Dynamic network model with continuous valued nodes for longitudinal brain morphometry

ABSTRACT Longitudinal brain morphometry probes time‐related brain morphometric patterns. We propose a method called dynamic network modeling with continuous valued nodes to generate a dynamic brain network from continuous valued longitudinal morphometric data. The mathematical framework of this method is based on state‐space modeling. We use a bootstrap‐enhanced least absolute shrinkage operator to solve the network‐structure generation problem. In contrast to discrete dynamic Bayesian network modeling, the proposed method enables network generation directly from continuous valued high‐dimensional short sequence data, being free from any discretization process. We applied the proposed method to a study of normal brain development. HIGHLIGHTSTo generate a dynamic brain network from longitudinal morphometric data.Network generation from continuous valued high‐dimensional short sequence data.Use a bootstrap‐enhanced LASSO to solve the network generation problem.

[1]  Rebecca W Doerge,et al.  An Empirical Bayesian Method for Estimating Biological Networks from Temporal Microarray Data , 2010, Statistical applications in genetics and molecular biology.

[2]  S. Shipp,et al.  The functional logic of cortical connections , 1988, Nature.

[3]  Rong Chen,et al.  Advanced Connectivity Analysis (ACA): a Large Scale Functional Connectivity Data Mining Environment , 2015, Neuroinformatics.

[4]  M. Detry,et al.  Analyzing Repeated Measurements Using Mixed Models. , 2016, JAMA.

[5]  H. Braak,et al.  Evolution of the neuropathology of Alzheimer's disease , 1996, Acta neurologica Scandinavica. Supplementum.

[6]  Bruce Fischl,et al.  FreeSurfer , 2012, NeuroImage.

[7]  Nir Friedman,et al.  Probabilistic Graphical Models - Principles and Techniques , 2009 .

[8]  Edward H. Herskovits,et al.  Predictive structural dynamic network analysis , 2015, Journal of Neuroscience Methods.

[9]  Paul M. Thompson,et al.  Registering Cortical Surfaces Based on Whole-Brain Structural Connectivity and Continuous Connectivity Analysis , 2014, MICCAI.

[10]  Alexander J. Hartemink,et al.  Learning Non-Stationary Dynamic Bayesian Networks , 2010, J. Mach. Learn. Res..

[11]  Alan C. Evans,et al.  The NIH MRI study of normal brain development , 2006, NeuroImage.

[12]  Moo K. Chung,et al.  Sparse Brain Network Recovery Under Compressed Sensing , 2011, IEEE Transactions on Medical Imaging.

[13]  Karl J. Friston,et al.  Structural and Functional Brain Networks: From Connections to Cognition , 2013, Science.

[14]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .

[15]  Ulrich Mansmann,et al.  Graphical modeling of binary data using the LASSO: a simulation study , 2012, BMC Medical Research Methodology.

[16]  N. Tzourio-Mazoyer,et al.  Automated Anatomical Labeling of Activations in SPM Using a Macroscopic Anatomical Parcellation of the MNI MRI Single-Subject Brain , 2002, NeuroImage.

[17]  E H Herskovits,et al.  A Prospective Longitudinal Brain Morphometry Study of Children with Sickle Cell Disease , 2015, American Journal of Neuroradiology.

[18]  Atle Bjørnerud,et al.  Maturation of Cortico-Subcortical Structural Networks-Segregation and Overlap of Medial Temporal and Fronto-Striatal Systems in Development. , 2015, Cerebral cortex.

[19]  Moo K. Chung,et al.  Persistent Homology in Sparse Regression and Its Application to Brain Morphometry , 2014, IEEE Transactions on Medical Imaging.

[20]  Trevor Hastie,et al.  Regularization Paths for Generalized Linear Models via Coordinate Descent. , 2010, Journal of statistical software.

[21]  L. Elliot Hong,et al.  Edge-Centered DTI Connectivity Analysis: Application to Schizophrenia , 2015, Neuroinformatics.

[22]  E. Bullmore,et al.  Imaging structural co-variance between human brain regions , 2013, Nature Reviews Neuroscience.

[23]  Alan C. Evans.  Networks of anatomical covariance , 2013, NeuroImage.

[24]  Alan C. Evans,et al.  Total and regional brain volumes in a population-based normative sample from 4 to 18 years: the NIH MRI Study of Normal Brain Development. , 2012, Cerebral cortex.

[25]  Thorsten Gerber,et al.  Applied Longitudinal Data Analysis Modeling Change And Event Occurrence , 2016 .

[26]  J. Singer,et al.  Applied Longitudinal Data Analysis , 2003 .

[27]  Jeffrey M. Spielberg,et al.  A Longitudinal Study: Changes in Cortical Thickness and Surface Area during Pubertal Maturation , 2015, PloS one.

[28]  S. Resnick,et al.  Longitudinal Magnetic Resonance Imaging Studies of Older Adults: A Shrinking Brain , 2003, The Journal of Neuroscience.

[29]  Brian B. Avants,et al.  Dementia induces correlated reductions in white matter integrity and cortical thickness: A multivariate neuroimaging study with sparse canonical correlation analysis , 2010, NeuroImage.

[30]  Keith Heberlein,et al.  Imaging human connectomes at the macroscale , 2013, Nature Methods.

[31]  Chris Wiggins,et al.  ARACNE: An Algorithm for the Reconstruction of Gene Regulatory Networks in a Mammalian Cellular Context , 2004, BMC Bioinformatics.

[32]  C. Gross,et al.  Neurogenesis in the neocortex of adult primates. , 1999, Science.

[33]  Christos Davatzikos,et al.  Dynamic Bayesian network modeling for longitudinal brain morphometry , 2012, NeuroImage.

[34]  Ruth A. Carper,et al.  Longitudinal Magnetic Resonance Imaging Study of Cortical Development through Early Childhood in Autism , 2010, The Journal of Neuroscience.

[35]  Terence P. Speed,et al.  Bayesian Inference of Signaling Network Topology in a Cancer Cell Line , 2012, Bioinform..

[36]  J. Giedd,et al.  Brain development in children and adolescents: Insights from anatomical magnetic resonance imaging , 2006, Neuroscience & Biobehavioral Reviews.