Brain tumor severity analysis using modified multi‐texton histogram and hybrid kernel SVM

A. Jayachandran; R. Dhanasekaran

doi:10.1002/ima.22081

journal article Feb 10, 2014

Brain tumor severity analysis using modified multi‐texton histogram and hybrid kernel SVM

A. Jayachandran R. Dhanasekaran

International Journal of Imaging Systems and Technology Vol. 24 No. 1 pp. 72-82 · Wiley

View at Publisher Save 10.1002/ima.22081

Abstract

ABSTRACTMagnetic resonance image (MRI) segmentation refers to a process of assigning labels to set of pixels or multiple regions. It plays a major role in the field of biomedical applications as it is widely used by the radiologists to segment the medical images input into meaningful regions. In recent years, various brain tumor detection techniques are presented in the literature. In this article, we have developed an approach to brain tumor detection and severity analysis is done using the various measures. The proposed approach comprises of preprocessing, segmentation, feature extraction, and classification. In preprocessing steps, we need to perform skull stripping and then, anisotropic filtering is applied to make image suitable for extracting features. In feature extraction, we have modified the multi‐texton histogram (MTH) technique to improve the feature extraction. In the classification stage, the hybrid kernel is designed and applied to training of support vector machine to perform automatic detection of tumor region in MRI images. For comparison analysis, our proposed approach is compared with the existing works usingK‐cross fold validation method. From the results, we can conclude that the modified multi‐texton histogram with non‐linear kernels has shown the accuracy of 86% but the MTH with non‐linear kernels shows the accuracy of 83.8%.

Topics

No keywords indexed for this article. Browse by subject →

References

32

[1]

F.Admasua S.A.Zubia K.Toenniesa N.Bodammerb andH.Hinrichsb Segmentation of multiple sclerosis lesions from MR brain images using the principles of fuzzy‐connectedness and artificial neuron networks Proceedings of International Conference on Image Processing Barcelona Spain Vol. 3 2003. 10.1109/icip.2003.1246873

[2]

10.1109/titb.2011.2104376

[3]

10.1109/tmi.2012.2219589

[4]

Bauer S. "Fully automatic segmentation of brain tumor images using support vector machine classification in combination with hierarchical conditional random field regularization" MICCAI, (2011)

[5]

Boswell D. "Introduction to support vector machines" Proc World Acad Sci Eng Technol (2002)

[6]

10.1109/tsmcb.2011.2124455

[7]

Fan R.E. "LIBLINEAR: A library for large linear classification" J Mach Learn Res (2008)

[8]

10.1016/j.mri.2008.05.017

[9]

Gladis V.P. "A novel approach for feature extraction and selection on MRI images for brain tumor classification" Int Conf Comput Sci Inf Technol (2012)

[10]

Hahn H.K. "The skull stripping problem in MRI solved by a single 3D watershed transform, Lecture notes in computer science" Medical image computing and computer‐assisted intervention (MICCAI)

[11]

Hussain S.J. "Segmentation of tissues in brain MRI images using dynamic neuro‐fuzzy technique" Int J Soft Comput Eng (2012)

[12]

10.1109/tbme.2013.2271383

[13]

Joachims T. (2002)

[14]

Joshi J. "Feature extraction and texture classification in MRI" Proc Int Conf Comput Technol (2010)

[15]

Texture Analysis: A Review of Neurologic MR Imaging Applications

A. Käßner, R.E. Thornhill

American Journal of Neuroradiology 10.3174/ajnr.a2061

[16]

10.1109/icceet.2012.6203809

[17]

10.1109/tbme.2011.2181167

[18]

Khalifa I. "MRI brain image segmentation based on wavelet and FCM algorithm" Int J Comput Appl (2012)

[19]

10.1016/j.fss.2008.11.016

[20]

10.1109/tbme.2013.2267212

[21]

10.1016/j.patcog.2010.02.012

[22]

R.Mishra MRI based brain tumor detection using wavelet packet feature and artificial neural networks Proceedings of the International Conference and Workshop on Emerging Trends in Technology Mumbai India February 26–27 2010. 10.1145/1741906.1742054

[23]

10.1109/tmi.2012.2230403

[24]

Pradhan N. "Development of a composite feature vector for the detection of pathological and healthy tissues in FLAIR MR images of brain" J ICGST‐BIME (2010)

[25]

Roy S. "Detection and quantification of brain tumor from MRI of brain and it's symmetric analysis" Int J Inf Commun Technol Res (2012)

[26]

10.1109/titb.2005.847500

[27]

10.1109/tmi.2013.2263388

[28]

N.K.Subbanna M.Shah S.J.Francis S.Narayanan D.L.Collins D.L.Arnold andT.Arbel MS lesion segmentation using Markov random fields Proceedings of International Conference on Medical Image Computing and Computer Assisted Intervention London UK September2009.

[29]

Umamaheswari J. "A hybrid approach for DICOM image segmentation using fuzzy techniques" Int J Fuzzy Logic Syst (2012)

[30]

10.1109/tmi.2011.2173766

[31]

S.N.WeissandI.Kapouleas An empirical comparison of pattern recognition neural nets and machine learning classification methods Proceedings of the 11th International Joint Conference on Artificial Intelligence Vol.234–237 1989.

[32]

W.Zhu N.Zeng andN.Wang Sensitivity specificity accuracy associated confidence interval and ROC analysis with practical SAS implementations Proceedings of the SAS Conference Baltimore MD 2010 pp.9.

Metrics

16

Citations

32

References

Details

Published: Feb 10, 2014
Vol/Issue: 24(1)
Pages: 72-82
License: View

Authors

A

A. Jayachandran

PSN College of Engineering and Technology Tirunelveli Tamil Nadu India

R

R. Dhanasekaran

Syed Ammal Engineering College Ramanathapuram Tamil Nadu India

Cite This Article

A. Jayachandran, R. Dhanasekaran (2014). Brain tumor severity analysis using modified multi‐texton histogram and hybrid kernel SVM. International Journal of Imaging Systems and Technology, 24(1), 72-82. https://doi.org/10.1002/ima.22081

Brain tumor severity analysis using modified multi‐texton histogram and hybrid kernel SVM

You May Also Like