A quantitative comparison of functional MRI cluster analysis

The aim of this work is to compare the efficiency and power of several cluster analysis techniques on fully artificial (mathematical) and synthesized (hybrid) functional magnetic resonance imaging (fMRI) data sets. The clustering algorithms used are hierarchical, crisp (neural gas, self-organizing maps, hard competitive learning, k-means, maximin-distance, CLARA) and fuzzy (c-means, fuzzy competitive learning). To compare these methods we use two performance measures, namely the correlation coefficient and the weighted Jaccard coefficient (wJC). Both performance coefficients (PCs) clearly show that the neural gas and the k-means algorithm perform significantly better than all the other methods using our setup. For the hierarchical methods the ward linkage algorithm performs best under our simulation design. In conclusion, the neural gas method seems to be the best choice for fMRI cluster analysis, given its correct classification of activated pixels (true positives (TPs)) whilst minimizing the misclassification of inactivated pixels (false positives (FPs)), and in the stability of the results achieved.

[1]  Herbert Witte,et al.  How to Avoid Spurious Cluster Validation? A Methodological Investigation on Simulated and fMRI Data , 2002, NeuroImage.

[2]  R Baumgartner,et al.  Quantification of intensity variations in functional MR images using rotated principal components. , 1996, Physics in medicine and biology.

[3]  Robert M. Gray,et al.  An Algorithm for Vector Quantizer Design , 1980, IEEE Trans. Commun..

[4]  Michael Erb,et al.  Dynamical Cluster Analysis of Cortical fMRI Activation , 1999, NeuroImage.

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

[6]  Ravi S. Menon,et al.  Functional brain mapping by blood oxygenation level-dependent contrast magnetic resonance imaging. A comparison of signal characteristics with a biophysical model. , 1993, Biophysical journal.

[7]  E Moser,et al.  Characterization of BOLD activation in multi‐echo fMRI data using fuzzy cluster analysis and a comparison with quantitative modeling , 2001, NMR in biomedicine.

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

[9]  Ross Ihaka,et al.  Gentleman R: R: A language for data analysis and graphics , 1996 .

[10]  L. K. Hansen,et al.  Plurality and Resemblance in fMRI Data Analysis , 1999, NeuroImage.

[11]  R Baumgartner,et al.  Comparison of two exploratory data analysis methods for fMRI: fuzzy clustering vs. principal component analysis. , 2000, Magnetic resonance imaging.

[12]  R. Somorjai,et al.  The utility of fuzzy clustering in identifying diverse activations in fMRI , 1996, NeuroImage.

[13]  Kurt Hornik,et al.  A Combination Scheme for Fuzzy Clustering , 2002, AFSS.

[14]  R Baumgartner,et al.  A hierarchical clustering method for analyzing functional MR images. , 1999, Magnetic resonance imaging.

[15]  Ewald Moser,et al.  Explorative signal processing in functional MR imaging , 1999, Int. J. Imaging Syst. Technol..

[16]  Peter Boesiger,et al.  Fuzzy membership vs. probability in cross correlation based fuzzy clustering of fMRI data , 1997 .

[17]  J. Reichenbach,et al.  High-resolution, multiple gradient-echo functional MRI at 1.5 T. , 1999, Magnetic Resonance Imaging.

[18]  Peter J. Rousseeuw,et al.  Finding Groups in Data: An Introduction to Cluster Analysis , 1990 .

[19]  Kai-Hsiang Chuang,et al.  Model-free functional MRI analysis using Kohonen clustering neural network and fuzzy C-means , 1999, IEEE Transactions on Medical Imaging.

[20]  Ray L. Somorjai,et al.  Exploring regions of interest with cluster analysis (EROICA) using a spectral peak statistic for selecting and testing the significance of fMRI activation time-series , 2002, Artif. Intell. Medicine.

[21]  R. Somorjai,et al.  Activation and deactivation in functional brain images , 1996, NeuroImage.

[22]  Allen Gersho,et al.  Globally optimal vector quantizer design by stochastic relaxation , 1992, IEEE Trans. Signal Process..

[23]  Michael R. Anderberg,et al.  Cluster Analysis for Applications , 1973 .

[24]  Ray L. Somorjai,et al.  Exploratory analysis of fMRI data by fuzzy clustering: philosophy, strategy, tactics, implementation , 2003 .

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

[26]  R Baumgartner,et al.  Fuzzy clustering of gradient‐echo functional MRI in the human visual cortex. Part II: Quantification , 1997, Journal of magnetic resonance imaging : JMRI.

[27]  James C. Bezdek,et al.  Sequential Competitive Learning and the Fuzzy c-Means Clustering Algorithms , 1996, Neural Networks.

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

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

[30]  Julius T. Tou,et al.  Pattern Recognition Principles , 1974 .

[31]  Thomas Martinetz,et al.  'Neural-gas' network for vector quantization and its application to time-series prediction , 1993, IEEE Trans. Neural Networks.

[32]  N J Pizzi,et al.  EvIdent(TM): a functional magnetic resonance image analysis system , 2001, Artif. Intell. Medicine.

[33]  M Diemling,et al.  Modulation of signal changes in gradient-recalled echo functional MRI with increasing echo time correlate with model calculations. , 1997, Magnetic resonance imaging.

[34]  Ulrich Möller,et al.  Pitfalls in the Clustering of Neuroimage Data and Improvements by Global Optimization Strategies , 2001, NeuroImage.

[35]  Teuvo Kohonen,et al.  Self-organization and associative memory: 3rd edition , 1989 .

[36]  Kurt Hornik,et al.  Voting-Merging: An Ensemble Method for Clustering , 2001, ICANN.

[37]  C. Windischberger,et al.  Quantification in functional magnetic resonance imaging: fuzzy clustering vs. correlation analysis. , 1998, Magnetic resonance imaging.

[38]  Claus Lamm,et al.  Fuzzy cluster analysis of high-field functional MRI data , 2003, Artif. Intell. Medicine.

[39]  Claus Lamm,et al.  Human motor cortex activity during mental rotation , 2003, NeuroImage.

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