A Serial Hierarchical Support Vector Machine and 2D Feature Sets Act for Brain DTI Segmentation

Authors: Mohammad Javadi

Abstract:

Serial hierarchical support vector machine (SHSVM) is proposed to discriminate three brain tissues which are white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF). SHSVM has novel classification approach by repeating the hierarchical classification on data set iteratively. It used Radial Basis Function (rbf) Kernel with different tuning to obtain accurate results. Also as the second approach, segmentation performed with DAGSVM method. In this article eight univariate features from the raw DTI data are extracted and all the possible 2D feature sets are examined within the segmentation process. SHSVM succeed to obtain DSI values higher than 0.95 accuracy for all the three tissues, which are higher than DAGSVM results.

Keywords: Brain segmentation, DTI, hierarchical, SVM.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1087155

References:

[1] E.D. Angelini, T. Song, B.D. Mensh, and A.F. Laine, “Brain MRI segmentation with multiphase minimal partitioning: A comparative study,” Int. Journal of Biomedical Imaging, vol. 2007, pp. 1–15.
[2] G. Heckenberg, Y. Xi, Y. Duan, and J. Hua, ”Brain structure segmentation from MRI by geometric surface flow,” International Journal of Biomedical Imaging, vol. 2006, pp. 1–6, 2006.
[3] O. Commowick, S.K. Warfield, “A continuous STAPLE for scalar, vector, and tensor images: An application to DTI analysis,” IEEE Transactions on Medical Imaging, vol. 28 , pp. 838–846, 2009.
[4] C. Lenglet, M. Rousson, and R. Deriche, "DTI segmentation by statistical surface evolution", IEEE Trans. on Medical Imaging, vol. 25, pp. 685–700, 2006
[5] I. Steinwart, A. Christmann, “Support Vector Machines (Book style),” Springer, LA, USA, 2008, pp. 112-116.
[6] Y. Washizawa, “Feature extraction using constrained approximation and suppression,” IEEE Trans. on Neural Networks, vol. 21, pp. 201–210, 2010.
[7] S. Knerr, L. Personnaz, and G. Dreyfus, “Single-layer learning revisited: A stepwise procedure for building and training a neural network,” in Neurocomputing: Algorithms, Architectures and Applications, J. Fogelman, Ed. New York: Springer-Verlag, 1990.
[8] J. Friedman. Another approach to polychotomous classification. Dept. Statist., Stanford Univ., Stanford, CA, 1996. (Online). Available: http://www-stat.stanford.edu/reports/friedman/poly.ps.Z
[9] J. C. Platt, N. Cristianini, and J. Shawe-Taylor, “Large margin DAG’s for multiclass classification,” in Advances in Neural Information Processing Systems. Cambridge, MA: MIT Press, 2000, vol. 12, pp. 547–553.
[10] S. Miri, N. Passat, and J.P. Armspach, “Topology-preserving discrete deformable model: Application to multi-segmentation of brain MRI,“ In Image and Signal Processing, pp. 67-75, Springer, 2008.
[11] C. Pierpaoli and P. J. Basser, "Toward a quantitative assessment of diffusion anisotropy," Magnetic Resonance in Medicine, vol. 36, pp. 893–906, 1996.
[12] P.J. Basser, J. Mattiello, and D. Lebihan, “MR diffusion tensor spectroscopy and imaging,” Biophysical Journal, vol. 66, pp. 259-267, 1994.
[13] A.L. Alexander, K. Hasan, G. Kindlmann, D.L. Parker, and J.S. Tsuruda, “A Geometric Analysis of Diffusion Tensor Measurements of The Human Brain,” Magnetic Resonance in Medicine, vol. 44, pp. 283– 291, 2000.
[14] L. Rittner and R. Lotufo, "Diffusion tensor imaging segmentation by watershed transform on tensorial morphological gradient," in Computer Graphics and Image Processing, 2008. SIBGRAPI'08. XXI Brazilian Symposium on, pp. 196–203, 2008.
[15] E.M. Akkerman, “Efficient measurement and calculation of MR diffusion anisotropy images using the platonic variance method,” Magnetic Resonance in Medicine, vol. 49, pp. 599–604, 2003.
[16] M. Javadi, Brain tissue segmentation using DTI data, Dept. Chalmers University of Technology, EX007, 2013. (Online). Available: http://publications.lib.chalmers.se/records/fulltext/176182/176182.pdf
[17] V. Vapnik, “Statistical learning theory,” John Wiley and Sons, Inc., NY, USA, 1998.
[18] Long Han, Mark J. Embrechts, Boleslaw Szymanski, “Sigma Tuning of Gaussian Kernels: Detection of Ischemia from Magnetocardiograms,” IGI Global 2011, pp. 206–223.