Node merging in Kohonen's self-organizing mapping of fMRI data

In this paper, Kohonen's self-organizing mapping (SOM) is used as a data-driven technique for analyzing functional magnetic resonance imaging (fMRI) data. Upon the completion of an SOM analysis, a cluster merging technique, based on examining the reproducibility of the fMRI data across epochs, is utilized to merge SOM nodes whose feature vectors are sufficiently similar to one another. The resulting 'super nodes' give time course templates of potential interest. These templates can be subsequently used in traditional template-based analysis methods, such as cross-correlation analysis, yielding statistical maps and activation patterns. This technique has been demonstrated on two fMRI datasets obtained from a visually-guided motor paradigm and a visual paradigm, respectively, showing satisfactory results.

[1]  J. Nazuno.  Haykin, Simon. Neural networks: A comprehensive foundation, Prentice Hall, Inc. Segunda Edición, 1999 , 2000 .

[2]  R. S. Hinks,et al.  Time course EPI of human brain function during task activation , 1992, Magnetic resonance in medicine.

[3]  S Makeig,et al.  Spatially independent activity patterns in functional MRI data during the stroop color-naming task. , 1998, Proceedings of the National Academy of Sciences of the United States of America.

[4]  L. K. Hansen,et al.  Feature‐space clustering for fMRI meta‐analysis , 2001, Human brain mapping.

[5]  R Baumgartner,et al.  Wavelet domain de-noising of time-courses in MR image sequences. , 2000, Magnetic resonance imaging.

[6]  E. Yacoub,et al.  Nonadditive Two-Way ANOVA for Event-Related fMRI Data Analysis , 2001, NeuroImage.

[7]  R. Baumgartner,et al.  Correlator Beware: Correlation Has Limited Selectivity for fMRI Data Analysis , 2000, NeuroImage.

[8]  Stephen J. Uftring,et al.  Detecting Brain Activation in FMRI Data without Prior Knowledge of Mental Event Timing , 2000, NeuroImage.

[9]  X. Hu,et al.  Evaluation of the early response in fMRI in individual subjects using short stimulus duration , 1997, Magnetic resonance in medicine.

[10]  Vladimir Cherkassky,et al.  Learning from Data: Concepts, Theory, and Methods , 1998 .

[11]  A M Dale,et al.  Event-related functional MRI: past, present, and future. , 1998, Proceedings of the National Academy of Sciences of the United States of America.

[12]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[13]  Shing-Chung Ngan,et al.  Temporal Filtering of Event-Related fMRI Data Using Cross-Validation , 2000, NeuroImage.

[14]  L Ryner,et al.  Novelty indices: identifiers of potentially interesting time-courses in functional MRI data. , 2000, Magnetic resonance imaging.

[15]  Richard Bowtell,et al.  Detecting activations in event‐related fMRI using analysis of variance , 1999, Magnetic resonance in medicine.

[16]  X Hu,et al.  Activation detection in event-related fMRI data based on spatio-temporal properties. , 2001, Magnetic resonance imaging.

[17]  J. Strupp.  Stimulate: A GUI based fMRI analysis software package , 1996, NeuroImage.

[18]  X Hu,et al.  Analysis of functional magnetic resonance imaging data using self‐organizing mapping with spatial connectivity , 1999, Magnetic resonance in medicine.

[19]  Ravi S. Menon,et al.  Intrinsic signal changes accompanying sensory stimulation: functional brain mapping with magnetic resonance imaging. , 1992, Proceedings of the National Academy of Sciences of the United States of America.

[20]  J Hennig,et al.  Neural network‐based analysis of MR time series , 1999, Magnetic resonance in medicine.

[21]  X Hu,et al.  Wavelet transform‐based Wiener filtering of event‐related fMRI data , 2000, Magnetic resonance in medicine.

[22]  Anthony C. Davison,et al.  Bootstrap Methods and Their Application , 1998 .

[23]  J R Moeller,et al.  A Regional Covariance Approach to the Analysis of Functional Patterns in Positron Emission Tomographic Data , 1991, Journal of cerebral blood flow and metabolism : official journal of the International Society of Cerebral Blood Flow and Metabolism.

[24]  R. Turner,et al.  Dynamic magnetic resonance imaging of human brain activity during primary sensory stimulation. , 1992, Proceedings of the National Academy of Sciences of the United States of America.

[25]  P. Boesiger,et al.  A new correlation‐based fuzzy logic clustering algorithm for FMRI , 1998, Magnetic resonance in medicine.

[26]  A. Georgopoulos,et al.  Time‐resolved fMRI of mental rotation , 1997, Neuroreport.

[27]  R Baumgartner,et al.  Assessment of cluster homogeneity in fMRI data using Kendall's coefficient of concordance. , 1999, Magnetic resonance imaging.