Systematic Construction of Texture Features for Hashimoto’s Lymphocytic Thyroiditis Recognition from Sonographic Images

  • Radim Šára
  • Daniel Smutek
  • Petr Sucharda
  • Štěpán Svačina
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2101)


The success of discrimination between normal and inflamed parenchyma of thyroid gland by means of automatic texture analysis is largely determined by selecting descriptive yet simple and independent sonographic image features.We replace the standard non-systematic process of feature selection by systematic feature construction based on the search for the separation distances among a clique of n pixels that minimise conditional entropy of class label given all data. The procedure is fairly general and does not require any assumptions about the form of the class probability density function. We show that a network of weak Bayes classifiers using 4-cliques as features and combined by majority vote achieves diagnosis recognition accuracy of 92%, as evaluated on a set of 741 B-mode sonographic images from 39 subjects. The results sug- gest the possibility to use this method in clinical diagnostic process.


Thyroid Gland Texture Feature Class Label Sampling System Conditional Entropy 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Y. Ariji et al. Texture analysis of sonographic features of the parotid gland in Sjogren’s syndrome. AJR Am J Roentgenol, 166(4):935–941, 1996.Google Scholar
  2. 2.
    D. Cavouras et al. Computer image analysis of ultrasound images for discriminating and grading liver parenchyma disease employing a hierarchical decision tree scheme and the multilayer perceptron neural network classifier. In Medical Informatics Europe’ 97, vol. 2, pp. 522–526, 1997.Google Scholar
  3. 3.
    K. Chan. Adaptation of ultrasound image texture characterization parameters. In Proceedings of the 20th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, vol. 2, pp. 804–807, 1998.CrossRefGoogle Scholar
  4. 4.
    K. Fukunaga. Introduction to Statistical Pattern Recognition. Computer Science and Scientific Computing. Academic Press, (2nd ed.), 1990.Google Scholar
  5. 5.
    R. M. Haralick and L. G. Shapiro. Computer and Robot Vision, vol. 1. Addison-Wesley, 1993.Google Scholar
  6. 6.
    T. Hirning et al. Quantification and classification of echographic findings in the thyroid gland by computerized B-mode texture analysis. Eur J Radiol, 9(4):244–247, 1989.Google Scholar
  7. 7.
    M.-H. Horng, Y.-N. Sun, and X.-Z. Lin. Texture feature coding method for classification of liver sonography. In Proceedings of 4th European Conference on Computer Vision, vol. 1, pp. 209–218, 1996.Google Scholar
  8. 8.
    G. J. Klir. Architecture of Systems Problem Solving. Plenum Press, 1985.Google Scholar
  9. 9.
    P. R. Larsen, T. F. Davies, and I. D. Hay. The thyroid gland. In Williams textbook of endocrinology. Saunders (9th ed), 1998.Google Scholar
  10. 10.
    G. Mailloux, M. Bertrand, R. Stampfler, and S. Ethier. Computer analysis of echographic textures in Hashimoto disease of the thyroid. JCU J Clin Ultrasound, 14(7):521–527, 1986.CrossRefGoogle Scholar
  11. 11.
    A. Mojsilovic, M. Popovic, and D. Sevic. Classification of the ultrasound liver images with the 2N multiplied by 1-D wavelet transform. In Proceedings of the IEEE International Conference on Image Processing, vol. 1, pp. 367–370, 1996.CrossRefGoogle Scholar
  12. 12.
    H. Morifuji. Analysis of ultrasound B-mode histogram in thyroid tumors. Journal of Japan Surgical Society, 90(2):210–21, 1989. In Japanese.Google Scholar
  13. 13.
    M. J. Muller, D. Lorenz, I. Zuna, W. J. Lorenz, and G. van Kaick. The value of computer-assisted sonographic tissue characterization in focal lesions of the thyroid. Radiologe, 29(3):132–136, 1989. In German.Google Scholar
  14. 14.
    R. Muzzolini, Y.-H. Yang, and R. Pierson. Texture characterization using robust statistics. Pattern Recognition, 27(1):119–134, 1994.CrossRefGoogle Scholar
  15. 15.
    R. Šára, M. Švec, D. Smutek, P. Sucharda, and Š. Svačina. Texture analysis of sonographic images for diffusion processes classification in thyroid gland parenchyma. In Proceedings Conference Analysis of Biomedical Signals and Images, pp. 210–212, 2000.Google Scholar
  16. 16.
    J. F. Simeone et al. High-resolution real-time sonography of the thyroid. Radiology, 145(2):431–435, 1982.Google Scholar
  17. 17.
    D. Smutek, R. Šára, M. Švec, P. Sucharda, and Š. Svačina. Chronic inflammatory processes in thyroid gland: Texture analysis of sonographic images. In Telematics in Health Care — Medical Infobahn for Europe, Proceedings of the MIE2000/GMDS2000 Congress, 2000.Google Scholar
  18. 18.
    D. Smutek, T. Tjahjadi, R. Šára, M. Švec, P. Sucharda, and Š. Svačina. Image texture analysis of sonograms in chronic inflammations of thyroid gland. Research Report CTU-CMP-2001-15, Center for Machine Perception, Czech Technical University, Prague, 2001.Google Scholar
  19. 19.
    L. Solbiati et al. The thyroid-gland with low uptake lesions — evaluation by ultrasound. Radiology, 155(1):187–191, 1985.Google Scholar
  20. 20.
    H. Sujana, S. Swarnamani, and S. Suresh. Application of artificial neural networks for the classification of liver lesions by image texture parameters. Ultrasound Med Biol, 22(9):1177–1181, 1996.CrossRefGoogle Scholar
  21. 21.
    L. Wartfsky and S. H. Ingbar. Harrison’s Principles of Internal Medicine, chapter Disease of the Thyroid, p. 1712. McGraw-Hill (12th ed), 1991.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • Radim Šára
    • 1
  • Daniel Smutek
    • 2
  • Petr Sucharda
    • 2
  • Štěpán Svačina
    • 2
  1. 1.Center for Machine PerceptionCzech Technical UniversityPragueCzech Republic
  2. 2.1st Medical FacultyCharles University PragueCzech Republic

Personalised recommendations