Advertisement

The Influence of the Normalisation of Spinal CT Images on the Significance of Textural Features in the Identification of Defects in the Spongy Tissue Structure

  • Róża DzierżakEmail author
  • Zbigniew Omiotek
  • Ewaryst Tkacz
  • Andrzej Kępa
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 925)

Abstract

The aim of the study was to determine the effect of normalisation of spinal CT images on the accuracy of automatic recognition of defects in the spongy tissue structure of the vertebrae on the thoraco-lumbar region. Feature descriptors were based on the grey-levels histogram, gradient matrix, run-length matrix, coocurrence matrix, autoregression model and wavelet transform. Six methods of feature selection were used: Fisher coefficient, minimisation of classification error probability and average correlation coefficients between chosen features, mutual information, Spearman correlation, heuristic identification of noisy variables, linear stepwise regression. Selection results were used to build 6 popular classifiers. The following values of individual classification quality factors were obtained (before normalisation/after normalisation): general accuracy of classification - 90%/82%, classification sensitivity - 89%/85%, classification specificity - 96%/82%, positive predictive value - 95%/95%, negative predictive value - 89%/84%. For the applied set of textural features, as well as the methods of selection and classification, image normalisation significantly worsened the accuracy of the automatic diagnosis of osteoporosis based on CT images of the spine. Therefore, it is necessary to use this operation with caution so as not to remove from the processed images information significant from the point of view of the purpose of the research.

Keywords

Osteoporosis CT images Image normalisation Feature selection Classification 

References

  1. 1.
    Downey, P.A., Siegel, M.I.: Bone biology and the clinical implications for osteoporosis. Phys. Ther. 86, 77–91 (2006)CrossRefGoogle Scholar
  2. 2.
    Marcus, R., Feldman, D., Dempster, D., Luckey, M., Cauley, J.: Osteoporosis, 4th edn. Academic Press (2013)Google Scholar
  3. 3.
    Reshmalakshmi, C., Sasikumar, M.: Trabecular bone quality metric from X-ray images for osteoporosis detection. In: 2017 International Conference on Intelligent Computing, Instrumentation and Control Technologies (ICICICT), pp. 1694–1697 (2017)Google Scholar
  4. 4.
    Nasser, Y., Hassouni, M., Brahim, A., Toumi, H., Lespessailles, E., Jennane, R.: Diagnosis of osteoporosis disease from bone X-ray images with stacked sparse autoencoder and SVM classifier. In: 2017 International Conference on Advanced Technologies for Signal and Image Processing (ATSIP), pp. 1–5 (2017)Google Scholar
  5. 5.
    Reshmalakshmi, C., Sasikumar, M.: Fuzzy inference system for osteoporosis detection. In: 2016 IEEE Global Humanitarian Technology Conference (GHTC), pp. 675–681 (2016)Google Scholar
  6. 6.
    Tejaswini, E., Vaishnavi, P., Sunitha, R.: Detection and prediction of osteoporosis using impulse response technique and artificial neural network. In: 2016 International Conference on Advances in Computing, Communications and Informatics (ICACCI), pp. 1571–1575 (2016)Google Scholar
  7. 7.
    Shahabaz, Somwanshi, D.K., Yadav, A.K., Roy, R.: Medical images texture analysis: a review. In: 2017 International Conference on Computer, Communications and Electronics (Comptelix), pp. 436–441 (2017)Google Scholar
  8. 8.
    Strzelecki, M., Materka, A.: Tekstura obrazów biomedycznych. Wydawnictwo Naukowe PWN (2017)Google Scholar
  9. 9.
  10. 10.
    Haralick, R.: Statistical and structural approaches to texture. Proc. IEEE 67(5), 786–804 (1979)CrossRefGoogle Scholar
  11. 11.
    Haralick, R., Shanmugam, K., Dinstein, I.: Textural features for image classification. IEEE Trans. Syst. Man Cybern. 3(6), 610–621 (1973)CrossRefGoogle Scholar
  12. 12.
    Hu, Y., Dennis, T.: Textured image segmentation by context enhanced clustering. IEE Proc.-Vis. Image Sig. Process. 141(6), 413–421 (1994)CrossRefGoogle Scholar
  13. 13.
    Lerski, R., Straughan, K., Shad, L., et al.: MR image texture analysis - an approach to tissue characterization. Magn. Reson. Imaging 11, 873–887 (1993)CrossRefGoogle Scholar
  14. 14.
    Omiotek, Z.: Improvement of the classification quality in detection of Hashimoto’s disease with a combined classifier approach. Proc. Inst. Mech. Eng. Part H: J. Eng. Med. 231(8), 774–782 (2017)CrossRefGoogle Scholar
  15. 15.
    Shurmann, J.: Pattern Classification. Wiley, Hoboken (1996)Google Scholar
  16. 16.
    Dash, M., Liu, H.: Feature selection for classification. Intell. Data Anal. 1(3), 131–156 (1997)CrossRefGoogle Scholar
  17. 17.
    Tourassi, G.D., Frederick, E.D., Markey, M.K., Floyd, C.E.: Application of the mutual information criterion for feature selection in computer-aided diagnosis. Med. Phys. 28(12), 2394–2402 (2001)CrossRefGoogle Scholar
  18. 18.
    Carmone, F.J., Kara, A., Maxwell, S.: HINoV: a new method to improve market segment definition by identifying noisy rariables. J. Mark. Res. 36, 501–509 (1999)CrossRefGoogle Scholar
  19. 19.
    Omiotek, Z., Burda, A.: Feature selection methods in image-based screening for the detection of Hashimoto’s thyroiditis in first-contact hospitals. Barometr Regionalny 14(2), 187–196 (2016)Google Scholar
  20. 20.
    Breiman, L., Friedman, J., Olshen, R., et al.: Classification and Regression Trees. CRC Press, London (1984)zbMATHGoogle Scholar
  21. 21.
    Enas, G.G., Chai, S.C.: Choice of the smoothing parameter and efficiency of the k-nearest neighbor classification. Comput. Math. Appl. 2, 235–244 (1986)CrossRefGoogle Scholar
  22. 22.
    Liao, S.H., Chu, P.H., Hsiao, P.Y.: Data mining techniques and applications - a decade review from 2000 to 2011. Expert. Syst. Appl. 39, 11303–11311 (2012)CrossRefGoogle Scholar
  23. 23.
    Quinlan, J.R.: Induction of decision trees. Mach. Learn. 1, 81–106 (1986)Google Scholar
  24. 24.
    Venables, W.N., Ripley, B.D.: Modern Applied Statistics with S-PLUS. Springer, Berlin (1998)zbMATHGoogle Scholar
  25. 25.
    Breiman, L.: Random forests. Mach. Learn. 45, 5–32 (2001)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Róża Dzierżak
    • 1
    Email author
  • Zbigniew Omiotek
    • 1
  • Ewaryst Tkacz
    • 2
  • Andrzej Kępa
    • 3
  1. 1.Faculty of Electrical Engineering and Computer ScienceLublin University of TechnologyLublinPoland
  2. 2.Faculty of Biomedical EngineeringSilesian University of TechnologyZabrzePoland
  3. 3.Department of Radiology and Nuclear MedicineIndependent Public Clinical Hospital No. 4LublinPoland

Personalised recommendations