Automatic independent component labeling for artifact removal in fMRI

Blood oxygenation level dependent (BOLD) signals in functional magnetic resonance imaging (fMRI) are often small compared to the level of noise in the data. The sources of noise are numerous including different kinds of motion artifacts and physiological noise with complex patterns. This complicates the statistical analysis of the fMRI data. In this study, we propose an automatic method to reduce fMRI artifacts based on independent component analysis (ICA). We trained a supervised classifier to distinguish between independent components relating to a potentially task-related signal and independent components clearly relating to structured noise. After the components had been classified as either signal or noise, a denoised fMR time-series was reconstructed based only on the independent components classified as potentially task-related. The classifier was a novel global (fixed structure) decision tree trained in a Neyman-Pearson (NP) framework, which allowed the shape of the decision regions to be controlled effectively. Additionally, the conservativeness of the classifier could be tuned by modifying the NP threshold. The classifier was tested against the component classifications by an expert with the data from a category learning task. The test set as well as the expert were different from the data used for classifier training and the expert labeling the training set. The misclassification rate was between 0.2 and 0.3 for both the event-related and blocked designs and it was consistent among variety of different NP thresholds. The effects of denoising on the group-level statistical analyses were as expected: The denoising generally decreased Z-scores in the white matter, where extreme Z-values can be expected to reflect artifacts. A similar but weaker decrease in Z-scores was observed in the gray matter on average. These two observations suggest that denoising was likely to reduce artifacts from gray matter and could be useful to improve the detection of activations. We conclude that automatic ICA-based denoising offers a potentially useful approach to improve the quality of fMRI data and consequently increase the accuracy of the statistical analysis of these data.

[1]  Rainer Goebel,et al.  Real-time independent component analysis of fMRI time-series , 2003, NeuroImage.

[2]  Jörn Diedrichsen,et al.  Detecting and adjusting for artifacts in fMRI time series data , 2005, NeuroImage.

[3]  David G. Stork,et al.  Pattern classification, 2nd Edition , 2000 .

[4]  E. DeYoe,et al.  Reduction of physiological fluctuations in fMRI using digital filters , 1996, Magnetic resonance in medicine.

[5]  Gary H Glover,et al.  Estimating sample size in functional MRI (fMRI) neuroimaging studies: Statistical power analyses , 2002, Journal of Neuroscience Methods.

[6]  J. O'Doherty,et al.  Dissociating Valence of Outcome from Behavioral Control in Human Orbital and Ventral Prefrontal Cortices , 2003, The Journal of Neuroscience.

[7]  Petre Stoica,et al.  Introduction to spectral analysis , 1997 .

[8]  Rui Liao,et al.  Isolation and minimization of head motion‐induced signal variations in fMRI data using independent component analysis , 2006, Magnetic resonance in medicine.

[9]  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.

[10]  Russell A. Poldrack,et al.  Long-term test–retest reliability of functional MRI in a classification learning task , 2006, NeuroImage.

[11]  Erkki Oja,et al.  Independent component analysis: algorithms and applications , 2000, Neural Networks.

[12]  Baxter P Rogers,et al.  Power spectrum ranked independent component analysis of a periodic fMRI complex motor paradigm , 2003, Human brain mapping.

[13]  Michael S Beauchamp,et al.  Detection of eye movements from fMRI data , 2003, Magnetic resonance in medicine.

[14]  Karl J. Friston,et al.  Human Brain Function , 1997 .

[15]  Richard G. Baraniuk,et al.  Controlling False Alarms With Support Vector Machines , 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

[16]  C. R. Rao,et al.  A Decomposition Theorem for Vector Variables with a Linear Structure , 1969 .

[17]  Ari Visa,et al.  Reproducibility of fMRI: Effect of the Use of Contextual Information , 2001, NeuroImage.

[18]  TreesKristin P. Bennett,et al.  Optimal Decision Trees , 1996 .

[19]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

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

[21]  M. McKeown.  Detection of Consistently Task-Related Activations in fMRI Data with Hybrid Independent Component Analysis , 2000, NeuroImage.

[22]  Michael Brady,et al.  Improved Optimization for the Robust and Accurate Linear Registration and Motion Correction of Brain Images , 2002, NeuroImage.

[23]  Mark W. Woolrich,et al.  Advances in functional and structural MR image analysis and implementation as FSL , 2004, NeuroImage.

[24]  Stephen M Smith,et al.  Fast robust automated brain extraction , 2002, Human brain mapping.

[25]  Robert Tibshirani,et al.  Bootstrap Methods for Standard Errors, Confidence Intervals, and Other Measures of Statistical Accuracy , 1986 .

[26]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[27]  Habib Benali,et al.  CORSICA: correction of structured noise in fMRI by automatic identification of ICA components. , 2007, Magnetic resonance imaging.

[28]  Aapo Hyvärinen,et al.  Validating the independent components of neuroimaging time series via clustering and visualization , 2004, NeuroImage.

[29]  N. Tzourio-Mazoyer,et al.  Automated Anatomical Labeling of Activations in SPM Using a Macroscopic Anatomical Parcellation of the MNI MRI Single-Subject Brain , 2002, NeuroImage.

[30]  Rainer Goebel,et al.  Classification of fMRI independent components using IC-fingerprints and support vector machine classifiers , 2007, NeuroImage.

[31]  L. K. Hansen,et al.  Independent component analysis of functional MRI: what is signal and what is noise? , 2003, Current Opinion in Neurobiology.

[32]  J. Hanley,et al.  The meaning and use of the area under a receiver operating characteristic (ROC) curve. , 1982, Radiology.

[33]  Stephen M. Smith,et al.  General multilevel linear modeling for group analysis in FMRI , 2003, NeuroImage.

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

[35]  G. Glover,et al.  Physiological noise in oxygenation‐sensitive magnetic resonance imaging , 2001, Magnetic resonance in medicine.

[36]  Stephen M. Smith,et al.  A global optimisation method for robust affine registration of brain images , 2001, Medical Image Anal..

[37]  Karl J. Friston,et al.  Movement‐Related effects in fMRI time‐series , 1996, Magnetic resonance in medicine.

[38]  R. Turner,et al.  Characterization and Correction of Interpolation Effects in the Realignment of fMRI Time Series , 2000, NeuroImage.

[39]  Jean-Francois Mangin,et al.  What is the best similarity measure for motion correction in fMRI time series? , 2002, IEEE Transactions on Medical Imaging.

[40]  L. Freire,et al.  Motion Correction Algorithms May Create Spurious Brain Activations in the Absence of Subject Motion , 2001, NeuroImage.

[41]  Richard A. Harshman,et al.  Noise Reduction in BOLD-Based fMRI Using Component Analysis , 2002, NeuroImage.

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

[43]  Rainer Goebel,et al.  Cortex-based independent component analysis of fMRI time series. , 2004 .

[44]  S Makeig,et al.  Analysis of fMRI data by blind separation into independent spatial components , 1998, Human brain mapping.

[45]  Karl J. Friston,et al.  Assessing the significance of focal activations using their spatial extent , 1994, Human brain mapping.

[46]  Kristin P. Bennett,et al.  Global Tree Optimization: A Non-greedy Decision Tree Algorithm , 2007 .

[47]  D. Louis Collins,et al.  Design and construction of a realistic digital brain phantom , 1998, IEEE Transactions on Medical Imaging.

[48]  Norihiro Sadato,et al.  Removing the effects of task-related motion using independent-component analysis , 2005, NeuroImage.

[49]  Russell A Poldrack,et al.  Modulation of competing memory systems by distraction. , 2006, Proceedings of the National Academy of Sciences of the United States of America.

[50]  Stephen M. Smith,et al.  Temporal Autocorrelation in Univariate Linear Modeling of FMRI Data , 2001, NeuroImage.

[51]  Martin J. McKeown,et al.  An information-theoretic criterion for intrasubject alignment of FMRI time series: motion corrected independent component analysis , 2005, IEEE Transactions on Medical Imaging.

[52]  Thomas E. Nichols,et al.  Non-white noise in fMRI: Does modelling have an impact? , 2006, NeuroImage.

[53]  J. Lewin,et al.  Inadequacy of motion correction algorithms in functional MRI: Role of susceptibility‐induced artifacts , 1997, Journal of magnetic resonance imaging : JMRI.