COMPARISON OF THE INFLUENCE OF STANDARDIZATION AND NORMALIZATION OF DATA ON THE EFFECTIVENESS OF SPONGY TISSUE TEXTURE CLASSIFICATION


Abstract

The aim of this article was to compare the influence of the data pre-processing methods – normalization and standardization – on the results of the classification of spongy tissue images. Four hundred CT images of the spine (L1 vertebra) were used for the analysis. The images were obtained from fifty healthy patients and fifty patients with diagnosed with osteoporosis. The samples of tissue (50×50 pixels) were subjected to a texture analysis to obtain descriptors of features based on a histogram of grey levels, gradient, run length matrix, co-occurrence matrix, autoregressive model and wavelet transform. The obtained results were set in the importance ranking (from the most important to the least important), and the first fifty features were used for further experiments. These data were normalized and standardized and then classified using five different methods: naive Bayes classifier, support vector machine, multilayer perceptrons, random forest and classification via regression. The best results were obtained for standardized data and classified by using multilayer perceptrons. This algorithm allowed for obtaining high accuracy of classification at the level of 94.25%.


Keywords

texture analysis; standardization; normalization; classification

Budzik G., Dziubek T., Turek P.: Podstawowe czynniki wpływające na jakość obrazów tomograficznych. Problemy Nauk Stosowanych 2015, 77–84.

Chen Y, Dougherty E.R.: Gray-scale morphological granulometric texture classification. Optical Engineering 33 (8)/1994, 2713–2722.

Cichy P.: Analiza tekstury obrazów cyfrowych – zastosowanie do wybranej klasy obrazów biomedycznych. Rozprawa doktorska, Politechnika Łódzka, Wydział Elektrotechniki i Elektroniki, Instytut Elektroniki, Łódź 2001.

Downey P.A., Siegel M.I.: Bone Biology and the Clinical Implications for Osteoporosis. Phys Ther 86/2006, 77–91.

Duda D., Krtowski M., Bézy-Wendling J.: Klasyfikacja tekstur w rozpoznawaniu nowotworów wątroby na podstawie serii obrazów tomograficznych. Obrazowanie Medyczne, tom 1, 2005.

Duda D., Krętowski M., Bézy-Wendling J.: Ekstrakcja cech teksturalnych w klasyfikacji obrazów tomograficznych wątroby. Zeszyty Naukowe Politechniki Białostockiej, Informatyka, 2007.

Dzierżak R., Omiotek Z., Tkacz E., Kępa A.: 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. IBE 2018 Innovations in Biomedical Engineering, 2019, 55–66.

Giannakopoulos X., Karhunen J., Oja E.: An Experimental Comparison Of Neural ICA Algorithms. Proc. Int. Conf. on Artificial Neural Networks ICANN’98, 1998, 651–656.

Ismail Bin M., Dauda U.: Standardization and Its Effects on K-Means Clustering Algorithm. Research Journal of Applied Sciences, Engineering and Technology 6(17)/ 2013, 3299–3303.

Lazarek J.: Metody analizy obrazu – analiza obrazu mammograficznego na podstawie cech wyznaczonych z tekstury. Informatyka, Automatyka Pomiary w Gospodarce i Ochronie Środowiska 4/2013, 10–13.

Lee T.W., Lewicki M.S.: Unsupervised Imane Classification, Segmentation and Enhancement Using ICA Mixture Models. IEEE Transactions on Image Processing 11(3)/2002, 270-279.

Lygeros J.: A Formal Approach to Fuzzy Modelling. Proceedings of ACC, 1995, 3740–3744.

Mala K., Sadasivam V.: Automatic Segmentation and Classification of Diffused Liver Diseases using Wavelet Based Texture Analysis and Neural Network. Annual IEEE INDICON Conference, 2005, 216–219.

Marcus R., Feldman D., Dempster D., Luckey M., Cauley J.: Osteoporosis, 4th ed. Elsevier Academic Press, 2013.

Matheron G.: Random sets and integraf geometry. Wiley, New York 1975.

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. Proceedings of the 2017 International Conference on Advanced Technologies for Signal and Image Processing (ATSIP), 2017, 1–5.

Nieniewski M., Serneels R.: Extraction of the Shape of Small Defects on the Surface of Ferrite Cores. Machine Graphics and Vision 9 (1/2)/2000, 453–462.

Omiotek, Z.: Improvement of the classification quality in detection of Hashimoto’s disease with a combined classifier approach. Journal of Engineering in Medicine 231(8)/ 2017, 774–782.

Omiotek Z., Wójcik W.: The use of Hellwig’s method for dimension reduction in feature space of thyroid ultrasound images. Informatyka, Automatyka, Pomiary 3/2014, 14–17 [DOI: 10.5604/20830157.1121333].

Reshmalakshmi C., Sasikumar M.: Trabecular bone quality metric from X-ray images for osteoporosis detection. Proceedings of the 2017 International Conference on Intelligent Computing, Instrumentation and Control Technologies (ICICICT), India, 2017, 1694–1697.

Snitkowska E.: Analiza tekstur w obrazach cyfrowych i jej zastosowanie do obrazów angiograficznych, Rozprawa doktorska, Politechnika Warszawska, 2004.

Strzelecki M., Materka A.: Tekstura obrazów biomedycznych. Metody analizy komputerowej. Wydawnictwo PWN, Warszawa 2017.

Tadeusiewicz R., Śmietański J.: Pozyskiwanie obrazów medycznych oraz ich przetwarzanie, analiza, automatyczne rozpoznawanie i diagnostyczna interpretacja. Wydawnictwo Studenckiego Towarzystwa Naukowego, Kraków 2011.

Titus A., Nehemiah H., Kannan A.: Classification of interstitial lung disease using particle swarm optimized support vector machines. International Journal of Soft Computing 10 (1)/2015, 25–36.

Usman, K., Rajpoot, K.: Brain tumor classification from multi-modality MRI using wavelets and machine learning. Pattern Analysis and Applications 20(3)/2017, 871–881.

www.eletel.p.lodz.pl/programy/cost/progr_mazda.html [06.05.2018].

Download

Published : 2019-09-26


Dzierżak, R. (2019). COMPARISON OF THE INFLUENCE OF STANDARDIZATION AND NORMALIZATION OF DATA ON THE EFFECTIVENESS OF SPONGY TISSUE TEXTURE CLASSIFICATION. Informatyka, Automatyka, Pomiary W Gospodarce I Ochronie Środowiska, 9(3), 66-69. https://doi.org/10.35784/iapgos.62

Róża Dzierżak  r.dzierzak@pollub.pl
Politechnika Lubelska  Poland
http://orcid.org/0000-0001-5640-0204