基于t-SNE的脑网络状态观测矩阵降维方法研究
|
摘要
针对基于功能核磁共振重构的脑网络状态观测矩阵维数过高和无特征的特点,对其降维方法展开研究,给出了基于t-SNE的脑网络状态观测矩阵降维算法,并且利用Python实现了降维及可视化平台。实验结果表明,与目前主流的其他降维算法相比较,使用该方法得到的脑网络状态观测矩阵低维空间的映射点有明显的聚类表现,并且在多个样本上的降维结果显现出一定的规律性,从而证明了该算法的有效性和普适性。
The brain network state observation matrix based on f MRI reconstruction technology is in high dimension and characterless. A dimension reduction method based on t-distributed Stochastic Neighbor Embedding algorithm for this kind of matrix is presented and a platform for the dimension reduction and visualization is built with Python. The experimental results show that compared with popular dimension reduction methods, the low dimension embedding of brain network state observation matrix with this method demonstrates distinct clustering, and the dimension reduction results of different brain network state observation matrix show up some common regularity, which supports the validity and universality of this method.
The brain network state observation matrix based on f MRI reconstruction technology is in high dimension and characterless. A dimension reduction method based on t-distributed Stochastic Neighbor Embedding algorithm for this kind of matrix is presented and a platform for the dimension reduction and visualization is built with Python. The experimental results show that compared with popular dimension reduction methods, the low dimension embedding of brain network state observation matrix with this method demonstrates distinct clustering, and the dimension reduction results of different brain network state observation matrix show up some common regularity, which supports the validity and universality of this method.
引文
[1]Biswal B,Yetkin F Z,Haughton V M,et al.Functional connectivity in the motor cortex of resting human brain using echo-planar MRI[J].Magn Reson Med,1995,34(4):537-541.
[2]Ogawa S,Tank D W,Menon R,et a1.Intrinsic signal changes accompanying sensory stimulation:Functional brain mapping with magnetic resonance imaging[J].Proceedings of the National Academy of Sciences,1992,89(13):5951-5955.
[3]杨亮.基于静息态f MRI数据的人脑功能连接研究[D].南京:南京理工大学,2014.
[4]Smith S M,Vidaurre D,Beckmann C F,et al.Functional connectomics from resting-state f MRI[J].Trends in Cognitive Sciences,2013,17(12):666-682.
[5]Xie X,Cao Z,Weng X.Spatiotemporal nonlinearity in resting-state f MRI of the human brain[J].Neuroimage,2008,40(4):1672-1685.
[6]梁夏,王金辉,贺永.人脑连接组研究:脑结构网络和脑功能网络[J].科学通报,2010,55(16):1565-1583.
[7]Achard S,Salvador R,Whitcher B,et al.A resilient,low frequency,smallworld human brain functional network with highly connected association cortical hubs[J].Journal of Neuroscience the Official Journal of the Society for Neuroscience,2006,26(1):63-72.
[8]Meunier D,Achard S,Morcom A,et al.Age-related changes in modular organization of human brain functional networks[J].Neuroimage,2008,44(3):715-723.
[9]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.
[10]Taubert M,Draganski B,Anwander A,et al.Dynamic properties of human brain structure:Learning-related changes in cortical areas and associated fiber connections[J].Journal of Neuroscience the Official Journal of the Society for Neuroscience,2010,30(35):11670-11677.
[11]Wang X,Wang Q.A novel image encryption algorithm based on dynamic S-boxes constructed by chaos[J].Nonlinear Dynamics,2014,75(3):567-576.
[12]Wang X,Liu L.Cryptanalysis of a parallel sub-image encryption method with high-dimensional chaos[J].Nonlinear Dynamics,2013,73:795-800.
[13]Yu Q,Erhardt E B,Jing S,et al.Assessing dynamic brain graphs of time-varying connectivity in f MRI data:Application to healthy controls and patients with schizophrenia[J].Neuroimage,2015,107:345-355.
[14]Nakai T,Bagarinao E,Matsuo K,et al.Dynamic monitoring of brain activation under visual stimulation using f MRI—The advantage of real-time f MRI with sliding window GLM analysis[J].Journal of Neuroscience Methods,2006,157(1):158-167.
[15]Du Y,Pearlson G D,Yu Q,et al.Interaction among subsystems within default mode network diminished in schizophrenia patients:A dynamic connectivity approach[J].Schizophrenia Research,2015,170(1):55-65.
[16]Suk H I,Wee C Y,Lee S W,et al.State-space model with deep learning for functional dynamics estimation in resting-state f MRI[J].Neuroimage,2016,129:292-307.
[17]Reich D,Price A L,Patterson N.Principal component analysis of genetic data[J].Nature Genetics,2008,40(5):491-492.
[18]Donoho D L,Grimes C.Hessian eigenmaps:Locally linear embedding techniques for high-dimensional data[J].Proceedings of the National Academy of Sciences,2003,100(10):5591-5596.
[19]Hagmann P,Cammoun L,Gigandet X,et al.Mapping the structural core of human cerebral cortex[J].Plos Biology,2008,6(7):159.
[20]Hinton G,Roweis S.Stochastic neighbor embedding[J].Advances in Neural Information Processing Systems,2010,41(4):833-840.
[21]Leon P S,Woodman M,Mcintosh R,et al.The virtual brain:A neuroinformatics platform for simulating largescale brain network models[J].Bmc Neuroscience,2013,14(1):1-2.
[22]Rana K D,Vaina L M,H?m?l?inen M S.A fast statistical significance test for baseline correction and comparative analysis in phase locking[J].Frontiers in Neuroinformatics,2013,7(3):3.
[23]Torben-Nielsen B.An efficient and extendable python library to analyze neuronal morphologies[J].Neuroinformatics,2014,12(4):619-622.
[24]Brain Imaging&Analysis Center.Python/FSL resting state pipeline[DB/OL].[2016-07-15].https://wiki.biac.duke.edu/biac:analysis:resting_pipeline.
[25]Darvas F,Pantazis D,Kucukaltun-Yildirim E,et al.Mapping human brain function with MEG and EEG:Methods and validation[J].Neuroimage,2004,23(1):289-299.
[26]Wang X,Luo C.Researches on chaos phenomenon of EEG dynamics model[J].Applied Mathematics&Computation,2006,183(1):30-41.
[27]Wang X,Luo C,Meng J.Nonlinear dynamic research on EEG signals in HAI experiment[J].Applied Mathematics&Computation,2009,207(1):63-74.
[2]Ogawa S,Tank D W,Menon R,et a1.Intrinsic signal changes accompanying sensory stimulation:Functional brain mapping with magnetic resonance imaging[J].Proceedings of the National Academy of Sciences,1992,89(13):5951-5955.
[3]杨亮.基于静息态f MRI数据的人脑功能连接研究[D].南京:南京理工大学,2014.
[4]Smith S M,Vidaurre D,Beckmann C F,et al.Functional connectomics from resting-state f MRI[J].Trends in Cognitive Sciences,2013,17(12):666-682.
[5]Xie X,Cao Z,Weng X.Spatiotemporal nonlinearity in resting-state f MRI of the human brain[J].Neuroimage,2008,40(4):1672-1685.
[6]梁夏,王金辉,贺永.人脑连接组研究:脑结构网络和脑功能网络[J].科学通报,2010,55(16):1565-1583.
[7]Achard S,Salvador R,Whitcher B,et al.A resilient,low frequency,smallworld human brain functional network with highly connected association cortical hubs[J].Journal of Neuroscience the Official Journal of the Society for Neuroscience,2006,26(1):63-72.
[8]Meunier D,Achard S,Morcom A,et al.Age-related changes in modular organization of human brain functional networks[J].Neuroimage,2008,44(3):715-723.
[9]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.
[10]Taubert M,Draganski B,Anwander A,et al.Dynamic properties of human brain structure:Learning-related changes in cortical areas and associated fiber connections[J].Journal of Neuroscience the Official Journal of the Society for Neuroscience,2010,30(35):11670-11677.
[11]Wang X,Wang Q.A novel image encryption algorithm based on dynamic S-boxes constructed by chaos[J].Nonlinear Dynamics,2014,75(3):567-576.
[12]Wang X,Liu L.Cryptanalysis of a parallel sub-image encryption method with high-dimensional chaos[J].Nonlinear Dynamics,2013,73:795-800.
[13]Yu Q,Erhardt E B,Jing S,et al.Assessing dynamic brain graphs of time-varying connectivity in f MRI data:Application to healthy controls and patients with schizophrenia[J].Neuroimage,2015,107:345-355.
[14]Nakai T,Bagarinao E,Matsuo K,et al.Dynamic monitoring of brain activation under visual stimulation using f MRI—The advantage of real-time f MRI with sliding window GLM analysis[J].Journal of Neuroscience Methods,2006,157(1):158-167.
[15]Du Y,Pearlson G D,Yu Q,et al.Interaction among subsystems within default mode network diminished in schizophrenia patients:A dynamic connectivity approach[J].Schizophrenia Research,2015,170(1):55-65.
[16]Suk H I,Wee C Y,Lee S W,et al.State-space model with deep learning for functional dynamics estimation in resting-state f MRI[J].Neuroimage,2016,129:292-307.
[17]Reich D,Price A L,Patterson N.Principal component analysis of genetic data[J].Nature Genetics,2008,40(5):491-492.
[18]Donoho D L,Grimes C.Hessian eigenmaps:Locally linear embedding techniques for high-dimensional data[J].Proceedings of the National Academy of Sciences,2003,100(10):5591-5596.
[19]Hagmann P,Cammoun L,Gigandet X,et al.Mapping the structural core of human cerebral cortex[J].Plos Biology,2008,6(7):159.
[20]Hinton G,Roweis S.Stochastic neighbor embedding[J].Advances in Neural Information Processing Systems,2010,41(4):833-840.
[21]Leon P S,Woodman M,Mcintosh R,et al.The virtual brain:A neuroinformatics platform for simulating largescale brain network models[J].Bmc Neuroscience,2013,14(1):1-2.
[22]Rana K D,Vaina L M,H?m?l?inen M S.A fast statistical significance test for baseline correction and comparative analysis in phase locking[J].Frontiers in Neuroinformatics,2013,7(3):3.
[23]Torben-Nielsen B.An efficient and extendable python library to analyze neuronal morphologies[J].Neuroinformatics,2014,12(4):619-622.
[24]Brain Imaging&Analysis Center.Python/FSL resting state pipeline[DB/OL].[2016-07-15].https://wiki.biac.duke.edu/biac:analysis:resting_pipeline.
[25]Darvas F,Pantazis D,Kucukaltun-Yildirim E,et al.Mapping human brain function with MEG and EEG:Methods and validation[J].Neuroimage,2004,23(1):289-299.
[26]Wang X,Luo C.Researches on chaos phenomenon of EEG dynamics model[J].Applied Mathematics&Computation,2006,183(1):30-41.
[27]Wang X,Luo C,Meng J.Nonlinear dynamic research on EEG signals in HAI experiment[J].Applied Mathematics&Computation,2009,207(1):63-74.