Medical Image Analysis Using Soft Computing Techniques

  • D. Jude HemanthEmail author
  • J. Anitha
Part of the Studies in Computational Intelligence book series (SCI, volume 543)


Soft computing methodologies have gained increasing attention over the past years due to their suitability for problem solving in the processing and evaluation of medical data. The processing of medical data includes two major processes called as segmentation and classification. Image segmentation is the process in which a single image is partitioned into several groups based on similarity measures. Image classification is the process in which several images are categorized into several groups. Image segmentation techniques are normally used for volumetric analysis of abnormalities in medical images and classification techniques are used for identification of the nature of disease. In both cases, the accuracy and convergence rate of the methodologies used must be significantly positive. Hence, soft computing techniques are widely preferred for such applications. In this chapter, the application of few soft computing techniques such as Fuzzy C-Means (FCM), K-means and Support Vector Machine (SVM) for image segmentation and classification are explored. Brain image database and Retinal image database are used in these experiments. The approaches are analyzed in terms of some performance measures and found to be more suitable for medical applications.


MR images Classification Segmentation Computing 



The authors wish to thank M/s. Devaki Scan Centre for their help regarding database and validation.


  1. 1.
    D.J. Hemanth, D. Selvathi, J. Anitha, Artificial Intelligence Techniques for Medical Image Analysis, Basics, Methods, Applications (VDM Verlag, Germany, 2010)Google Scholar
  2. 2.
    D.L. Pham, C. Xu, J.L. Prince, Current methods in medical image segmentation. Annu. Rev. Biomed. Eng. 2, 315–337 (2000)CrossRefGoogle Scholar
  3. 3.
    D.J. Hemanth, C.K.S. Vijila, J. Anitha, Fuzzy based experimental verification of significance of skull tissue removal in brain tumor image segmentation. Int. J. Comput. Appl. 1, 56–61 (2010)Google Scholar
  4. 4.
    D.J. Hemanth, D. Selvathi, J. Anitha, Effective fuzzy clustering algorithm for abnormal MR brain image segmentation. Proceedings of IEEE International Advance Computing Conference, 2009, pp. 609–614Google Scholar
  5. 5.
    H.P. Ng, et al., Medical image segmentation using k-means clustering and improved watershed algorithm. Proceedings of IEEE Southwest Symposium on Image Analysis and Interpretation, 2006, pp. 61–65Google Scholar
  6. 6.
    P. Vasuda, S. Satheesh, Improved fuzzy c-means algorithm for MR brain image segmentation. Int. J. Comput. Sci. Eng. 2, 1713–1715 (2010)Google Scholar
  7. 7.
    P. Vijayalakshmi, K. Selvamani, M. Geetha, Segmentation of brain MRI using k-means clustering algorithm. Int. J. Eng. Trends Technol. 3, 113–115 (2011)Google Scholar
  8. 8.
    C. Correa et al., A comparison of fuzzy clustering algorithms applied to feature extraction on vineyard. Proceedings of International Conference in Advances in Artificial Intelligence, 2011, pp. 234–239Google Scholar
  9. 9.
    J. David, C. MacKay, Information Theory: Inference, Learning Algorithms, 4th edn. (Cambridge University Press, London, 2005)Google Scholar
  10. 10.
    M.H. Ahmad Fadzil et al., Analysis of retinal fundus images for grading of diabetic retinopathy severity. Med. Biol. Eng. Compu. 49, 693–700 (2011)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  1. 1.Department of ECEKarunya UniversityCoimbatoreIndia

Personalised recommendations