Bayesian decoding of brain images

This paper introduces a multivariate Bayesian (MVB) scheme to decode or recognise brain states from neuroimages. It resolves the ill-posed many-to-one mapping, from voxel values or data features to a target variable, using a parametric empirical or hierarchical Bayesian model. This model is inverted using standard variational techniques, in this case expectation maximisation, to furnish the model evidence and the conditional density of the model's parameters. This allows one to compare different models or hypotheses about the mapping from functional or structural anatomy to perceptual and behavioural consequences (or their deficits). We frame this approach in terms of decoding measured brain states to predict or classify outcomes using the rhetoric established in pattern classification of neuroimaging data. However, the aim of MVB is not to predict (because the outcomes are known) but to enable inference on different models of structure-function mappings; such as distributed and sparse representations. This allows one to optimise the model itself and produce predictions that outperform standard pattern classification approaches, like support vector machines. Technically, the model inversion and inference uses the same empirical Bayesian procedures developed for ill-posed inverse problems (e.g., source reconstruction in EEG). However, the MVB scheme used here extends this approach to include a greedy search for sparse solutions. It reduces the problem to the same form used in Gaussian process modelling, which affords a generic and efficient scheme for model optimisation and evaluating model evidence. We illustrate MVB using simulated and real data, with a special focus on model comparison; where models can differ in the form of the mapping (i.e., neuronal representation) within one region, or in the (combination of) regions per se.

[1]  R. Hales,et al.  J Neuropsychiatry Clin Neurosci , 1992 .

[2]  T. Carlson,et al.  Patterns of Activity in the Categorical Representations of Objects , 2003 .

[3]  M. Aizerman,et al.  Theoretical Foundations of the Potential Function Method in Pattern Recognition Learning , 1964 .

[4]  Geoffrey E. Hinton,et al.  A View of the Em Algorithm that Justifies Incremental, Sparse, and other Variants , 1998, Learning in Graphical Models.

[5]  Colin Blakemore,et al.  Vision: Coding and Efficiency , 1991 .

[6]  Matthew J. Beal Variational algorithms for approximate Bayesian inference , 2003 .

[7]  K. Friston,et al.  APPENDIX 1 – Linear models and inference , 2007 .

[8]  Edward H Herskovits,et al.  Application of a data-mining method based on Bayesian networks to lesion-deficit analysis , 2003, NeuroImage.

[9]  Sean M. Polyn,et al.  Beyond mind-reading: multi-voxel pattern analysis of fMRI data , 2006, Trends in Cognitive Sciences.

[10]  George Eastman House,et al.  Sparse Bayesian Learning and the Relevan e Ve tor Ma hine , 2001 .

[11]  S. Zeki Vision: The motion pathways of the visual cortex , 1991 .

[12]  F. Tong,et al.  Decoding Seen and Attended Motion Directions from Activity in the Human Visual Cortex , 2006, Current Biology.

[13]  S. Strother,et al.  Scaled Subprofile Model: A Statistical Approach to the Analysis of Functional Patterns in Positron Emission Tomographic Data , 1987, Journal of cerebral blood flow and metabolism : official journal of the International Society of Cerebral Blood Flow and Metabolism.

[14]  Dietmar Cordes,et al.  Novel nonparametric approach to canonical correlation analysis with applications to low CNR functional MRI data , 2003, Magnetic resonance in medicine.

[15]  Jean-Baptiste Poline,et al.  Inverse retinotopy: Inferring the visual content of images from brain activation patterns , 2006, NeuroImage.

[16]  Christopher M. Bishop,et al.  Variational Relevance Vector Machines , 2000, UAI.

[17]  H. Knutsson,et al.  Detection of neural activity in functional MRI using canonical correlation analysis , 2001, Magnetic resonance in medicine.

[18]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[19]  Lars Kai Hansen,et al.  Massive Weight Sharing: A Cure For Extremely Ill-Posed Problems , 1994 .

[20]  Karl J. Friston,et al.  Characterizing Stimulus–Response Functions Using Nonlinear Regressors in Parametric fMRI Experiments , 1998, NeuroImage.

[21]  Karl J. Friston,et al.  Degeneracy and cognitive anatomy , 2002, Trends in Cognitive Sciences.

[22]  Karl J. Friston,et al.  Characterizing the Response of PET and fMRI Data Using Multivariate Linear Models , 1997, NeuroImage.

[23]  David J. C. MacKay,et al.  Comparison of Approximate Methods for Handling Hyperparameters , 1999, Neural Computation.

[24]  Rainer Goebel,et al.  Information-based functional brain mapping. , 2006, Proceedings of the National Academy of Sciences of the United States of America.

[25]  Mark A. Pitt,et al.  Advances in Minimum Description Length: Theory and Applications , 2005 .

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

[27]  G. Rees,et al.  Neuroimaging: Decoding mental states from brain activity in humans , 2006, Nature Reviews Neuroscience.

[28]  David D. Cox,et al.  Functional magnetic resonance imaging (fMRI) “brain reading”: detecting and classifying distributed patterns of fMRI activity in human visual cortex , 2003, NeuroImage.

[29]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[30]  D. Harville Maximum Likelihood Approaches to Variance Component Estimation and to Related Problems , 1977 .

[31]  Karl J. Friston,et al.  Statistical parametric mapping , 2013 .

[32]  Hyun-Chul Kim,et al.  Bayesian Gaussian Process Classification with the EM-EP Algorithm , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[33]  Harry Wechsler,et al.  From Statistics to Neural Networks , 1994, NATO ASI Series.

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

[35]  Karl J. Friston,et al.  Unified segmentation , 2005, NeuroImage.

[36]  Brian D. Ripley,et al.  Flexible Non-linear Approaches to Classification , 1994 .

[37]  Karl J. Friston,et al.  An empirical Bayesian solution to the source reconstruction problem in EEG , 2005, NeuroImage.

[38]  R. Kass,et al.  Approximate Bayesian Inference in Conditionally Independent Hierarchical Models (Parametric Empirical Bayes Models) , 1989 .

[39]  Karl J. Friston,et al.  Entropy and cortical activity: information theory and PET findings. , 1992, Cerebral cortex.

[40]  Stephen C. Strother,et al.  An evaluation of methods for detecting brain activations from functional neuroimages , 2002, Artif. Intell. Medicine.

[41]  Karl J. Friston,et al.  MEG source localization under multiple constraints: An extended Bayesian framework , 2006, NeuroImage.

[42]  Stephen José Hanson,et al.  Combinatorial codes in ventral temporal lobe for object recognition: Haxby (2001) revisited: is there a “face” area? , 2004, NeuroImage.

[43]  D. Mackay,et al.  Introduction to Gaussian processes , 1998 .

[44]  Manel Martínez-Ramón,et al.  fMRI pattern classification using neuroanatomically constrained boosting , 2006, NeuroImage.

[45]  E. Mugnaini,et al.  Cell junctions and intramembrane particles of astrocytes and oligodendrocytes: A freeze-fracture study , 1982, Neuroscience.

[46]  R. Malach,et al.  Intersubject Synchronization of Cortical Activity During Natural Vision , 2004, Science.

[47]  Karl J. Friston,et al.  Detecting Activations in PET and fMRI: Levels of Inference and Power , 1996, NeuroImage.

[48]  Ryo Takeuchi,et al.  Interpolation models with multiple hyperparameters , 1998, Stat. Comput..

[49]  Karl J. Friston,et al.  The left medial temporal region and schizophrenia. A PET study. , 1992, Brain : a journal of neurology.

[50]  R. Turner,et al.  Characterizing Dynamic Brain Responses with fMRI: A Multivariate Approach , 1995, NeuroImage.

[51]  B. Efron,et al.  Stein's Estimation Rule and Its Competitors- An Empirical Bayes Approach , 1973 .

[52]  宁北芳,et al.  疟原虫var基因转换速率变化导致抗原变异[英]/Paul H, Robert P, Christodoulou Z, et al//Proc Natl Acad Sci U S A , 2005 .

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

[54]  Karl J. Friston,et al.  Classical and Bayesian Inference in Neuroimaging: Theory , 2002, NeuroImage.

[55]  M. V. Rossum,et al.  In Neural Computation , 2022 .

[56]  John Skilling,et al.  Maximum Entropy and Bayesian Methods , 1989 .

[57]  Geoffrey E. Hinton,et al.  Evaluation of Gaussian processes and other methods for non-linear regression , 1997 .

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

[59]  J V Haxby,et al.  Subgroups in dementia of the Alzheimer type identified using positron emission tomography. , 1990, The Journal of neuropsychiatry and clinical neurosciences.

[60]  G. Rees,et al.  Predicting the orientation of invisible stimuli from activity in human primary visual cortex , 2005, Nature Neuroscience.

[61]  A W Toga,et al.  Quantification of white matter and gray matter volumes from T1 parametric images using fuzzy classifiers , 1996, Journal of magnetic resonance imaging : JMRI.