A Non-Parametric Approach for the Activation Detection of Block Design fMRI Simulated Data Using Self-Organizing Maps and Support Vector Machine

Sheyda Bahrami, Mousa Shamsi



Functional magnetic resonance imaging (fMRI) is a popular method to probe the functional organizationof the brain using hemodynamic responses. In this method, volume images of the entire brain areobtained with a very good spatial resolution and low temporal resolution. However, they always sufferfrom high dimensionality in the face of classification algorithms. In this work, we combine a supportvector machine (SVM) with a self-organizing map (SOM) for having a feature-based classification byusing SVM. Then, a linear kernel SVM is used for detecting the active areas. Here, we use SOM forfeature extracting and labeling the datasets. SOM has two major advances: (i) it reduces dimension ofdata sets for having less computational complexity and (ii) it is useful for identifying brain regions withsmall onset differences in hemodynamic responses. Our non-parametric model is compared withparametric and non-parametric methods. We use simulated fMRI data sets and block design inputsin this paper and consider the contrast to noise ratio (CNR) value equal to 0.6 for simulated datasets.fMRI simulated dataset has contrast 1–4% in active areas. The accuracy of our proposed method is93.63% and the error rate is 6.37%.


classification; FMRI; non-parametric methods; self-organizing map (SOM); support vector machine (SVM)

Full Text:



Friston KJ, Jezzard P, Turner R. Analysis of functional MRI timeseries. Hum Brain Map 1994;1:153-71.

Clare S. Functional MRI: Methods and Applications. University of Nottingham; 1997. p. 155.

Cohen MS. Parametric analysis of fMRI data using linear systems methods. Neuroimage 1997;6:93-103.

Fadili MJ, Ruan S, Bloyet D, Mazoyer B. Unsupervised fuzzy clustering analysis of fMRI series. Engineering in Medicine and Biology Society, 1998. Proceedings of the 20th Annual International Conference of the IEEE, vol. 2, 1998. p. 696-9.

Sekihara K, Koizumi H. Detecting cortical activities from fMRI time course data using the music algorithm with forward and backward covariance averaging. Magn Reson Med 1996;35:807-13.

Descombes X, Kruggel F, Von Cramon DY. Spatio-temporal fMRI analysis using Markov random fields. IEEE Trans Med Imaging 1998;17:1028-39.

Worsley KJ, Cao J, Paus T, Petrides M, Evans AC. Applications of random field theory to functional connectivity. Hum Brain Map 1998;6:364-7.

Ardekani BA, Kershaw J, Kashikura K, Kanno I. Activation detection in functional MRI using subspace modeling and maximum likelihood estimation. IEEE Trans Med Imaging 1999;18:101-14.

Ruttimann UE, Unser M, Rawlings RR, Rio D, Ramsey NF, Mattay VS, et al. Statistical analysis of functional MRI data in the wavelet domain. IEEE Trans Med Imaging 1998;17:142-54.

Unser M, Aldroubi A. A review of wavelets in biomedical applications. Proc IEEE 1996;84:626-38.

Poline JB, Mazoyer BM. Analysis of individual brain activation maps using hierarchical description and multiscale detection. IEEE Trans Med Imaging 1994;13:702-10.

Ardekani BA, Kanno I. Statistical methods for detecting activated regions in functional MRI of the brain. Magn Reson Imaging 1998;16:1217-25.

Friman O, Cedefamn J, Lundberg P, Borga M, Knutsson H. Detection of neural activity in functional MRI using canonical correlation analysis. Magn Reson Med 2001;45:323-30.

Ardekani BA, Choi SJ, Hossein-Zadeh GA, Porjesz B, Tanabe JL, Lim KO, et al. Functional magnetic resonance imaging of brain activity in the visual oddball task. Cogn Brain Res 2002;14:347-56.

Monti MM. Statistical analysis of fMRI time-series: A critical review of the GLM approach. Front Hum Neurosci 2011;5.

Afshin-Pour B, Hossein-Zadeh GA, Strother SC, Soltanian-Zadeh H. Enhancing reproducibility of fMRI statistical maps using generalized canonical correlation analysis in NPAIRS framework. Neuroimage 2012;60:1970-81.

Hossein-Zadeh GA, Soltanian-Zadeh H, Ardekani BA. Multiresolution fMRI activation detection using translation invariant wavelet transform and statistical analysis based on resampling. IEEE Trans Med Imaging 2003;22:302-14.

Xie SY, Guo R, Li NF, Wang G, Zhao HT. Brain fMRI processing and classification based on combination of PCA and SVM. 2009 International Joint Conference on Neural Networks, June 14, 2009. p. 3384-9.

Cox DD, Savoy RL. Functional magnetic resonance imaging (fMRI) “brain reading”: Detecting and classifying distributed patterns of fMRI activity in human visual cortex. Neuroimage 2003;19:261-70.

Liang L, Cherkassky V, Rottenberg DA. Spatial SVM for feature selection and fMRI activation detection. The 2006 IEEE International Joint Conference on Neural Network Proceedings, July 16, 2006. p. 1463-9.

Fan Y, Shen D, Davatzikos C. Detecting cognitive states from fMRI images by machine learning and multivariate classification. 2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW’06), June 17, 2006. p. 89.

Jain AK, Duin RP, Mao J. Statistical pattern recognition: A review. IEEE Trans Pattern Anal Mach Intell 2000;22:4-37.

Calhoun VD, Adali T, Pearlson GD, Pekar JJ. Spatial and temporal independent component analysis of functional MRI data containing a pair of task-related waveforms. Hum Brain Map 2001;13:43-53.

Chen H, Yao D. Discussion on the choice of separated components in fMRI data analysis by spatial independent component analysis. Magn Reson Imaging 2004;22:827-33.

Kohonen T. The self-organizing map. Proc IEEE 1990;78: 1464-80.

Kohonen T, Simula O. Engineering applications of the selforganizing map. Proc IEEE 1996;84:1358-84.

Liao W, Chen H, Yang Q, Lei X. Analysis of fMRI data using improved self-organizing mapping and spatio-temporal metric hierarchical clustering. IEEE Trans Med Imaging 2008;27: 1472-83.

Huang TM, Kecman V, Kopriva I. Kernel Based Algorithms for Mining Huge Data Sets. Heidelberg: Springer; 2006.

Kecman V. Learning and Soft Computing: Support Vector Machines, Neural Networks, and Fuzzy Logic Models. MIT Press; 2001.

Afshinpour B, Hossein-ZadehGA, Soltanian-Zadeh H. Nonparametric trend estimation in the presence of fractal noise: Application to fMRI time-series analysis. J Neurosci Methods 2008;171:340-8.

Welvaert M, Rosseel Y. On the definition of signal-to-noise ratio and contrast-to-noise ratio for fMRI data. PLoS One 2013;8:1-10.

Vijay K, Selvakumar K. Brain fMRI clustering using interaction K-means algorithm with PCA. International Conference on Communications and Signal Processing (ICCSP), April, 2015. p. 0909-13.

Toor AK, Singh A. Analysis of clustering algorithm based on number of clusters, error rate, computation time and map topology on large data set. Int J Emerg Trends Technol Comput Sci 2013;2:94-8.

Bandettini PA, Jesmanowicz A, Wong EC, Hyde JS. Processing strategies for time-course data sets in functional MRI of the human brain. Magn Reson Med 1993;30:161-73.

Ardekani BA, Kanno I. Statistical methods for detecting activated regions in functional MRI of the brain. Magn Reson Imaging 1998;16:1217-25.


  • There are currently no refbacks.