Generative Temporal Modelling of Neuroimaging - Decomposition and Nonparametric Testing

Functional Magnetic Resonance Imaging (fMRI) gives us a unique insight into the processes of the brain, and opens up for analyzing the functional activation patterns of the underlying sources. Task inferred supervised learning with restrictive assumptions in the regression set-up, restrict the exploratory nature of the analysis. Fully unsupervised independent component analysis (ICA) algorithms, on the other hand, can struggle to detect clear classifiable components on single subject data. We attribute this shortcoming to inadequate modeling of the fMRI source signals, by incorporating a temporal source prior. fMRI source signals, biological stimuli and non-stimuli related artifacts, are all smooth over a time-scale compatible with the sampling time (TR), and we therefore propose Gaussian process ICA (GPICA), which facilitates temporal dependency of the extracted sources, by use of Gaussian Process priors. On two fMRI data sets with different sampling frequency, we show that the GPICA inferred temporal components, and associated spatial maps, that allow for a more definite interpretation than standard ICA methods. The temporal structure of the sources are controlled by the covariance of the Gaussian Process, specified by a kernel function with a interpretable and controllable temporal length scale parameter. We propose a hierarchical model specification, considering both instantaneous and convolutive mixing, and infer Preprint submitted to NeuroImage June 8, 2016 56 Gaussian Process Based Independent Analysis for Temporal Source Separation in fMRI

[1]  R. Buxton,et al.  Modeling the hemodynamic response to brain activation , 2004, NeuroImage.

[2]  Erkki Oja,et al.  Independent component analysis: algorithms and applications , 2000, Neural Networks.

[3]  H. Sebastian Seung,et al.  Learning the parts of objects by non-negative matrix factorization , 1999, Nature.

[4]  Carl E. Rasmussen,et al.  Warped Gaussian Processes , 2003, NIPS.

[5]  Lars Kai Hansen,et al.  On Independent Component Analysis for Multimedia Signals , 2000 .

[6]  Robert E. Tarjan,et al.  Depth-First Search and Linear Graph Algorithms , 1972, SIAM J. Comput..

[7]  Karl J. Friston,et al.  False discovery rate revisited: FDR and topological inference using Gaussian random fields , 2009, NeuroImage.

[8]  R. Oostenveld,et al.  Nonparametric statistical testing of EEG- and MEG-data , 2007, Journal of Neuroscience Methods.

[9]  B. Biswal,et al.  Functional connectivity in the motor cortex of resting human brain using echo‐planar mri , 1995, Magnetic resonance in medicine.

[10]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[11]  Derek J. Pike,et al.  Empirical Model‐building and Response Surfaces. , 1988 .

[12]  Helle Henriksen.  A Generative Approach to EEG Source Separation , Classification and Artifact Correction , .

[14]  M. Lindquist.  The Statistical Analysis of fMRI Data. , 2008, 0906.3662.

[15]  Lars Kai Hansen,et al.  Blind Separation of More Sources than Sensors in Convolutive Mixtures , 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

[16]  Thomas E. Nichols,et al.  Nonparametric Permutation Tests for Functional Neuroimaging , 2003 .

[17]  Lars Kai Hansen,et al.  Model Selection for Convolutive ICA with an Application to Spatiotemporal Analysis of EEG , 2007, Neural Computation.

[18]  S. Rombouts,et al.  Consistent resting-state networks across healthy subjects , 2006, Proceedings of the National Academy of Sciences.

[19]  Mikkel N. Schmidt.  Function factorization using warped Gaussian processes , 2009, ICML '09.

[20]  Terrence J. Sejnowski,et al.  An Information-Maximization Approach to Blind Separation and Blind Deconvolution , 1995, Neural Computation.

[21]  Karl J. Friston,et al.  Human Brain Function , 1997 .

[22]  Aapo Hyvärinen,et al.  Fast and robust fixed-point algorithms for independent component analysis , 1999, IEEE Trans. Neural Networks.

[23]  Geoffrey E. Hinton,et al.  Unsupervised learning : foundations of neural computation , 1999 .

[24]  Michael S. Lazar,et al.  Spatial patterns underlying population differences in the background EEG , 2005, Brain Topography.

[25]  P. Good,et al.  Permutation Tests: A Practical Guide to Resampling Methods for Testing Hypotheses , 1995 .

[26]  G L Shulman,et al.  INAUGURAL ARTICLE by a Recently Elected Academy Member:A default mode of brain function , 2001 .

[27]  Pierre Comon,et al.  Independent component analysis, A new concept? , 1994, Signal Process..

[28]  Hartwig R. Siebner,et al.  Infinite Relational Modeling of Functional Connectivity in Resting State fMRI , 2010, NIPS.

[29]  David J. C. MacKay,et al.  Information Theory, Inference, and Learning Algorithms , 2004, IEEE Transactions on Information Theory.

[30]  E. C. Cmm,et al.  on the Recognition of Speech, with , 2008 .

[31]  Jerome H. Saltzer,et al.  End-to-end arguments in system design , 1984, TOCS.

[32]  Mikkel N. Schmidt,et al.  Nonnegative Matrix Factorization with Gaussian Process Priors , 2008, Comput. Intell. Neurosci..

[33]  Alexander Ilin,et al.  Variational Gaussian-process factor analysis for modeling spatio-temporal data , 2009, NIPS.

[34]  John Suckling,et al.  Global, voxel, and cluster tests, by theory and permutation, for a difference between two groups of structural MR images of the brain , 1999, IEEE Transactions on Medical Imaging.

[35]  Jouni Hartikainen,et al.  Kalman filtering and smoothing solutions to temporal Gaussian process regression models , 2010, 2010 IEEE International Workshop on Machine Learning for Signal Processing.

[36]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[37]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[38]  Lars Kai Hansen,et al.  Blind detection of independent dynamic components , 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).

[39]  Reinhold Orglmeister,et al.  Blind source separation of real world signals , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[40]  Schuster,et al.  Separation of a mixture of independent signals using time delayed correlations. , 1994, Physical review letters.

[41]  M. D’Esposito,et al.  The variability of human BOLD hemodynamic responses , 1998, NeuroImage.

[42]  M. P. van den Heuvel,et al.  Normalized Cut Group Clustering of Resting-State fMRI Data , 2008, PloS one.

[43]  Simon Haykin,et al.  The Cocktail Party Problem , 2005, Neural Computation.

[44]  Lars Kai Hansen,et al.  Model sparsity and brain pattern interpretation of classification models in neuroimaging , 2012, Pattern Recognit..

[45]  John P. Cunningham,et al.  Gaussian-process factor analysis for low-dimensional single-trial analysis of neural population activity , 2008, NIPS.

[46]  Sunho Park,et al.  Source Separation with Gaussian Process Models , 2007, ECML.

[47]  Sunho Park,et al.  Gaussian processes for source separation , 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

[48]  Robert Oostenveld,et al.  FieldTrip: Open Source Software for Advanced Analysis of MEG, EEG, and Invasive Electrophysiological Data , 2010, Comput. Intell. Neurosci..

[49]  S. Kiebel,et al.  An Introduction to Random Field Theory , 2003 .