Analysis of Sonogram Images of Thyroid Gland Based on Wavelet Transform

Sonogram images of normal and lymphocyte thyroid tissues have considerable overlap which makes it difficult to interpret and distinguish. Classification from sonogram images of thyroid gland is tackled in semiautomatic way. While making manual diagnosis from images, some relevant information need not to be recognized by human visual system. Quantitative image analysis could be helpful to manual diagnostic process so far done by physician. Two classes are considered: normal tissue and chronic lymphocyte thyroid (Hashimoto's Thyroid). Data structure is analyzed using K-nearest-neighbors classification. This paper is mentioned that unlike the wavelet sub bands' energy, histograms and Haralick features are not appropriate to distinguish between normal tissue and Hashimoto's thyroid.

Authors:

• M. Bastanfard
• B. Jalaeian
• S. Jafari

Keywords:

• Sonogram
• thyroid
• Haralick feature
• wavelet.

References:

[1] C. M. Bishop. Neural Networks for Pattern Recognition. Clarendon
Press, 1995.
[2] E. A. Toufik. Automatic classification of the thyroid gland diseases by a
histogram. Master-s thesis, Faculty of Electrical Engineering, Czech
Technical University, Prague, Czech Republic, Jan 2001.
[3] M. Svec and R. Sara. Analyza textury sonografick'ych obraz┬░u
dif'uzn'ıch process °u parenchymu ˇst'ıtn'e ˇzl'azy. Research Report
CTU-CMP-1999-12, Center for Machine Perception, FEE CTU in
Prague, Dec 1999.
[4] Mallat, S. G. A Theory for multi resolution signal decomposition: The
Wavelet representation. IEEE Transactions on Pattern Analysis and
Machine Intelligence, Vol. 11, No. 7 1989, pp. 674-693.
[5] R. Sara, D. Smutek, P. Sucharda, and S. Svacina. Systematic
construction of texture features for Hashimoto-s lymphocytic thyroiditis
recognition from sonographic images. In S. Quaglini, P. Barahona, and
S. Andreassen, editors, Artificial Intelligence in Medicine, LNCS,
Berlin-Heidelberg, Germany, 2001.
[6] R. Sara, M. Svec, D. Smutek, P. Sucharda, and S. Svacina. Diffusion
process classification in thyroid gland parenchyma based on texture
analysis of sonographic images: Preliminary results. In Svoboda T.,
editor, Proceedings of the Czech Pattern Recognition Workshop 2000.
Czech Pattern Recognition Society Praha, Feb 2000, pp 45-47.
[7] R. Sara. Sonograph images: Texture analysis [online]. C 1998, last
revision 9th of November 2000.
http://cmp.felk.cvut.cz/~sara/Sono/sono.html.
[8] Z. Kotek, I. Br┬░uha, V. Chalupa, and J. Jel─▒nek. Adaptivn─▒ a uc─▒c─▒
sesystemy. SNTL, 1980.