Automatic Classification of Brain MRI Images Using SVM and Neural Network Classifiers

Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 320)


Computer Aided Diagnosis (CAD) is a technique where diagnosis is performed in an automatic way. This work has developed a CAD system for automatically classifying the given brain Magnetic Resonance Imaging (MRI) image into ‘tumor affected’ or ‘tumor not affected’. The input image is preprocessed using wiener filter and Contrast Limited Adaptive Histogram Equalization (CLAHE). The image is then quantized and aggregated to get a reduced image data. The reduced image is then segmented into four regions such as gray matter, white matter, cerebrospinal fluid and high intensity tumor cluster using Fuzzy C Means (FCM) algorithm. The tumor region is then extracted using the intensity metric. A contour is evolved over the identified tumor region using Active Contour model (ACM) to extract exact tumor segment. Thirty five features including Gray Level Co-occurrence Matrix (GLCM) features, Gray Level Run Length Matrix features (GLRL), statistical features and shape based features are extracted from the tumor region. Neural network and Support Vector Machine (SVM) classifiers are trained using these features. Results indicate that Support vector machine classifier with quadratic kernel function performs better than Radial Basis Function (RBF) kernel function and neural network classifier with fifty hidden nodes performs better than twenty five hidden nodes. It is also evident from the result that average running time of FCM is less when used on reduced image data.


Computer aided diagnosis (CAD) Fuzzy C Means (FCM) Active Contour model (ACM) feature extraction Neural network Support vector machine (SVM) Magnetic Resonance Imaging (MRI) 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Ibrahim, W.H., Osman, A.A.A., Mohamed, Y.I.: MRI Brain Image Classification using neural networks. In: International Conference on Computing, Electrical and Electronics Engineering, pp. 253–258 (2013)Google Scholar
  2. 2.
    Akram, F., Kim, J.H., Choi, K.N.: Active contour method with locally computed signed pressure force function: An application to brain MR image segmentation. In: Seventh International Conference on Image and Graphics, pp. 154–159 (2013)Google Scholar
  3. 3.
    Gebejes, A., Huertas, R.: Texture characterization based on GLCM. In: Conference on Informatics and Management Sciences (2013)Google Scholar
  4. 4.
    Badmera, M.S., Nilawar, A.P., Karawankar, A.R.: Modified FCM approach for Brain MR Image segmentation. In: International Conference on Circuits, Power and Computing Technologies, pp. 891–896 (2013)Google Scholar
  5. 5.
    Sridhar, M.K.: Brain Tumor classification using Discrete Cosine transform and Probabilistic neural network. In: International Conference on Signal Processing Image Processing & Pattern Recognition (ICSIPR), pp. 92–96 (2013)Google Scholar
  6. 6.
    Gladis Pushparathi, V.P., Palani, S.: Brain tumor MRI image classification with feature selection and extraction using Linear Discriminant analysis. Computer Vision and Pattern Recognition (2012)Google Scholar
  7. 7.
    Kavitha, A.R., Chellamuthu, C., Rupa, K.: An efficient approach for brain tumor detection based on modified region growing and Neural Network in MRI images. In: International Conference on Computing, Electronics, Electrical Technologies, pp. 1087–1095 (2012)Google Scholar
  8. 8.
    Shasidhar, M., Raja, V.S., Kumar, B.V.: Mri brain image segmentation using modified fuzzy c means clustering. In: International Conference on Communication and Network Technologies, pp. 473–478 (2011)Google Scholar
  9. 9.
    Abdullah, N., Ngah, U.K., Aziz, S.A.: Image classification of brain MRI using support vector machine. In: International conference on Imaging Systems and Techniques, pp. 242–247 (2011)Google Scholar
  10. 10.
    Qurat-Ul-ain, Latif, G., Kazmi, S.B., Jaffer, M.A., Mirza, A.M.: Classification and segmentation of Brain tumor using texture analysis. In: International Conference on Artificial Intelligence, Knowledge Engineering and Data bases, pp. 147–155 (2010)Google Scholar
  11. 11.
    Wang, L., Hi, L., Mishra, A., Li, C.: Active contour model driven by Local Gaussian Distribution Fitting Energy. Signal Processing, 2435–2447 (2009)Google Scholar
  12. 12.
    Ubeyeli, E.D., Goeler, I.: Feature extraction from Doppler ultrasound signals for automated diagnostic system. Computers in Biology and Medicine 7, 678–684 (2007)Google Scholar
  13. 13.
    Albergtsen, F.: Statistical Feature measures computed from gray level co-occurrence matrices. International Journal on Computer Applications (2005)Google Scholar
  14. 14.
    Huixu, D., Kurani, A.S., Furst, J.D., Raicu, D.S.: Run length encoding for volumetric texture. In: International Conference on Visualization, Imaging and Image Processing (2004)Google Scholar
  15. 15.
    Troy, E.B., Deutch, E.S., Rosen Feld, A.: Gray level manipulation experiments for texture analysis. IEEE Transactions on System, Man, Cybernetics smc-3, 91–98 (1973)CrossRefGoogle Scholar
  16. 16.
  17. 17.
  18. 18.
  19. 19.
  20. 20.
  21. 21.
  22. 22.

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.Department of Computer Science and Engineering, College of Engineering GuindyAnna UniversityChennaiIndia

Personalised recommendations