A Mixed L2 Norm Regularized HRF Estimation Method for Rapid Event-Related fMRI Experiments

Brain state decoding or “mind reading” via multivoxel pattern analysis (MVPA) has become a popular focus of functional magnetic resonance imaging (fMRI) studies. In brain decoding, stimulus presentation rate is increased as fast as possible to collect many training samples and obtain an effective and reliable classifier or computational model. However, for extremely rapid event-related experiments, the blood-oxygen-level-dependent (BOLD) signals evoked by adjacent trials are heavily overlapped in the time domain. Thus, identifying trial-specific BOLD responses is difficult. In addition, voxel-specific hemodynamic response function (HRF), which is useful in MVPA, should be used in estimation to decrease the loss of weak information across voxels and obtain fine-grained spatial information. Regularization methods have been widely used to increase the efficiency of HRF estimates. In this study, we propose a regularization framework called mixed L2 norm regularization. This framework involves Tikhonov regularization and an additional L2 norm regularization term to calculate reliable HRF estimates. This technique improves the accuracy of HRF estimates and significantly increases the classification accuracy of the brain decoding task when applied to a rapid event-related four-category object classification experiment. At last, some essential issues such as the impact of low-frequency fluctuation (LFF) and the influence of smoothing are discussed for rapid event-related experiments.

• Publication year

  2013

• Venue

  Comput. Math. Methods Medicine

• Publication date

  2013-05-12

• Fields of study

  Medicine, Computer Science

• Identifiers
  DOI 10.1155/2013/643129PMID 23762193PMCID 3665251
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• Decoding visual brain states from fMRI using an ensemble of classifiers

  2012cited by this paper
• Deconvolving BOLD activation in event-related designs for multivoxel pattern classification analyses

  2012influential reference
• Linear systems analysis of the fMRI signal

  2012cited by this paper
• Nonparametric inference of the hemodynamic response using multi-subject fMRI data

  2012cited by this paper
• Utilizing temporal information in fMRI decoding: Classifier using kernel regression methods

  2011cited by this paper
• LIBSVM: A library for support vector machines

  2011cited by this paper
• Comparative Study of SVM Methods Combined with Voxel Selection for Object Category Classification on fMRI Data

  2011cited by this paper
• Computational and Mathematical Methods in Medicine

  2011cited by this paper
• Against hyperacuity in brain reading: Spatial smoothing does not hurt multivariate fMRI analyses?

  2010cited by this paper
• Reading the mind's eye: Decoding category information during mental imagery

  2010cited by this paper
• Bayesian reconstruction of natural images from human brain activity.

  2009cited by this paper
• Comments and Controversies Spatial smoothing hurts localization but not information : Pitfalls for brain mappers

  2009cited by this paper
• Evaluating the impact of spatio-temporal smoothness constraints on the BOLD hemodynamic response function estimation: an analysis based on Tikhonov regularization

  2009cited by this paper
• Revealing representational content with pattern-information fMRI--an introductory guide.

  2009cited by this paper
• Data-driven haemodynamic response function extraction using Fourier-wavelet regularised deconvolution

  2008cited by this paper
• The impact of temporal regularization on estimates of the BOLD hemodynamic response function: A comparative analysis

  2008cited by this paper
• Multivariate analysis of fMRI time series: classification and regression of brain responses using machine learning.

  2008cited by this paper
• Identifying natural images from human brain activity

  2008cited by this paper
• Modeling low‐frequency fluctuation and hemodynamic response timecourse in event‐related fMRI

  2008cited by this paper
• Comments and Controversies Analyzing for information, not activation, to exploit high-resolution fMRI

  2007cited by this paper
• Characterizing the functional MRI response using Tikhonov regularization

  2007cited by this paper
• Computational and mathematical methods in medicine.

  2006cited by this paper
• Decoding the visual and subjective contents of the human brain

  2005cited by this paper
• BMC Medical Imaging BioMed Central

  2005cited by this paper
• Constrained linear basis sets for HRF modelling using Variational Bayes

  2004cited by this paper
• A state-space model of the hemodynamic approach: nonlinear filtering of BOLD signals

  2004cited by this paper
• Convex Optimization

  2004cited by this paper
• Temporal Autocorrelation in Univariate Linear Modeling of FMRI Data

  2001cited by this paper
• Distributed and Overlapping Representations of Faces and Objects in Ventral Temporal Cortex

  2001cited by this paper
• Modeling the hemodynamic response in fMRI using smooth FIR filters

  2000cited by this paper
• Ridge Regression: Biased Estimation for Nonorthogonal Problems

  2000cited by this paper
• Optimal experimental design for event‐related fMRI

  1999cited by this paper
• Investigation of low frequency drift in fMRI signal.

  1999cited by this paper
• Nonlinear event‐related responses in fMRI

  1998cited by this paper
• The variability of human, BOLD hemodynamic responses.

  1998cited by this paper
• Event-related fMRI: characterizing differential responses.

  1998cited by this paper
• Borders of multiple visual areas in humans revealed by functional magnetic resonance imaging.

  1995cited by this paper
• Analysis of functional MRI time‐series

  1994cited by this paper
• Adjacent zinc-finger motifs in multiple zinc-finger peptides from SWI5 form structurally independent, flexibly linked domains.

  1992cited by this paper
• Numerische Mathematik 1

  1989cited by this paper
• Partial least-squares regression: a tutorial

  1986cited by this paper
• The Molecular Biology of Aging

  1986cited by this paper
• Smoothing noisy data with spline functions

  1978cited by this paper
• Estimating the Dimension of a Model

  1978cited by this paper
• A new look at the statistical model identification

  1974cited by this paper
• See Blockindiscussions, Blockinstats, Blockinand Blockinauthor Blockinprofiles Blockinfor Blockinthis Blockinpublication Comparison Blockinof Blockindetrending Blockinmethods Blockinfor Optimal Blockinfmri Blockinpreprocessing

  year unknowncited by this paper
• Human Neuroscience

  year unknowncited by this paper
• Category Selectivity in the Ventral obustness to Clutter and Diverted Attention

  year unknowncited by this paper

• HRfunc: a tool for modeling hemodynamic response variability in fNIRS

  2025cites this paper
• Evaluating Computational Models of Vision with Functional Magnetic Resonance Imaging. (Évaluation de modèles computationnels de la vision humaine en imagerie par résonance magnétique fonctionnelle)

  2015cites this paper
• A focused information criterion for graphical models in fMRI connectivity with high-dimensional data

  2015cites this paper
• Functional Brain Imaging of Human Olfaction

  2015cites this paper
• Feature extraction and supervised learning on fMRI : from practice to theory

  2015cites this paper
• Data-driven HRF estimation for encoding and decoding models

  2014cites this paper
• Principal Feature Analysis: A Multivariate Feature Selection Method for fMRI Data

  2013cites this paper