A Novel Machine Learning Approach for Detecting the Brain Abnormalities from MRI Structural Images

  • Lavneet Singh
  • Girija Chetty
  • Dharmendra Sharma
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7632)

Abstract

In this study, we present the investigations being pursued in our research laboratory on magnetic resonance images (MRI) of various states of brain by extracting the most significant features, and to classify them into normal and abnormal brain images. We propose a novel method based ondeep and extreme machine learning on wavelet transform to initially decompose the images, and then use various features selection and search algorithms to extract the most significant features of brain from the MRI images. By using a comparative study with different classifiers to detect the abnormality of brain images from publicly available neuro-imaging dataset, we found that a principled approach involving wavelet based feature extraction, followed by selection of most significant features using PCA technique, and the classification using deep and extreme machine learning based classifiers results in a significant improvement in accuracy and faster training and testing time as compared to previously reported studies.

Keywords

Deep Machine Learning Extreme Machine Learning MRI PCA 

References

  1. 1.
    Fletcher-Heath, L.M., Hall, L.O., Goldgof, D.B., Murtagh, F.R.: Automatic segmentation of non-enhancing brain tumors in magnetic resonance images. Artificial Intelligencein Medicine 21, 43–63 (2001)CrossRefGoogle Scholar
  2. 2.
    Chaplot, S., Patnaik, L.M., Jagannathan, N.R.: Classification of magnetic resonance brain images using wavelets as input to support vector machine and neuralnetwork. Biomedical Signal Processing and Control 1, 86–92 (2006)CrossRefGoogle Scholar
  3. 3.
    Gorunescu, F.: Data Mining Techniques in Computer-Aided Diagnosis: Non-InvasiveCancer Detection. PWASET 25, 427–430 (2007) ISSN 1307-6884Google Scholar
  4. 4.
    Kara, S., Dirgenali, F.: A system to diagnose atherosclerosis via wavelet transforms,principal component analysis and artificial neural networks. Expert Systems with Applications 32, 632–640 (2007)CrossRefGoogle Scholar
  5. 5.
    Maitra, M., Chatterjee, A.: Hybrid multi-resolutionSlantlet transform and fuzzy c-means clustering approach for normal-pathological brain MR image segregation. Med. Eng. Phys. (2007), doi:10.1016/j.medengphy.2007.06.009Google Scholar
  6. 6.
    Abdolmaleki, P., Mihara, F., Masuda, K., DansoBuadu, L.: Neural networks analysis of astrocyticgliomas from MRI appearances. Cancer Letters 118, 69–78 (1997)CrossRefGoogle Scholar
  7. 7.
    Rosenbaum, T., Engelbrecht, V., Krolls, W., van Dorstenc, F.A., Hoehn-Berlagec, M., Lenard, H.: MRI abnormalities in neuro-bromatosistype 1 (NF1): a study of men and mice. Brain & Development 21, 268–273 (1999)CrossRefGoogle Scholar
  8. 8.
    Cocosco, C., Zijdenbos, A.P., Evans, A.C.: A fully automatic and robust brainMRI tissue classification method. Medical Image Analysis 7, 513–527 (2003)CrossRefGoogle Scholar
  9. 9.
    Database taken from, http://med.harvard.edu/AANLIB/
  10. 10.
    Hintonand, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504–507 (2006)MathSciNetCrossRefGoogle Scholar
  11. 11.
    Hinton, G.E., Osindero, S.: A fast learning algorithm for deep belief nets. Neural Computation 18, 1527–1554 (2006)MathSciNetCrossRefMATHGoogle Scholar
  12. 12.
    Lin, M.-B., Huang, G.-B., Saratchandran, P., Sudararajan, N.: Fully complex extreme learning machine. Neurocomputing 68, 306–314 (2005)CrossRefGoogle Scholar
  13. 13.
    Huang, G.-B., Zhu, Q.-Y., Siew, C.K.: Extreme Learning Machine: Theory and Applications. Neurocomputing 70, 489–501 (2006)CrossRefGoogle Scholar
  14. 14.
    Serre, D.: Matrices: Theory and Applications. Springer Verlag, New York Inc. (2002)Google Scholar
  15. 15.
    Mishra, A., Singh, L., Chetty, G.: A Novel Image Water Marking Scheme Using Extreme Learning Machine. In: Proceedings of IEEE World Congress on Computational Intelligence (WCCI 2012). IEEE Explore, Brisbane (2012)Google Scholar
  16. 16.
    Singh, L., Chetty, G., Sharma, D.: A Hybrid Approach to Increase the Performance of Protein Folding Recognition Using Support Vector Machines. In: Perner, P. (ed.) MLDM 2012. LNCS, vol. 7376, pp. 660–668. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  17. 17.
    Singh, L., Chetty, G.: Review of Classification of Brain Abnormalities in Magnetic Resonance Images Using Pattern Recognition and Machine Learning. In: Proceedings of International Conference of Neuro Computing and Evolving Intelligence, NCEI 2012, Auckland, New-Zealand. LNCS Bioinformatics, Springer (2012)Google Scholar
  18. 18.
    Singh, L., Chetty, G.: A Novel Approach for protein Structure prediction Using Pattern Recognition and Extreme Machine Learning. In: Proceedings of International Conference of Neuro Computing and Evolving Intelligence, NCEI 2012, Auckland, New-Zealand. LNCS Bioinformatics. Springer (2012)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Lavneet Singh
    • 1
  • Girija Chetty
    • 1
  • Dharmendra Sharma
    • 1
  1. 1.Faculty of Information Sciences and EngineeringUniversity of CanberraAustralia

Personalised recommendations