Abstract

This study presents a neural network based technique for automatic classification of Magnetic Resonance Images (MRI) of the brain in two categories of benign and malignant. The proposed method consists the following stages; i.e., preprocessing, tumor region segmentation, feature extraction using DWT and classification using ANFIS classifier. Preprocessing involves removing low-frequency surrounding noise, normalizing the intensity of the individual particle images. In the second stage, the fuzzy Connectedness segmentation is used for partitioning the image into meaningful regions. In feature extraction, the obtained feature connected to MRI images using the Discrete Wavelet Transform (DWT). In the classification stage, ANFIS Classifier is used to classify the subjects to normal or abnormal (benign, malignant). The proposed technique gives high-quality results for brain tissue detection and is more robust and efficient compared with other recent works.

Keywords:

ANFIS , classification , Discrete Wavelet Transform (DWT), fuzzy connectedness segmentation,

References

1. Ashby, L.S., M.M. Troester and W.R. Shapiro, 2006. Central nervous system tumors. Cancer Ther., 1: 475-513.
   CrossRef    
2. Chaplot, S., L.M. Patnaik and N.R. Jagannathan, 2006. Classification of magnetic resonance brain images using wavelets as input to support vector machine and neural network. Biomed. Signal Proces., 1: 86-92.
   CrossRef    
3. Doolittle, N.D., 2004. State of the science in brain tumor classification. Semin. Oncol. Nurs., 20: 224-230.
   CrossRef    
4. Gerig, G., O. Kubler, R. Kikinis and F.A. Jolesz, 1992. Nonlinear anisotropic filtering of MRI data. IEEE T. Med. Imaging, 1(2): 221-232.
   CrossRef    PMid:18218376    
5. Hiremath, P.S., S. Shivashankar and J. Pujari, 2006. Wavelet based features for color texture classification with application to CBIR. Int. J. Comput. Sci. Network Sec., 6(9A): 124-133.
   
6. Jaya, J., K. Thanushkodi and M. Karnan, 2009. Tracking algorithm for denoising of MR brain images. IJCSNS Int. J. Comput. Sci. Netw. Secur. 9(11): 262-267.
   
7. Jayachandran, A. and R. Dhanasekaran, 2013a. Automatic detection of brain tumor in magnetic resonance images using multi-texton histogram and support vector machine. Int. J. Imag. Syst. Tech., 23: 97-103.
   CrossRef    
8. Jayachandran, A. and R. Dhanasekaran, 2013b. Brain tumor detection using fuzzy support vector machine classification based on a texton co-occurrence matrix. J. Imaging Sci. Techn., 57(1): 10507-1-10507-7(7).
   
9. Lashkari, A., 2010. A neural network based method for brain abnormality detection in MR images using gabor wavelets. Int. J. Comput. Appl., 4(7): 9-13.
   CrossRef    
10. Lukas, L., A. Devos, J.A. Suykens, L. Vanhamme, F.A. Howe, C. Majo’s, A. Moreno-Torres, M. Van Der Graaf, A.R. Tate, C. Aru’s and S. Van Huffel, 2004. Brain tumor classification based on long echo proton MRS signals. Artif. Intell. Med., 31(1): 73-89.
    CrossRef    PMid:15182848    
11. Mallat, S.G., 1980. A theory of multiresolution signal decomposition: The wavelet representation. IEEE T. Pattern Anal., 11(7): 674-693.
    CrossRef    
12. Schmidt, M., I. Levner, R. Greiner, A. Murtha and A. Bistritz, 2005. Segmenting brain tumors using alignment-based features. Proceeding of 4th International Conference on Machine Learning and Applications, Los Angeles.
    CrossRef    
13. Sengur, A., 2008. An expert system based on principal component analysis, artificial immune system and fuzzy k-NN for diagnosis of valvular heart diseases. Comput. Biol. Med., 51(3): 329-338.
    CrossRef    PMid:18177849    
14. Silipo, R., G. Deco and H. Bartsch, 1999. Brain tumor classification based on EEG hidden dynamics. Intell. Data Anal., 3(4): 287-306.
    CrossRef    
15. Subasi, A., 2007. Application of adaptive neuro-fuzzy inference system for epileptic seizure detection using wavelet feature extraction. Comput. Biol. Med., 37: 227-244.
    CrossRef    PMid:16480706    
16. Zhu, W., N. Zeng and N. Wang, 2010. Sensitivity, specificity, accuracy, associated confidence interval and ROC analysis with practical SAS® implementations. Proceeding of NESUG: Health Care and Life Sciences. Baltimore, Maryland, pp: 1-9.
    

Competing interests

The authors have no competing interests.

Open Access Policy

This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.

Copyright

The authors have no competing interests.