Discrimination of Poorly Distinguishable Random Textures by Statistical Analysis of Morphological Spectra

• Autorzy: Przytulska M. , Kulikowski J. L. , Wierzbicka D.
• Języki publikacji: EN

Abstrakty

EN

The paper describes a method for discrimination of poorly distinguishable textures based on application of morphological spectra. The textures are analyzed as random fields of specific probability distributions. The samples of textures are thus considered as their instances and so are also their morphological spectra. Some basic properties of morphological spectra, as well as the definition of similarity measure are shortly reminded. The problem of textures discrimination is formulated as similarity assessment of spectral components histograms. For this purpose, various statistics like: mean value, standard deviation, skewness and kurtosis, as well as some secondary statistics based on theformer, are used. A discriminating index is introduced for evaluation of their discriminating properties. The method of evaluating the discriminating power of statistics based on 1st and 2nd level morphological spectra is illustrated by analysis of the spectra of USG liver images in the groups of healthy persons and patients affected by liver fibrosis. A short description of a IASS program used to the calculations is given. The problem of textures discrimination invariant to rotations and parallel translations of images is described. It is shown that the proposed method discriminates statistically the “ill” and “healthy” textures despite the fact that the differences between them are visually not distinguishable.

Słowa kluczowe

EN

computer-aided image analysis; textures discrimination; morphological spectra; statistical data analysis; ultrasound liver imaging

• Wydawca: Institute of Information Technology of the Warsaw University of Life Sciences – SGGW
• Czasopismo: Machine Graphics and Vision
• Rocznik: 2011
• Tom: Vol. 20, No. 4
• Strony: 455--477
• Opis fizyczny: Bibliogr. 12 poz., wykr.

Twórcy

autor

Przytulska M.

• Nalecz Institute of Biocybernetics and Biomedical Engineering PAS, 4 Ks. Trojdena str., 02-109 Warsaw, Poland

autor

Kulikowski J. L.

• Nalecz Institute of Biocybernetics and Biomedical Engineering PAS, 4 Ks. Trojdena str., 02-109 Warsaw, Poland

autor

Wierzbicka D.

• Nalecz Institute of Biocybernetics and Biomedical Engineering PAS, 4 Ks. Trojdena str., 02-109 Warsaw, Poland

Bibliografia

• [1] Mann H. B., Whitney D. R. On a test of whether one of two random variables is stochastically larger than the other. Ann. Math. Statistics, vol. 18, 1947.
• [2] Fisz M. Probability Theory and Mathematical Statistics. John Wiley & Sons Inc. New York, 1965.
• [3] Bruno A., Collorec R., Bezy-Wendling J., et al. Texture Analysis in Medical Imaging. In: Roux C., Coatrieux J.-L. (Eds) Contemporary Perspectives in Three-Dimensional Biomedical Imaging. IOS Press, Amsterdam, pp. 133-164, 1997.
• [4] Kulikowski J .L. Pattern Recognition Based on Ambiguous Indications of Experts. In: Kurzynski M. (Ed.) Komputerowe Systemy Rozpoznawania KOSYR’2001, Wyd. Politechniki Wrocławskiej, Wroclaw, pp. 15-22, 2001.
• [5] Kulikowski J. L. Pattern recognition (Rozpoznawanie obrazów, in Polish). In: Chmielewski L. Kulikowski J. L., Nowakowski A. (Eds) Obrazowanie biomedyczne, vol. 8, Chapt. 7. AOW EXIT, Warsaw, pp. 193-237, 2003.
• [6] Suri J .S., Wilson D. L., Laxminarayan S. (Eds.) Handbook of Biomedical Image Analysis. Vol. I, Segmentation Models, Part B. Kluwer Academic/Plenum Publishers, New York, 2005.
• [7] Kulikowski J. L., Przytulska M., Wierzbicka D. Recognition of Textures Based on Analysis of Multilevel Morphological Spectra. GESTS International Transactions on Computer Science and Engineering, vol. 38 (1), pp. 99-107, 2007.
• [8] Kulikowski J. L., Przytulska M., Wierzbicka D.. Morphological Spectra as Tools for Texture Analysis. In: Kurzynski M. & al. (Eds.). Computer Recognition Systems 2. LNSC 45, Springer-Verlag, Berlin, 510-517, 2007.
• [9] Kulikowski J. L., Przytulska M., Wierzbicka D.. Biomedical Structures Representation by Morphological Spectra. In: Piętka E., Kawa J. (Eds.).Information Technologies in Biomedicine. LNSC 47, Springer-Verlag, Berlin, pp. 57-65, 2008.
• [10] Przytulska M., Kulikowski J. L., Bajera A., Królicki L. Comparison of SPECT Cerebral Images Examination Methods Based on Luminance Level and Morphological Spectra Evaluation. Biocybernetics and Biomedical Engineering, vol. 28, nr 1, pp. 29-42, 2009.
• [11] Kulikowski J. L., Przytulska M., Wierzbicka D. Description of Biomedical Textures by Statistical Properties of Morphological Spectra. Biocybernetics and Biomedical Engineering, vol. 30, nr 3, pp. 19-34, 2010.
• [12] Report on the research project No N N518 4211 33. (Sprawozdanie merytoryczne z realizacji projektu badawczego nr N N518 4211 33, in Polish). Methods of computer analysis of radiological images for assessment of pathomorphological changes in selected inner organs. Nalecz Institute of Biocybernetics and Biomedical Engineering PAS, Warsaw, 2010 (not published, accessible at the IBBE PAS).