Application of Self-organizing Maps in Functional Magnetic Resonance Imaging

In the present work, we used Kohonen’s self-organizing map algorithm (SOM) to analyze functional magnetic resonance imaging (fMRI) data. As a first step to increase computational efficiency in data handling by the SOM algorithm, we performed an entropy analysis on the input dataset. The resulting map allowed us to define the pattern of active voxels correlated with auditory stimulation in the data matrix. The validity of the algorithm was tested using both real and simulated data.

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

[2]  G. Glover.  Deconvolution of Impulse Response in Event-Related BOLD fMRI1 , 1999, NeuroImage.

[3]  Sang Joon Kim,et al.  A Mathematical Theory of Communication , 2006 .

[4]  Karl J. Friston,et al.  Statistical parametric maps in functional imaging: A general linear approach , 1994 .

[5]  Scott J Peltier,et al.  Detecting low‐frequency functional connectivity in fMRI using a self‐organizing map (SOM) algorithm , 2003, Human brain mapping.

[6]  D. Tank,et al.  Brain magnetic resonance imaging with contrast dependent on blood oxygenation. , 1990, Proceedings of the National Academy of Sciences of the United States of America.

[7]  T. Kohonen.  Self-Organized Formation of Correct Feature Maps , 1982 .

[8]  J. Costa,et al.  Identificação de regiões cerebrais de linguagem: estudo de ressonância magnética funcional em pacientes com epilepsia refratária de lobo temporal , 2008 .

[9]  Essa Yacoub,et al.  Node merging in Kohonen's self-organizing mapping of fMRI data , 2002, Artif. Intell. Medicine.

[10]  Qin Yang,et al.  Analysis of fMRI Data Using Improved Self-Organizing Mapping and Spatio-Temporal Metric Hierarchical Clustering , 2008, IEEE Transactions on Medical Imaging.

[11]  Chung-Chih Lin,et al.  Model Free Functional MRI Analysis Using Kohonen Clustering Neural Network , 1999, IEEE Trans. Medical Imaging.

[12]  Anke Meyer-Bäse,et al.  Model-free functional MRI analysis based on unsupervised clustering , 2004 .

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

[14]  Oswaldo Baffa,et al.  Shannon entropy applied to the analysis of event-related fMRI time series , 2003, NeuroImage.

[15]  L. K. Hansen,et al.  On Clustering fMRI Time Series , 1999, NeuroImage.

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

[17]  Blind Source Separation using Independent Component Analysis , 2012 .

[18]  R. Turner,et al.  Event-Related fMRI: Characterizing Differential Responses , 1998, NeuroImage.

[19]  Karl J. Friston,et al.  Functional Connectivity: The Principal-Component Analysis of Large (PET) Data Sets , 1993, Journal of cerebral blood flow and metabolism : official journal of the International Society of Cerebral Blood Flow and Metabolism.

[20]  Teuvo Kohonen,et al.  Self-organized formation of topologically correct feature maps , 2004, Biological Cybernetics.

[21]  C. D. Coryell,et al.  The Magnetic Properties and Structure of Hemoglobin, Oxyhemoglobin and Carbonmonoxyhemoglobin , 1936, Proceedings of the National Academy of Sciences.

[22]  M J Brammer,et al.  The analysis of functional magnetic resonance images , 1997, Statistical methods in medical research.

[23]  Yul-Wan Sung,et al.  Functional magnetic resonance imaging , 2004, Scholarpedia.

[24]  G. Radda,et al.  Oxygenation dependence of the transverse relaxation time of water protons in whole blood at high field. , 1982, Biochimica et biophysica acta.

[25]  Stanley L. Sclove,et al.  Estimation and classification of fMRI hemodynamic response patterns , 2004, NeuroImage.

[26]  B. Biswal,et al.  Blind source separation of multiple signal sources of fMRI data sets using independent component analysis. , 1999, Journal of computer assisted tomography.