Machine Learning with Brain Graphs: Predictive Modeling Approaches for Functional Imaging in Systems Neuroscience

The observation and description of the living brain has attracted a lot of research over the past centuries. Many noninvasive imaging modalities have been developed, such as topographical techniques based on the electromagnetic field potential [i.e., electroencephalography (EEG) and magnetoencephalography (MEG)], and tomography approaches including positron emission tomography and magnetic resonance imaging (MRI). Here we will focus on functional MRI (fMRI) since it is widely deployed for clinical and cognitive neurosciences today, and it can reveal brain function due to neurovascular coupling (see ?From Brain Images to fMRI Time Series?). It has led to a much better understanding of brain function, including the description of brain areas with very specialized functions such as face recognition. These neuroscientific insights have been made possible by important methodological advances in MR physics, signal processing, and mathematical modeling.

[1]  C. Porcaro,et al.  Multimodal Functional Network Connectivity: An EEG-fMRI Fusion in Network Space , 2011, PloS one.

[2]  Vince D. Calhoun,et al.  Effective connectivity analysis of fMRI and MEG data collected under identical paradigms , 2011, Comput. Biol. Medicine.

[3]  E. Bullmore,et al.  Wavelets and functional magnetic resonance imaging of the human brain , 2004, NeuroImage.

[4]  Thomas Gärtner,et al.  Kernels for structured data , 2008, Series in Machine Perception and Artificial Intelligence.

[5]  Hang Joon Jo,et al.  Mapping sources of correlation in resting state FMRI, with artifact detection and removal , 2010, NeuroImage.

[6]  Gholam-Ali Hossein-Zadeh,et al.  Decoding brain states using backward edge elimination and graph kernels in fMRI connectivity networks , 2013, Journal of Neuroscience Methods.

[7]  D. Long.  Networks of the Brain , 2011 .

[8]  Bryon A. Mueller,et al.  Altered resting state complexity in schizophrenia , 2012, NeuroImage.

[9]  Robert P. W. Duin,et al.  A Generalized Kernel Approach to Dissimilarity-based Classification , 2002, J. Mach. Learn. Res..

[10]  Edwin R. Hancock,et al.  Spectral embedding of graphs , 2003, Pattern Recognit..

[11]  Luiz A Baccalá,et al.  Frequency domain connectivity identification: An application of partial directed coherence in fMRI , 2009, Human brain mapping.

[12]  J. Lachaux,et al.  A simple measure of correlation across time, frequency and space between continuous brain signals , 2003, Journal of Neuroscience Methods.

[13]  Dimitri Van De Ville,et al.  Low-Dimensional Embedding of Functional Connectivity Graphs for Brain State Decoding , 2010, 2010 First Workshop on Brain Decoding: Pattern Recognition Challenges in Neuroimaging.

[14]  Enzo Tagliazucchi,et al.  Automatic sleep staging using fMRI functional connectivity data , 2012, NeuroImage.

[15]  Mark W. Woolrich,et al.  Network modelling methods for FMRI , 2011, NeuroImage.

[16]  Larry A. Wasserman,et al.  Time varying undirected graphs , 2008, Machine Learning.

[17]  PROCEssIng magazInE.  IEEE Signal Processing Magazine , 2004 .

[18]  Scott T. Grafton,et al.  Dynamic reconfiguration of human brain networks during learning , 2010, Proceedings of the National Academy of Sciences.

[19]  Olaf Sporns,et al.  Complex network measures of brain connectivity: Uses and interpretations , 2010, NeuroImage.

[20]  M. Hulle,et al.  Functional connectivity analysis of fMRI data based on regularized multiset canonical correlation analysis , 2011, Journal of Neuroscience Methods.

[21]  Tianzi Jiang,et al.  Discriminative Analysis of Early Alzheimer's Disease Based on Two Intrinsically Anti-correlated Networks with Resting-State fMRI , 2006, MICCAI.

[22]  O. Sporns,et al.  Complex brain networks: graph theoretical analysis of structural and functional systems , 2009, Nature Reviews Neuroscience.

[23]  Jonathan D. Power,et al.  Prediction of Individual Brain Maturity Using fMRI , 2010, Science.

[24]  A. Hero,et al.  Large-Scale Correlation Screening , 2011, 1102.1204.

[25]  Gang Chen,et al.  Classification of Alzheimer disease, mild cognitive impairment, and normal cognitive status with large-scale network analysis based on resting-state functional MR imaging. , 2011, Radiology.

[26]  Susan L. Whitfield-Gabrieli,et al.  Conn: A Functional Connectivity Toolbox for Correlated and Anticorrelated Brain Networks , 2012, Brain Connect..

[27]  S. Achard,et al.  fMRI functional connectivity estimators robust to region size bias , 2011, 2011 IEEE Statistical Signal Processing Workshop (SSP).

[28]  Horst Bunke,et al.  Matching graphs with unique node labels , 2004, Pattern Analysis and Applications.

[29]  H. Bunke,et al.  Matching graphs with unique node labels , 2004, Pattern Analysis and Applications.

[30]  Tom M. Mitchell,et al.  Machine learning classifiers and fMRI: A tutorial overview , 2009, NeuroImage.

[31]  Jakob Heinzle,et al.  Visuomotor Functional Network Topology Predicts Upcoming Tasks , 2012, The Journal of Neuroscience.

[32]  Edward T. Bullmore,et al.  Whole-brain anatomical networks: Does the choice of nodes matter? , 2010, NeuroImage.

[33]  E. Bullmore,et al.  A Resilient, Low-Frequency, Small-World Human Brain Functional Network with Highly Connected Association Cortical Hubs , 2006, The Journal of Neuroscience.

[34]  Thomas Gärtner,et al.  Why Kernels for Structured Data , 2008 .

[35]  Dimitri Van De Ville,et al.  Classifying minimally disabled multiple sclerosis patients from resting state functional connectivity , 2012, NeuroImage.

[36]  Daoqiang Zhang,et al.  Constrained Sparse Functional Connectivity Networks for MCI Classification , 2012, MICCAI.

[37]  R. Turner,et al.  Eigenvector Centrality Mapping for Analyzing Connectivity Patterns in fMRI Data of the Human Brain , 2010, PloS one.

[38]  R Cameron Craddock,et al.  Disease state prediction from resting state functional connectivity , 2009, Magnetic resonance in medicine.

[39]  Dimitri Van De Ville,et al.  Vector Space Embedding of Undirected Graphs with Fixed-cardinality Vertex Sequences for Classification , 2010, 2010 20th International Conference on Pattern Recognition.

[40]  Mohamed-Jalal Fadili,et al.  Fractional Gaussian noise, functional MRI and Alzheimer's disease , 2005, NeuroImage.

[41]  S. V. N. Vishwanathan,et al.  Graph kernels , 2007 .

[42]  Dietmar Cordes,et al.  Hierarchical clustering to measure connectivity in fMRI resting-state data. , 2002, Magnetic resonance imaging.

[43]  Dimitri Van De Ville,et al.  Decoding brain states from fMRI connectivity graphs , 2011, NeuroImage.

[44]  G. Buzsáki.  Rhythms of the brain , 2006 .

[45]  M. Greicius,et al.  Decoding subject-driven cognitive states with whole-brain connectivity patterns. , 2012, Cerebral cortex.

[46]  Maurizio Corbetta,et al.  Functional connectivity in resting-state fMRI: Is linear correlation sufficient? , 2011, NeuroImage.

[47]  Mark Newman,et al.  Networks: An Introduction , 2010 .

[48]  Benjamin Thyreau,et al.  Discriminative Network Models of Schizophrenia , 2009, NIPS.

[49]  Ethan R. Buch,et al.  Parietofrontal integrity determines neural modulation associated with grasping imagery after stroke. , 2012, Brain : a journal of neurology.

[50]  Peter Guttorp,et al.  Wavelet analysis of covariance with application to atmospheric time series , 2000 .

[51]  Luiz A. Baccalá,et al.  Partial directed coherence: a new concept in neural structure determination , 2001, Biological Cybernetics.

[52]  William M. Wells,et al.  Medical Image Computing and Computer-Assisted Intervention — MICCAI’98 , 1998, Lecture Notes in Computer Science.

[53]  E. Bullmore,et al.  Neurophysiological architecture of functional magnetic resonance images of human brain. , 2005, Cerebral cortex.

[54]  Vince D. Calhoun,et al.  A method for functional network connectivity among spatially independent resting-state components in schizophrenia , 2008, NeuroImage.

[55]  Kaspar Riesen,et al.  Graph Classification and Clustering Based on Vector Space Embedding , 2010, Series in Machine Perception and Artificial Intelligence.

[56]  S.C. Strother,et al.  Evaluating fMRI preprocessing pipelines , 2006, IEEE Engineering in Medicine and Biology Magazine.

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

[58]  Habib Benali,et al.  Partial correlation for functional brain interactivity investigation in functional MRI , 2006, NeuroImage.

[59]  Bernard Haasdonk,et al.  Feature space interpretation of SVMs with indefinite kernels , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[60]  M. Fox,et al.  Frontiers in Systems Neuroscience Systems Neuroscience , 2022 .

[61]  Lars Kai Hansen,et al.  Optimizing the fMRI data-processing pipeline using prediction and reproducibility performance metrics: I. A preliminary group analysis , 2004, NeuroImage.

[62]  Dewen Hu,et al.  Discriminative analysis of resting-state functional connectivity patterns of schizophrenia using low dimensional embedding of fMRI , 2010, NeuroImage.

[63]  J. Pekar,et al.  A method for making group inferences from functional MRI data using independent component analysis , 2001, Human brain mapping.