THE USE OF HELLWIG’S METHOD FOR DIMENSION REDUCTION IN FEATURE SPACE OF THYROID ULTRASOUND IMAGES


Abstract

This paper presents the use of Hellwig’s method for dimension reduction in feature space of thyroid ultrasound images. On the base of this method, the combination of three features with the greatest value of Hellwig’s index information capacity from the input set of 283 features was obtained. This set was used to build and test the classifiers. Classification results were compared with the results obtained for a set of 48 features obtained using correlation method. It turned out that the accuracy of classifiers built on the base of 3 features is not worse than the accuracy of classifiers built on the base of 48 features, and in some cases it is even higher. This suggests that the Hellwig’s method can be used as an effective method for dimension reduction in feature space for the future thyroid ultrasound images classification.


Keywords

Hellwig’s method; Hashimoto’s disease; image processing; texture classification

Cichosz P.: Systemy uczące się. Wydawnictwa Naukowo-Techniczne, Warszawa, 2007.

Ćwik J., Koronacki J.: Statystyczne systemy uczące się. Wydawnictwa Naukowo-Techniczne, Warszawa, 2005.

Ćwik J., Mielniczuk J.: Statystyczne systemy uczące się. Ćwiczenia w oparciu o pakiet R. Oficyna Wydawnicza Politechniki Warszawskiej, Warszawa, 2009.

Haralick R., Shanmugam K., Dinstein I.: Textural Features for Image Classification. IEEE Transactions on Systems, Man and Cybernetics, Vol. 3, No 6, 610-621, 1973.

Hayashi N., Tamaki N.: Sonography of Hashimoto’s thyroiditis. J. Clin. Ultrasound, Vol. 14, 1986, pp. 123-126.

Hellwig Z.: On the optimal choice of predictors. Study VI in Z. Gostkowski (ed.): Toward a system of quantitative indicators of components of human resources development; Paris: UNESCO, 1968.

Koprowski R., Korzyńska A., Wróbel Z., Zieleźnik W., Witkowska A., Małyszek J., Wójcik W.: Influence of the measurement method of features in ultrasound images of the thyroid in the diagnosis of Hashimoto’s disease. BioMedical Engineering OnLine 2012, 11:91, DOI:10.1186/1475-925X-11-91

Koprowski R., Wróbel Z., Zieleźnik W.: Automatic ultrasound image analysis in Hashimoto’s disease. Lect. Notes in Comput. Sci. – Adv. in Pattern Recognit. Vol. 6256, 2010, pp. 98-106.

Koprowski R., Wróbel Z., Zieleźnik W.: Analysis of thyroid ultrasonogram in Hashimoto’s disease. The 2010 International Congress on Computer Applications and Computational Science. IRAST, Singapore, 2010, pp. 448-451.

Koprowski R., Zieleźnik W., Wróbel Z., Małyszek J., Stępień B., Wójcik W.: Assessment of significance of features acquired from thyroid ultrasonograms in Hashimoto's disease. BioMedical Engineering OnLine 2012, 11:48, DOI:10.1186/1475-925X-11-48

Krzyśko M., Wołyński W., Górecki T., Skorzybut M.: Systemy uczące się. Rozpoznawanie wzorców analiza skupień i redukcja wymiarowości. Wydawnictwa Naukowo-Techniczne, Warszawa, 2008.

Loy M., Cianchetti M.E., Cardia F., Melis A., Boi F., Mariotti S.: Correlation of computerized gray-scale sonographic findings with thyroid function and thyroid autoimmune activity in patients with Hashimoto's thyroiditis. J. Clin. Ultrasound, Vol. 32(3), 2004, pp. 136-140.

Mailloux G., Bertrand M., Stampfler R., Ethier S.: Computer analysis of echographic textures in Hashimoto disease of the thyroid. J. Clin. Ultrasound, Vol. 14(7), 1986, pp. 521-527.

Mazzotii G., Sorvillo F., Iorio S., Carbone A., Romeo A., Piscopo M., Capuano S., Capuano E., Amato G., Carella C.: Grey-scale analysis allows a quantitative evaluation of thyroid echogenicity in the patients with Hashimoto’s thyroiditis. Clin. Endocrinol. Vol. 59, 2003, pp. 223-229.

Omiotek Z., Burda A., Wójcik W.: Metoda klasyfikacji obrazów USG tarczycy z wykorzystaniem indukcji drzew decyzji. Prace Instytutu Elektrotechniki, Zeszyt 260, 2012 s. 57-68.

Omiotek Z., Burda A., Wójcik W.: The use of decision tree induction and artificial neural networks for automatic diagnosis of Hashimoto’s disease. Expert Systems with Applications (2013), DOI: http://dx.doi.org/10.1016/j.eswa.2013.03.022

Petrie A., Sabin C.: Statystyka medyczna w zarysie. Wydawnictwo Lekarskie PZWL, Warszawa 2006.

Sara R., Smutek D., Sucharda R., Svacina S.: Systematic Construction of Texture Features for Hashimoto’s Lymphocytic Thyroiditis Recognition from Sonographic Images. In 8th Conference on Artificial Intelligence in Medicine in Europe. AIME, Cascais, Portugal, 2001, pp. 339-346.

Schiemann U., Gellner R., Riemann B., Schierbaum G., Menzel J., Domschke W., Hengst K.: Standardized grey scale ultrasonography in Graves' disease: correlation toautoimmune activity. Eur. J. Endocrinol. Vol. 141(4), 1999, pp. 332-336.

Stąpor K.: Metody klasyfikacji obiektów w wizji komputerowej. Wydawnictwo Naukowe PWN. Warszawa, 2011.

Uwe S., Avenhaus W., Konturek J., Gellner R., Hengst K., Gross M.: Relationship of clinical features and laboratory parameters to thyroid echogenicity measured by standardized grey scale ultrasonography in patients with Hashimoto’s thyroiditis. Med. Sci. Monit. Vol. 9(4), 2003, pp. 49-53.

Zieleźnik W., Małyszek-Tumidajewicz J., Stęchły T., Stępień B., Wójcik W., Owczarek A.: The analysis of thyroid ultrasound echogenicity in the patients with hashimoto’s disease. Eur Thyroid J, 5:160, 2011.

Zieleźnik W., Witkowska A., Małyszek-Tumidajewicz J., Koprowski R., Stępień B., Owczarek A., Koprowski R., Wójcik W.: The new method of analysis thyroid echogenicity in the patients with Hashimoto’s disease. Sent to Thyroid, 2012.

Strona domowa środowiska R: http://www.r-project.org/


Published : 2014-09-26


Omiotek, Z., & Wójcik, W. (2014). THE USE OF HELLWIG’S METHOD FOR DIMENSION REDUCTION IN FEATURE SPACE OF THYROID ULTRASOUND IMAGES. Informatyka, Automatyka, Pomiary W Gospodarce I Ochronie Środowiska, 4(3), 14-17. https://doi.org/10.5604/20830157.1121333

Zbigniew Omiotek  zomiotek@gmail.com
Lublin University of Technology, Faculty of Electrical Engineering and Computer Science  Poland
Waldemar Wójcik 
Lublin University of Technology, Faculty of Electrical Engineering and Computer Science  Poland