Informed feature regularization in voxelwise modeling for naturalistic fMRI experiments

Voxelwise modeling is a powerful framework to predict single‐voxel functional selectivity for the stimulus features that exist in complex natural stimuli. Yet, because VM disregards potential correlations across stimulus features or neighboring voxels, it may yield suboptimal sensitivity in measuring functional selectivity in the presence of high levels of measurement noise. Here, we introduce a novel voxelwise modeling approach that simultaneously utilizes stimulus correlations in model features and response correlations among voxel neighborhoods. The proposed method performs feature and spatial regularization while still generating single‐voxel response predictions. We demonstrated the performance of our approach on a functional magnetic resonance imaging dataset from a natural vision experiment. Compared to VM, the proposed method yields clear improvements in prediction performance, together with increased feature coherence and spatial coherence of voxelwise models. Overall, the proposed method can offer improved sensitivity in modeling of single voxels in naturalistic functional magnetic resonance imaging experiments.

[1]  Dinggang Shen,et al.  A novel relational regularization feature selection method for joint regression and classification in AD diagnosis , 2017, Medical Image Anal..

[2]  M. D’Esposito,et al.  Empirical analyses of BOLD fMRI statistics. I. Spatially unsmoothed data collected under null-hypothesis conditions. , 1997, NeuroImage.

[3]  Peter Wiemer-Hastings,et al.  Latent semantic analysis , 2004, Annu. Rev. Inf. Sci. Technol..

[4]  George A. Miller,et al.  WordNet: A Lexical Database for English , 1995, HLT.

[5]  Tolga Çukur,et al.  Functional Subdomains within Human FFA , 2013, The Journal of Neuroscience.

[6]  Thomas L. Griffiths,et al.  Supplementary Information for Natural Speech Reveals the Semantic Maps That Tile Human Cerebral Cortex , 2022 .

[7]  N. Kanwisher,et al.  Domain specificity in visual cortex. , 2006, Cerebral cortex.

[8]  Nancy Kanwisher,et al.  A cortical representation of the local visual environment , 1998, Nature.

[9]  Alexander G. Huth,et al.  Attention During Natural Vision Warps Semantic Representation Across the Human Brain , 2013, Nature Neuroscience.

[10]  Wei Luo,et al.  Stabilized sparse ordinal regression for medical risk stratification , 2014, Knowledge and Information Systems.

[11]  J. Gallant,et al.  Reconstructing Visual Experiences from Brain Activity Evoked by Natural Movies , 2011, Current Biology.

[12]  T. Schormann,et al.  Functional delineation of the human occipito-temporal areas related to face and scene processing. A PET study. , 2000, Brain : a journal of neurology.

[13]  Arthur E. Hoerl,et al.  Ridge Regression: Biased Estimation for Nonorthogonal Problems , 2000, Technometrics.

[14]  Jack L. Gallant,et al.  A Continuous Semantic Space Describes the Representation of Thousands of Object and Action Categories across the Human Brain , 2012, Neuron.

[15]  Brian Murphy,et al.  Simultaneously Uncovering the Patterns of Brain Regions Involved in Different Story Reading Subprocesses , 2014, PloS one.

[16]  Tom Michael Mitchell,et al.  Predicting Human Brain Activity Associated with the Meanings of Nouns , 2008, Science.

[17]  N. Kanwisher,et al.  Interpreting fMRI data: maps, modules and dimensions , 2008, Nature Reviews Neuroscience.

[18]  Nikolaus Kriegeskorte,et al.  The Emergence of Semantic Meaning in the Ventral Temporal Pathway , 2014, Journal of Cognitive Neuroscience.

[19]  Geoffrey Zweig,et al.  Linguistic Regularities in Continuous Space Word Representations , 2013, NAACL.

[20]  J. S. Guntupalli,et al.  The Representation of Biological Classes in the Human Brain , 2012, The Journal of Neuroscience.

[21]  G. Glover,et al.  Retinotopic organization in human visual cortex and the spatial precision of functional MRI. , 1997, Cerebral cortex.

[22]  D. V. van Essen,et al.  Functional and structural mapping of human cerebral cortex: solutions are in the surfaces. , 1998, Proceedings of the National Academy of Sciences of the United States of America.

[23]  N. Kanwisher,et al.  The Fusiform Face Area: A Module in Human Extrastriate Cortex Specialized for Face Perception , 1997, The Journal of Neuroscience.

[24]  N. Kanwisher,et al.  The Human Body , 2001 .

[25]  Alexander Borst,et al.  Quantifying variability in neural responses and its application for the validation of model predictions , 2004, Network.

[26]  J. Gallant,et al.  Predicting neuronal responses during natural vision , 2005, Network.

[27]  John Blitzer,et al.  Regularized Learning with Networks of Features , 2008, NIPS.

[28]  Richard A. Harshman,et al.  Indexing by Latent Semantic Analysis , 1990, J. Am. Soc. Inf. Sci..

[29]  Ryan J. Prenger,et al.  Bayesian Reconstruction of Natural Images from Human Brain Activity , 2009, Neuron.

[30]  Klaus Schulten,et al.  Models of Orientation and Ocular Dominance Columns in the Visual Cortex: A Critical Comparison , 1995, Neural Computation.

[31]  Tom Heskes,et al.  Linear reconstruction of perceived images from human brain activity , 2013, NeuroImage.

[32]  Jack L. Gallant,et al.  Voxelwise encoding models with non-spherical multivariate normal priors , 2018, NeuroImage.

[33]  Maneesh Sahani,et al.  How Linear are Auditory Cortical Responses? , 2002, NIPS.

[34]  Junxing Shi,et al.  Deep Residual Network Predicts Cortical Representation and Organization of Visual Features for Rapid Categorization , 2018, Scientific Reports.

[35]  Curt Burgess,et al.  Producing high-dimensional semantic spaces from lexical co-occurrence , 1996 .

[36]  Bertrand Thirion,et al.  An empirical comparison of surface-based and volume-based group studies in neuroimaging , 2012, NeuroImage.

[37]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

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

[39]  Patrick Pantel,et al.  From Frequency to Meaning: Vector Space Models of Semantics , 2010, J. Artif. Intell. Res..

[40]  Mari Ostendorf,et al.  Semi-supervised learning for text classification using feature affinity regularization , 2012, MLSLP.

[41]  J. Gallant,et al.  Identifying natural images from human brain activity , 2008, Nature.

[42]  L. Tyler,et al.  Understanding What We See: How We Derive Meaning From Vision , 2015, Trends in Cognitive Sciences.

[43]  Mark W. Woolrich,et al.  Bayesian analysis of neuroimaging data in FSL , 2009, NeuroImage.

[44]  Tolga Çukur,et al.  Spatially informed voxelwise modeling for naturalistic fMRI experiments , 2019, NeuroImage.

[45]  Anders M. Dale,et al.  Cortical Surface-Based Analysis I. Segmentation and Surface Reconstruction , 1999, NeuroImage.

[46]  Jonathan E. Taylor,et al.  Interpretable whole-brain prediction analysis with GraphNet , 2013, NeuroImage.

[47]  A. Dale,et al.  Functional analysis of primary visual cortex (V1) in humans. , 1998, Proceedings of the National Academy of Sciences of the United States of America.

[48]  Jack L. Gallant,et al.  Pycortex: an interactive surface visualizer for fMRI , 2015, Front. Neuroinform..

[49]  Jack L. Gallant,et al.  Fourier power, subjective distance, and object categories all provide plausible models of BOLD responses in scene-selective visual areas , 2015, Front. Comput. Neurosci..