Processing,2015:909-913.
[18] FCP classic data sharing samples[DB/OL].[2018-05-23].http://fcon_1000.projects.nitrc.org/fcpClassic/FcpTable.html.
[19] Brain Imaging & Analysis Center.Python/FSL resting state pipeline[DB/OL].[2018-05-23].https://wiki.biac.duke.edu/biac:analysis:resting_pipeline.
[20] Tzouriomazoyer N,Landeau B,Papathanassiou D,et al.Automated anatomical labeling of activations in SPM using a macroscopic anatomical parcellation of the MNI MRI single-subject brain[J].NeuroImage,2002,15(1):273-289.
[21] Benesty J,Chen J,Huang Y,et al.Pearson correlation coefficient[M]//Noise Reduction in Speech Processing.Berlin:Springer Berlin Heidelberg,2009:1-4.
[22] Hinton G E.Visualizing high-dimensional data using t-SNE[J].Journal of Machine Learning Research,2008,9(2):2579-2605.
[23] Kuckartz U,R?diker S,Kollewe T,et al.t-Test:zwei Mittelwerte vergleichen[M]//Statistik.Wiesbaden:VS Verlag für Sozialwissenschaften,2010:147-166.
[8] 张欣,胡新韬,郭雷.基于动态功能连接的运动任务大脑状态表达[J].计算机应用,2015,35(7):1933-1938.
[15] 谢元伟.fMRI功能网络与连接关联模式[D].兰州:兰州大学,2017.
[16] 马福民,逯瑞强,张腾飞.基于局部密度自适应度量的粗糙K-means聚类算法[J].计算机工程与科学,2018,40(1):184-190.