Evaluation of Statistical Features for Medical Image Retrieval

  • Cecilia Di Ruberto
  • Giuseppe Fodde
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8156)


In this paper we present a complete system allowing the classification of medical images in order to detect possible diseases present in them. The proposed method is developed in two distinct stages: calculation of descriptors and their classification. In the first stage we compute a vector of thirty-three statistical features: seven are related to statistics of the first level order, fifteen to that of second level where thirteen are calculated by means of co-occurrence matrices and two with absolute gradient; finally the last eleven are calculated using run-length matrices. In the second phase, using the descriptors already calculated, there is the actual image classification. Naive Bayes, RBF, Support VectorMachine, K-Nearest Neighbor, Random Forest and Random Tree classifiers are used. The results obtained applying the proposed system both on textured and on medical images show a very high accuracy.


texture feature extraction feature selection classification medical image analysis 


  1. 1.
    Brodatz, P.: Texture: A photographic album for Artists and Designers. Dover Pubblications (1966)Google Scholar
  2. 2.
    Julesz, B.: Textons, the Elements of Texture Perception, and Their Interactions. Nature 290, 91–97 (1981)CrossRefGoogle Scholar
  3. 3.
    Sutton, R., Hall, E.L.: Texture Measures for Automatic Classification of Pulmonary Disease. IEEE Transactions on Computers C-21, 667–676 (1972)CrossRefGoogle Scholar
  4. 4.
    Harms, H., Gunzer, U., Aus, H.M.: Combined Local Color and Texture Analysis of Stained Cells. Computer Vision, Graphics, and Image Processing 33, 364–376 (1986)CrossRefGoogle Scholar
  5. 5.
    Landeweerd, G.H., Gelsema, E.S.: The Use of Nuclear Texture Parameters in the Automatic Analysis of Leukocytes. Pattern Recognition 10, 57–61 (1978)CrossRefGoogle Scholar
  6. 6.
    Insana, M.F., Wagner, R.F., Garra, B.S., Brown, D.G., Shawker, T.H.: Analysis of Ultrasound Image Texture via Generalized Rician Statistics. Optical Engineering 25, 743–748 (1986)CrossRefGoogle Scholar
  7. 7.
    Chen, C.C., Daponte, J.S., Fox, M.D.: Fractal Feature Analysis and Classification in Medical Imaging. IEEE Transactions on Medical Imaging 8, 133–142 (1989)CrossRefGoogle Scholar
  8. 8.
    Lundervold, A.: Ultrasonic Tissue Characterization - A Pattern Recognition Approach, Technical Report. Norwegian Computing Center Oslo Norway (1992)Google Scholar
  9. 9.
    Haralick, R.M.: Statistical and Structural Approaches to Texture. IEEE Proceedings 7, 786–804 (1979)CrossRefGoogle Scholar
  10. 10.
    Hearth, M., Bowyer, K., Kopans, D., Moore, R., Kegelmeyer, W.P.: The digital database for Screening Mammography. Medical Physics Publishing, 212–218 (2001)Google Scholar
  11. 11.
    Desager, C., Geerts, S., Van der Schueren, F., Ledda, A.: Texture Analysis and Classification of Brodatz Textures using ESAC Framework. The E-Lab Masters Theses 2010–2011 (2011)Google Scholar
  12. 12.
    Puig, D., Garcia, M.: Automatic texture feature selection for image pixel classification. Pattern Recognition 39, 1996–2009 (2006)CrossRefzbMATHGoogle Scholar
  13. 13.
    Umarani, C., Ganesan, L., Radhakrishnan, S.: Combined Statistical and Structural Approach for Unsupervised Texture Classification. International Journal of Imaging Scienze and Engineering, 162–165 (2008)Google Scholar
  14. 14.
    Karoui, I., Fablet, R., Boucher, J.M., Pieczynski, W., Augustin, J.M.: Fusion of textural statistics using a similarity measure: application to texture recognition and segmentation. Pattern Analysis & Applications 11, 425–434 (2008)MathSciNetCrossRefGoogle Scholar
  15. 15.
    Chuan-Yu, C., Shih-Yu, F.: Image Classification using a Module RBF Neural Network. In: Proceedings of the First International Conference on Innovative Computing, Information and Control (2006)Google Scholar
  16. 16.
    Hee-Kooi, K., Hong-Choon, O., Ya-Ping, W.: Image Texture Classification using Combined Grey Level Co-occurrence Probabilities and Support Vector Machines. In: Proceedings of Fifth International Conference on Computer Graphics, Imaging and Visualization, pp. 180–184 (2008)Google Scholar
  17. 17.
    Lei, Q., Qingfang, Z., Shuqiang, J., Qingming, H., Wen, G.: Unsupervised texture classification: Automatically discover and classify texture patterns. Image and Vision Computing 26, 647–656 (2008)CrossRefGoogle Scholar
  18. 18.
    Sengur, A., Turkoglu, I., Ince Cevdet, M.: Wavelet packet neural networks for texture classification. Expert Systems with Applications 32, 527–533 (2007)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Cecilia Di Ruberto
    • 1
  • Giuseppe Fodde
    • 1
  1. 1.Department of Mathematics and Computer ScienceUniversity of CagliariCagliariItaly

Personalised recommendations