A statistical test to identify differences in clustering structures

Statistical inference on functional magnetic resonance imaging (fMRI) data is an important task in brain imaging. One major hypothesis is that the presence or not of a psychiatric disorder can be explained by the differential clustering of neurons in the brain. In view of this fact, it is clearly of interest to address the question of whether the properties of the clusters have changed between groups of patients and controls. The normal method of approaching group differences in brain imaging is to carry out a voxel-wise univariate analysis for a difference between the mean group responses using an appropriate test (e.g. a t-test) and to assemble the resulting "significantly different voxels" into clusters, testing again at cluster level. In this approach of course, the primary voxel-level test is blind to any cluster structure. Direct assessments of differences between groups (or reproducibility within groups) at the cluster level have been rare in brain imaging. For this reason, we introduce a novel statistical test called ANOCVA - ANalysis Of Cluster structure Variability, which statistically tests whether two or more populations are equally clustered using specific features. The proposed method allows us to compare the clustering structure of multiple groups simultaneously, and also to identify features that contribute to the differential clustering. We illustrate the performance of ANOCVA through simulations and an application to an fMRI data set composed of children with ADHD and controls. Results show that there are several differences in the brain's clustering structure between them, corroborating the hypothesis in the literature. Furthermore, we identified some brain regions previously not described, generating new hypothesis to be tested empirically.

[1]  Robert Tibshirani,et al.  An Introduction to the Bootstrap , 1994 .

[2]  Polina Golland,et al.  Search for patterns of functional specificity in the brain: A nonparametric hierarchical Bayesian model for group fMRI data , 2011, NeuroImage.

[3]  Patricia N. Pastor,et al.  Diagnosed attention deficit hyperactivity disorder and learning disability: United States, 2004-2006. , 2008, Vital and health statistics. Series 10, Data from the National Health Survey.

[4]  Joseph T. Chang,et al.  Spectral biclustering of microarray data: coclustering genes and conditions. , 2003, Genome research.

[5]  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.

[6]  P. Hagmann,et al.  MR connectomics: a conceptual framework for studying the developing brain , 2012, Front. Syst. Neurosci..

[7]  Robert Tibshirani,et al.  Estimating the number of clusters in a data set via the gap statistic , 2000 .

[8]  João Ricardo Sato,et al.  DWT–CEM: an algorithm for scale-temporal clustering in fMRI , 2007, Biological Cybernetics.

[9]  J. Peacock,et al.  Simulations of the formation, evolution and clustering of galaxies and quasars , 2005, Nature.

[10]  Ayala Cohen,et al.  Language Deficit With Attention-Deficit Disorder: A Prevalent Comorbidity , 1998, Journal of child neurology.

[11]  M. Rietschel,et al.  Adolescent impulsivity phenotypes characterized by distinct brain networks , 2012, Nature Neuroscience.

[12]  Martin J. Lercher,et al.  Clustering of housekeeping genes provides a unified model of gene order in the human genome , 2002, Nature Genetics.

[13]  Lijun Zhang,et al.  Determining functional connectivity using fMRI data with diffusion-based anatomical weighting , 2009, NeuroImage.

[14]  Christian Windischberger,et al.  Toward discovery science of human brain function , 2010, Proceedings of the National Academy of Sciences.

[15]  R Cameron Craddock,et al.  A whole brain fMRI atlas generated via spatially constrained spectral clustering , 2012, Human brain mapping.

[16]  Edmund J Crampin,et al.  Biclustering reveals breast cancer tumour subgroups with common clinical features and improves prediction of disease recurrence , 2013, BMC Genomics.

[17]  Maurizio Corbetta,et al.  Data-driven analysis of analogous brain networks in monkeys and humans during natural vision , 2012, NeuroImage.

[18]  T. Robbins,et al.  Inhibition and the right inferior frontal cortex , 2004, Trends in Cognitive Sciences.

[19]  J B Woodward,et al.  The Functional Magnetic Resonance Imaging Data Center (fMRIDC): the challenges and rewards of large-scale databasing of neuroimaging studies. , 2001, Philosophical transactions of the Royal Society of London. Series B, Biological sciences.

[20]  Michael I. Jordan,et al.  On Spectral Clustering: Analysis and an algorithm , 2001, NIPS.

[21]  Michael P Milham,et al.  The neural correlates of attention deficit hyperactivity disorder: an ALE meta-analysis. , 2006, Journal of child psychology and psychiatry, and allied disciplines.

[22]  Lincoln D. Stein,et al.  Towards a cyberinfrastructure for the biological sciences: progress, visions and challenges , 2008, Nature Reviews Genetics.

[23]  P. Rousseeuw Silhouettes: a graphical aid to the interpretation and validation of cluster analysis , 1987 .

[24]  S. Petersen,et al.  Development of distinct control networks through segregation and integration , 2007, Proceedings of the National Academy of Sciences.

[25]  A. Ravishankar Rao,et al.  A Cluster Overlap Measure for Comparison of Activations in fMRI Studies , 2009, MICCAI.

[26]  D. Tank,et al.  Brain magnetic resonance imaging with contrast dependent on blood oxygenation. , 1990, Proceedings of the National Academy of Sciences of the United States of America.

[27]  Qin Yang,et al.  Analysis of fMRI Data Using Improved Self-Organizing Mapping and Spatio-Temporal Metric Hierarchical Clustering , 2008, IEEE Transactions on Medical Imaging.

[28]  Andreas J Fallgatter,et al.  Reduced Neural Error Signaling in Left Inferior Prefrontal Cortex in Young Adults With ADHD , 2014, Journal of attention disorders.

[29]  James Bailey,et al.  Clustering Similarity Comparison Using Density Profiles , 2006, Australian Conference on Artificial Intelligence.

[30]  H. Hotelling The Generalization of Student’s Ratio , 1931 .

[31]  Andrew H. Sung,et al.  A Similarity Measure for Clustering and its Applications , 2008 .

[32]  Edward T. Bullmore,et al.  The discovery of population differences in network community structure: New methods and applications to brain functional networks in schizophrenia , 2012, NeuroImage.

[33]  Nicole M. Long,et al.  Journal of the American Statistical Association Spatio-spectral Mixed-effects Model for Functional Magnetic Resonance Imaging Data Spatio-spectral Mixed-effects Model for Functional Magnetic Resonance Imaging Data , 2022 .

[34]  Y. Benjamini,et al.  Controlling the false discovery rate: a practical and powerful approach to multiple testing , 1995 .

[35]  M. Meilă Comparing clusterings---an information based distance , 2007 .

[36]  Nick C Fox,et al.  The Alzheimer's disease neuroimaging initiative (ADNI): MRI methods , 2008, Journal of magnetic resonance imaging : JMRI.

[37]  Jin Fan,et al.  Common and unique therapeutic mechanisms of stimulant and nonstimulant treatments for attention-deficit/hyperactivity disorder. , 2012, Archives of general psychiatry.

[38]  Francesco Bertoni,et al.  Hierarchical clustering analysis of pathologic and molecular data identifies prognostically and biologically distinct groups of colorectal carcinomas , 2011, Modern Pathology.

[39]  Vinod Menon,et al.  Parietal attentional system aberrations during target detection in adolescents with attention deficit hyperactivity disorder: event-related fMRI evidence. , 2006, The American journal of psychiatry.

[40]  Rajesh Nandy,et al.  Cluster analysis of fMRI data using dendrogram sharpening , 2003, Human brain mapping.

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

[42]  S. Grossberg The complementary brain: unifying brain dynamics and modularity , 2000, Trends in Cognitive Sciences.

[43]  Carlos H. Acuña The ADHD-200 Consortium: a model to advance the translational potential of neuroimaging in clinical neuroscience , 2012 .

[44]  Nava Rubin,et al.  Cluster-based analysis of FMRI data , 2006, NeuroImage.

[45]  G. W. Milligan,et al.  An examination of procedures for determining the number of clusters in a data set , 1985 .

[46]  Carl D. Hacker,et al.  Clustering of Resting State Networks , 2012, PloS one.

[47]  Jenifer Juranek,et al.  Functional disruption of the brain mechanism for reading: effects of comorbidity and task difficulty among children with developmental learning problems. , 2011, Neuropsychology.

[48]  F. Xavier Castellanos,et al.  Large-scale brain systems in ADHD: beyond the prefrontal–striatal model , 2012, Trends in Cognitive Sciences.