Multivariate models of inter-subject anatomical variability

This paper presents a very selective review of some of the approaches for multivariate modelling of inter-subject variability among brain images. It focusses on applying probabilistic kernel-based pattern recognition approaches to pre-processed anatomical MRI, with the aim of most accurately modelling the difference between populations of subjects. Some of the principles underlying the pattern recognition approaches of Gaussian process classification and regression are briefly described, although the reader is advised to look elsewhere for full implementational details. Kernel pattern recognition methods require matrices that encode the degree of similarity between the images of each pair of subjects. This review focusses on similarity measures derived from the relative shapes of the subjects' brains. Pre-processing is viewed as generative modelling of anatomical variability, and there is a special emphasis on the diffeomorphic image registration framework, which provides a very parsimonious representation of relative shapes. Although the review is largely methodological, excessive mathematical notation is avoided as far as possible, as the paper attempts to convey a more intuitive understanding of various concepts. The paper should be of interest to readers wishing to apply pattern recognition methods to MRI data, with the aim of clinical diagnosis or biomarker development. It also tries to explain that the best models are those that most accurately predict, so similar approaches should also be relevant to basic science. Knowledge of some basic linear algebra and probability theory should make the review easier to follow, although it may still have something to offer to those readers whose mathematics may be more limited.

[1]  Karl J. Friston,et al.  Diffeomorphic registration using geodesic shooting and Gauss–Newton optimisation , 2011, NeuroImage.

[2]  C. Jack,et al.  Ways toward an early diagnosis in Alzheimer’s disease: The Alzheimer’s Disease Neuroimaging Initiative (ADNI) , 2005, Alzheimer's & Dementia.

[3]  Dinggang Shen,et al.  Morphological classification of medical images using nonlinear support vector machines , 2004, 2004 2nd IEEE International Symposium on Biomedical Imaging: Nano to Macro (IEEE Cat No. 04EX821).

[4]  H. Kitano,et al.  Computational systems biology , 2002, Nature.

[5]  Karl J. Friston,et al.  Variational free energy and the Laplace approximation , 2007, NeuroImage.

[6]  Charles M. Bishop.  Variational principal components , 1999 .

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

[8]  Arthur W. Toga,et al.  Is it time to re-prioritize neuroimaging databases and digital repositories? , 2009, NeuroImage.

[9]  T. K. Carne,et al.  Shape and Shape Theory , 1999 .

[10]  R. Martin,et al.  Relative brain size and basal metabolic rate in terrestrial vertebrates , 1981, Nature.

[11]  Vladimir Vapnik,et al.  An overview of statistical learning theory , 1999, IEEE Trans. Neural Networks.

[12]  Alain Trouvé,et al.  Geodesic Shooting for Computational Anatomy , 2006, Journal of Mathematical Imaging and Vision.

[13]  D'arcy W. Thompson,et al.  On Growth and Form , 1917, Nature.

[14]  Stephen R. Marsland,et al.  A Hamiltonian Particle Method for Diffeomorphic Image Registration , 2007, IPMI.

[15]  Alain Trouvé,et al.  Metric Similarities Learning through Examples: An Application to Shape Retrieval , 2001, EMMCVPR.

[16]  Polina Golland.  Discriminative Direction for Kernel Classifiers , 2001, NIPS.

[17]  James H. Brown,et al.  A general model for ontogenetic growth , 2001, Nature.

[18]  S. Resnick,et al.  Detection of prodromal Alzheimer's disease via pattern classification of magnetic resonance imaging , 2008, Neurobiology of Aging.

[19]  Carl-Fredrik Westin,et al.  Deformable registration of DT-MRI data based on transformation invariant tensor characteristics , 2002, Proceedings IEEE International Symposium on Biomedical Imaging.

[20]  M. Young,et al.  Advanced database methodology for the Collation of Connectivity data on the Macaque brain (CoCoMac). , 2001, Philosophical transactions of the Royal Society of London. Series B, Biological sciences.

[21]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[22]  Lai Xu,et al.  Source based morphometry using structural MRI phase images to identify sources of gray matter and white matter relative differences in schizophrenia versus controls , 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

[23]  John G. Csernansky,et al.  Open Access Series of Imaging Studies (OASIS): Cross-sectional MRI Data in Young, Middle Aged, Nondemented, and Demented Older Adults , 2007, Journal of Cognitive Neuroscience.

[24]  Christopher J. Taylor,et al.  Statistical models of shape - optimisation and evaluation , 2008 .

[25]  L. Younes.  Jacobi fields in groups of diffeomorphisms and applications , 2007 .

[26]  D'arcy W. Thompson.  On growth and form i , 1943 .

[27]  Karl J. Friston,et al.  Bayesian decoding of brain images , 2008, NeuroImage.

[28]  Shun-ichi Amari,et al.  Methods of information geometry , 2000 .

[29]  Michael I. Miller,et al.  Multi-structure network shape analysis via normal surface momentum maps , 2008, NeuroImage.

[30]  George Eastman House,et al.  Sparse Bayesian Learning and the Relevance Vector Machine , 2001 .

[31]  A. Atiya,et al.  Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond , 2005, IEEE Transactions on Neural Networks.

[32]  Lutz Jäncke,et al.  Brain size and grey matter volume in the healthy human brain , 2002, Neuroreport.

[33]  Karl J. Friston,et al.  Identifying global anatomical differences: Deformation‐based morphometry , 1998 .

[34]  B. Miller,et al.  Neurodegenerative Diseases Target Large-Scale Human Brain Networks , 2009, Neuron.

[35]  W. Eric L. Grimson,et al.  Detection and analysis of statistical differences in anatomical shape , 2005, Medical Image Anal..

[36]  K. Mardia,et al.  Statistical Shape Analysis , 1998 .

[37]  J. Ashburner,et al.  Multimodal Image Coregistration and Partitioning—A Unified Framework , 1997, NeuroImage.

[38]  Michael I. Miller,et al.  The emerging discipline of Computational Functional Anatomy , 2009, NeuroImage.

[39]  Dinggang Shen,et al.  Morphological classification of brains via high-dimensional shape transformations and machine learning methods , 2004, NeuroImage.

[40]  J. Gee,et al.  Geodesic estimation for large deformation anatomical shape averaging and interpolation , 2004, NeuroImage.

[41]  Karl J. Friston,et al.  Comparing dynamic causal models , 2004, NeuroImage.

[42]  Mark W. Woolrich,et al.  Probabilistic diffusion tractography with multiple fibre orientations: What can we gain? , 2007, NeuroImage.

[43]  J. Rilling.  Human and nonhuman primate brains: Are they allometrically scaled versions of the same design? , 2006 .

[44]  K. Zou,et al.  Receiver-Operating Characteristic Analysis for Evaluating Diagnostic Tests and Predictive Models , 2007, Circulation.

[45]  Dinggang Shen,et al.  Classification of Structural Images via High-Dimensional Image Warping, Robust Feature Extraction, and SVM , 2005, MICCAI.

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

[47]  J Mazziotta,et al.  A probabilistic atlas and reference system for the human brain: International Consortium for Brain Mapping (ICBM). , 2001, Philosophical transactions of the Royal Society of London. Series B, Biological sciences.

[48]  A. P. Dawid,et al.  Generative or Discriminative? Getting the Best of Both Worlds , 2007 .

[49]  Karl J. Friston,et al.  Structural Covariance in the Human Cortex , 2005, The Journal of Neuroscience.

[50]  J. Hirsch.  Does the h index have predictive power? , 2007, Proceedings of the National Academy of Sciences.

[51]  Michael I. Miller,et al.  Transport of Relational Structures in Groups of Diffeomorphisms , 2008, Journal of Mathematical Imaging and Vision.

[52]  Karl J. Friston,et al.  Statistical parametric maps in functional imaging: A general linear approach , 1994 .

[53]  C. Small.  The statistical theory of shape , 1996 .

[54]  Michael I. Miller,et al.  Large Deformation Diffeomorphism and Momentum Based Hippocampal Shape Discrimination in Dementia of the Alzheimer type , 2007, IEEE Transactions on Medical Imaging.

[55]  Darryl D. Holm,et al.  Singular solutions, momentum maps and computational anatomy , 2006, nlin/0605020.

[56]  Carl E. Rasmussen,et al.  In Advances in Neural Information Processing Systems , 2011 .

[57]  A. Elstein,et al.  Clinical problem solving and diagnostic decision making: selective review of the cognitive literature , 2002, BMJ : British Medical Journal.

[58]  R. Baierlein.  Probability Theory: The Logic of Science , 2004 .

[59]  Guy M. McKhann,et al.  Non-invasive Mapping of Connections Between Human Thalamus and Cortex Using Diffusion Imaging , 2004 .

[60]  T. Sejnowski,et al.  A universal scaling law between gray matter and white matter of cerebral cortex. , 2000, Proceedings of the National Academy of Sciences of the United States of America.

[61]  Karl J. Friston,et al.  A Voxel-Based Method for the Statistical Analysis of Gray and White Matter Density Applied to Schizophrenia , 1995, NeuroImage.

[62]  Ali R. Khan,et al.  Computing an average anatomical atlas using LDDMM and geodesic shooting , 2006, 3rd IEEE International Symposium on Biomedical Imaging: Nano to Macro, 2006..

[63]  Stephen M. Smith,et al.  Probabilistic independent component analysis for functional magnetic resonance imaging , 2004, IEEE Transactions on Medical Imaging.

[64]  Nancy Kanwisher,et al.  Divide and conquer: A defense of functional localizers , 2006, NeuroImage.

[65]  James H. Brown,et al.  The origin of allometric scaling laws in biology from genomes to ecosystems: towards a quantitative unifying theory of biological structure and organization , 2005, Journal of Experimental Biology.

[66]  S. Baron-Cohen.  The extreme male brain theory of autism , 2002, Trends in Cognitive Sciences.

[67]  Steven A. Chance,et al.  Macroscopic brain asymmetry is changed along the antero–posterior axis in schizophrenia , 2005, Schizophrenia Research.

[68]  James Butcher,et al.  Alzheimer's researchers open the doors to data sharing , 2007, Lancet Neurology.

[69]  Christos Davatzikos,et al.  Anatomical Equivalence Class: A Morphological Analysis Framework Using a Lossless Shape Descriptor , 2007, IEEE Transactions on Medical Imaging.

[70]  Stephen M Smith,et al.  Correspondence of the brain's functional architecture during activation and rest , 2009, Proceedings of the National Academy of Sciences.

[71]  Morten Bro-Nielsen,et al.  Real‐time Volumetric Deformable Models for Surgery Simulation using Finite Elements and Condensation , 1996, Comput. Graph. Forum.

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

[73]  D. Mumford.  Perception as Bayesian Inference: Pattern theory: A unifying perspective , 1996 .

[74]  S. D. Chatterji.  Proceedings of the International Congress of Mathematicians , 1995 .

[75]  U. Grenander,et al.  Statistical methods in computational anatomy , 1997, Statistical methods in medical research.

[76]  渡辺 慧,et al.  Knowing and guessing : a quantitative study of inference and information , 1969 .

[77]  Y. Amit,et al.  Towards a coherent statistical framework for dense deformable template estimation , 2007 .

[78]  Karl J. Friston,et al.  Computing average shaped tissue probability templates , 2009, NeuroImage.

[79]  Karl J. Friston,et al.  Generative and recognition models for neuroanatomy , 2004, NeuroImage.

[80]  Timothy Edward John Behrens,et al.  Functional-anatomical validation and individual variation of diffusion tractography-based segmentation of the human thalamus. , 2005, Cerebral cortex.

[81]  W. Richards,et al.  Perception as Bayesian Inference , 2008 .

[82]  Geoffrey E. Hinton,et al.  Generative versus discriminative training of RBMs for classification of fMRI images , 2008, NIPS.

[83]  Desmond J. Higham,et al.  Connectivity-based parcellation of human cortex using diffusion MRI: Establishing reproducibility, validity and observer independence in BA 44/45 and SMA/pre-SMA , 2007, NeuroImage.

[84]  Paul A. Yushkevich,et al.  Deformable Registration of Diffusion Tensor MR Images with Explicit Orientation Optimization , 2005, MICCAI.

[85]  Alain Trouvé,et al.  Computing Large Deformation Metric Mappings via Geodesic Flows of Diffeomorphisms , 2005, International Journal of Computer Vision.

[86]  David G. Stork,et al.  Pattern Classification , 1973 .

[87]  David Mumford,et al.  Pattern Theory: the Mathematics of Perception , 2002, math/0212400.

[88]  David Barber,et al.  Bayesian Classification With Gaussian Processes , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[89]  J. Huxley.  Problems of relative growth , 1932 .

[90]  John Ashburner,et al.  A fast diffeomorphic image registration algorithm , 2007, NeuroImage.

[91]  F L Bookstein,et al.  Biometrics, biomathematics and the morphometric synthesis. , 1996, Bulletin of mathematical biology.

[92]  Ruzena Bajcsy,et al.  Elastic matching of diffusion tensor MRIs , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[93]  Zoubin Ghahramani,et al.  A Unifying Review of Linear Gaussian Models , 1999, Neural Computation.

[94]  Nick C Fox,et al.  Accuracy of dementia diagnosis—a direct comparison between radiologists and a computerized method , 2008, Brain : a journal of neurology.

[95]  Alexander Zien,et al.  Semi-Supervised Learning , 2006 .

[96]  Silke Dodel,et al.  Analysis of correlated activity in fMRI data by artificial neural networks , 2004, 2004 2nd IEEE International Symposium on Biomedical Imaging: Nano to Macro (IEEE Cat No. 04EX821).

[97]  David J. C. MacKay,et al.  The Evidence Framework Applied to Classification Networks , 1992, Neural Computation.

[98]  Francis Eustache,et al.  Semantic and episodic memory of music are subserved by distinct neural networks , 2003, NeuroImage.

[99]  Thomas E. Nichols,et al.  Image-based vs. Coordinate-based Meta-analysis , 2009, NeuroImage.

[100]  J. V. Haxby,et al.  Spatial Pattern Analysis of Functional Brain Images Using Partial Least Squares , 1996, NeuroImage.

[101]  Joel L. Davis,et al.  Large-Scale Neuronal Theories of the Brain , 1994 .

[102]  Roger P. Woods,et al.  Characterizing volume and surface deformations in an atlas framework: theory, applications, and implementation , 2003, NeuroImage.

[103]  Peter Lorenzen,et al.  Unbiased Atlas Formation Via Large Deformations Metric Mapping , 2005, MICCAI.

[104]  Hamid Krim,et al.  Statistics and Analysis of Shapes , 2006, Modeling and Simulation in Science, Engineering and Technology.

[105]  D. Kendall.  MORPHOMETRIC TOOLS FOR LANDMARK DATA: GEOMETRY AND BIOLOGY , 1994 .

[106]  Koenraad Van Leemput,et al.  Automated model-based tissue classification of MR images of the brain , 1999, IEEE Transactions on Medical Imaging.

[107]  Pietro Perona,et al.  Hybrid Generative-Discriminative Visual Categorization , 2008, International Journal of Computer Vision.

[108]  Karl J. Friston,et al.  Is Multivariate Analysis of PET Data More Revealing Than the Univariate Approach? Evidence from a Study of Episodic Memory Retrieval , 1996, NeuroImage.

[109]  Karl J. Friston,et al.  Why Voxel-Based Morphometry Should Be Used , 2001, NeuroImage.

[110]  Terrence J. Sejnowski,et al.  New Directions in Statistical Signal Processing: From Systems to Brains (Neural Information Processing) , 2006 .

[111]  L. Younes,et al.  Statistics on diffeomorphisms via tangent space representations , 2004, NeuroImage.

[112]  Bryan R. Conroy,et al.  Function-based Intersubject Alignment of Human Cortical Anatomy , 2009, Cerebral cortex.

[113]  Mark Jenkinson,et al.  A consistent relationship between local white matter architecture and functional specialisation in medial frontal cortex , 2006, NeuroImage.

[114]  David Haussler,et al.  A Discriminative Framework for Detecting Remote Protein Homologies , 2000, J. Comput. Biol..

[115]  W. Eric L. Grimson,et al.  Deformation Analysis for Shape Based Classification , 2001, IPMI.

[116]  Michael I. Jordan,et al.  A Probabilistic Interpretation of Canonical Correlation Analysis , 2005 .

[117]  S. Lele,et al.  An Invariant Approach to Statistical Analysis of Shapes , 2001 .

[118]  Carey E. Priebe,et al.  Collaborative computational anatomy: An MRI morphometry study of the human brain via diffeomorphic metric mapping , 2009, Human Brain Mapping.

[119]  Carl E. Rasmussen,et al.  Healing the relevance vector machine through augmentation , 2005, ICML.

[120]  Karl J. Friston,et al.  Variational Bayesian inversion of the equivalent current dipole model in EEG/MEG , 2008, NeuroImage.

[121]  U. Grenander,et al.  Computational anatomy: an emerging discipline , 1998 .

[122]  Bernhard E. Boser,et al.  A training algorithm for optimal margin classifiers , 1992, COLT '92.

[123]  Guido Gerig,et al.  Unbiased diffeomorphic atlas construction for computational anatomy , 2004, NeuroImage.

[124]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[125]  Xiaojin Zhu,et al.  Introduction to Semi-Supervised Learning , 2009, Synthesis Lectures on Artificial Intelligence and Machine Learning.

[126]  Michael I. Miller,et al.  Evolutions equations in computational anatomy , 2009, NeuroImage.

[127]  David Mumford,et al.  Neuronal Architectures for Pattern-theoretic Problems , 1995 .

[128]  Michael E. Tipping,et al.  Probabilistic Principal Component Analysis , 1999 .

[129]  Christopher M. Bishop,et al.  Mixtures of Probabilistic Principal Component Analyzers , 1999, Neural Computation.

[130]  Luciano da Fontoura Costa,et al.  Shape Analysis and Classification: Theory and Practice , 2000 .

[131]  F. Rohlf,et al.  Geometric morphometrics: Ten years of progress following the ‘revolution’ , 2004 .

[132]  Alain Trouvé,et al.  Foundations of Computational Mathematics Metamorphoses through Lie Group Action , 2005 .

[133]  David J. Hand,et al.  Measuring Diagnostic Accuracy of Statistical Prediction Rules , 2001 .

[134]  Juan Ruiz-Alzola,et al.  Nonrigid registration of 3D tensor medical data , 2002, Medical Image Anal..

[135]  Bernhard Schölkopf,et al.  Nonlinear causal discovery with additive noise models , 2008, NIPS.

[136]  H. Markram.  The Blue Brain Project , 2006, Nature Reviews Neuroscience.

[137]  Carl-Fredrik Westin,et al.  Spatial normalization of diffusion tensor MRI using multiple channels , 2003, NeuroImage.

[138]  Marie Chupin,et al.  Multidimensional classification of hippocampal shape features discriminates Alzheimer's disease and mild cognitive impairment from normal aging , 2009, NeuroImage.

[139]  Michael I. Miller,et al.  Pattern Theory: From Representation to Inference , 2007 .

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

[141]  Nick C Fox,et al.  Automatic classification of MR scans in Alzheimer's disease. , 2008, Brain : a journal of neurology.

[142]  D. Mumford.  Pattern theory: a unifying perspective , 1996 .

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

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

[145]  Clifford R. Jack,et al.  Alzheimer's disease diagnosis in individual subjects using structural MR images: Validation studies , 2008, NeuroImage.

[146]  Tom M. Mitchell,et al.  Learning to Decode Cognitive States from Brain Images , 2004, Machine Learning.

[147]  M. Miller.  Computational anatomy: shape, growth, and atrophy comparison via diffeomorphisms , 2004, NeuroImage.

[148]  Christos Davatzikos,et al.  Morphological Appearance Manifolds in Computational Anatomy: Groupwise Registration and Morphological Analysis , 2009, ISBI.

[149]  Zoubin Ghahramani,et al.  Variational Inference for Bayesian Mixtures of Factor Analysers , 1999, NIPS.

[150]  J. Doyle,et al.  Reverse Engineering of Biological Complexity , 2002, Science.

[151]  Arthur W. Toga,et al.  Human brain white matter atlas: Identification and assignment of common anatomical structures in superficial white matter , 2008, NeuroImage.

[152]  David Mumford,et al.  Empirical Statistics and Stochastic Models for Visual Signals , 2006 .

[153]  Thomas E. Nichols,et al.  Statistical limitations in functional neuroimaging. I. Non-inferential methods and statistical models. , 1999, Philosophical transactions of the Royal Society of London. Series B, Biological sciences.

[154]  Karl J. Friston,et al.  A multivariate analysis of PET activation studies , 1996, Human brain mapping.

[155]  H. Benali,et al.  Support vector machine-based classification of Alzheimer’s disease from whole-brain anatomical MRI , 2009, Neuroradiology.

[156]  Tom Minka,et al.  Principled Hybrids of Generative and Discriminative Models , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).