An empirical comparison of different LDA methods in fMRI-based brain states decoding.

Decoding brain states from response patterns with multivariate pattern recognition techniques is a popular method for detecting multivoxel patterns of brain activation. These patterns are informative with respect to a subject's perceptual or cognitive states. Linear discriminant analysis (LDA) cannot be directly applied to fMRI data analysis because of the "few samples and large features" nature of functional magnetic resonance imaging (fMRI) data. Although several improved LDA methods have been used in fMRI-based decoding, little is known regarding the relative performance of different LDA classifiers on fMRI data. In this study, we compared five LDA classifiers using both simulated data with varied noise levels and real fMRI data. The compared LDA classifiers include LDA combined with PCA (LDA-PCA), LDA with three types of regularizations (identity matrix, diagonal matrix and scaled identity matrix) and LDA with optimal-shrinkage covariance estimator using Ledoit and Wolf lemma (LDA-LW). The results indicated that LDA-LW was the most robust to noises. Moreover, LDA-LW and LDA with scaled identity matrix showed better stability and classification accuracy than the other methods. LDA-LW demonstrated the best overall performance.

[1]  Arthur Gretton,et al.  Comparison of Pattern Recognition Methods in Classifying High-resolution Bold Signals Obtained at High Magnetic Field in Monkeys , 2008 .

[2]  Zhiying Long,et al.  Improved sparse decomposition based on a smoothed L0 norm using a Laplacian kernel to select features from fMRI data , 2015, Journal of Neuroscience Methods.

[3]  Konstantinos N. Plataniotis,et al.  Regularization studies of linear discriminant analysis in small sample size scenarios with application to face recognition , 2005, Pattern Recognit. Lett..

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

[5]  Olivier Ledoit,et al.  Improved estimation of the covariance matrix of stock returns with an application to portfolio selection , 2003 .

[6]  Stephen C. Strother,et al.  Support vector machines for temporal classification of block design fMRI data , 2005, NeuroImage.

[7]  Charles A. Bouman,et al.  Covariance Estimation for High Dimensional Data Vectors Using the Sparse Matrix Transform , 2008, NIPS.

[8]  Tao Li,et al.  Using discriminant analysis for multi-class classification: an experimental investigation , 2006, Knowledge and Information Systems.

[9]  Nikolaus Kriegeskorte,et al.  Comparison of multivariate classifiers and response normalizations for pattern-information fMRI , 2010, NeuroImage.

[10]  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.

[11]  K. Strimmer,et al.  Statistical Applications in Genetics and Molecular Biology A Shrinkage Approach to Large-Scale Covariance Matrix Estimation and Implications for Functional Genomics , 2011 .

[12]  R. Fisher.  THE USE OF MULTIPLE MEASUREMENTS IN TAXONOMIC PROBLEMS , 1936 .

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

[14]  Janaina Mourão Miranda,et al.  Classifying brain states and determining the discriminating activation patterns: Support Vector Machine on functional MRI data , 2005, NeuroImage.