Analiza wpływu segmentacji jąder komórkowych w rozmazach Papanicolaou na pomiar wymiaru fraktalnego

• Autorzy: Mazurek P. , Oszutowska-Mazurek D.

Warianty tytułu

EN

Analysis of influence of cell nuclei segmentation in Papanicolaou smears on fractal dimension measurements

• Języki publikacji: PL

Abstrakty

PL

W artykule badano wrażliwość metody pryzm trójkątnych (TPM - Triangular Prism Method) do estymacji wymiaru fraktalnego dla różnych rozmiarów jądra komórkowego w cytologii ginekologicznej wybarwionej metodą Papanicolaou. Zmiana obszaru analizy pozwala na zmniejszenie wpływu algorytmu segmentacji na wynik. Wykorzystanie kanału zielonego gęstości optycznej i zmian wymiaru fraktalnego dla par skal: 1-2 oraz 2-3 pozwala na otrzymanie wyników dla systemu klasyfikacji z małą wrażliwością na segmentację.

EN

In the paper the influence of segmentation algorithms on estimation for the fractal dimension is analyzed. The Papanicolaou smears are very complex images and their automatic analysis is very hard. Segmentation algorithms of cell nuclei should support blurred and noised edges between cytoplasm and cell nucleus. The estimation of the cell nuclei image parameters is necessary, but the edge related parameters are not sufficient. The classification of the cells (correct/atypical) needs surface related parameters. Fractal based estimators are important for classification. The Papanicolaou images are colourful but only the green channel is important [9]. The TPM (Triangular Prism Method) is applied to the square area (2N+1 edge size) [5]. Multiple box selection variants occur and the multiple TPM analysis is applied and the mean value is calculated. The fractal dimension is calculated for a pair of scales (1-2, 2-3, 3-4). The correct and atypical cell nuclei are known and the analysis is separated. The histograms of difference between the known and reduced cell area are shown (Figs. 6-11). The atypical cells are less sensitive due to a larger size of the analysis area in comparison to the correct ones. Two scales (1-2) and (2-3) are useful, especially for smaller reduction parameter (erosion up to 9 pixels of original cell nuclei). Both scales are used in the classification system [9]. The fractal dimension changes are less than +/- 1%.

Słowa kluczowe

PL

estymacja; wymiar fraktalny; przetwarzanie obrazów; jądra komórkowe

EN

estimation; fractal dimension; image processing; cell nuclei

• Wydawca: Wydawnictwo PAK
• Czasopismo: Pomiary Automatyka Kontrola
• Rocznik: 2012
• Tom: R. 58, nr 6
• Strony: 498--501
• Opis fizyczny: Bibliogr. 16 poz., rys., wykr., wzory

Twórcy

autor

Mazurek P.

autor

Oszutowska-Mazurek D.

• West-Pomeranian University of Technology, Szczecin, Department of Signal Processing and Multimedia Engineering, 26. kwietnia 10, 71-126 Szczecin,

Bibliografia

• [1] Ballerini L, Franzn L.: Fractal Analysis of Microscopic Images of Breast Tissue, WSEAS Trans. on Circuit, Vol. 11, No. 2 p. 7, 2001. doi:10.1186/1471-2407-10-260.
• [2] Bauer W., Mackenzie C. D.: Cancer Detection via Determination of Fractal Cell Dimension, 1999, http://cdsweb.cern.ch/record/376287
• [3] Bedin V., Adam R. L., de Sa B., Landman G., Metze K.: Fractal dimension of chromatin is an independent prognostic factor for survival in melanoma”, BMC Cancer, 10:260, 2010, http://www.biomedcentral.com/1471-2407/10/260
• [4] Blackledge J. Dubovitskiy D.: An Optical Machine Vision System for Applications in Cytopathology, ISAST Transactions on Computers and Intelligent Systems, Vol. 2, Issue 1, pp. 95-109, 2010.
• [5] Clarke K. C.: Computation of the Fractal Dimension of Topographic Surfaces using the Triangular Prism Surface Area Method. Computer and Geosciences, Vol. 12, No. 5, pp. 713-722, 1986.
• [6] Dey P.: Fractal geometry: Basic principles and applications in pathology, Anal Quant Cytol Histol 2005, 27 (5), pp. 284-290, PMID: 16447821.
• [7] Goutzanis L., Papadogeorgakis N., Pavlopoulos P. M., Katti K., Petsinis V., Plochoras I., Pantelidaki C., Kavantzas N., Patsouris E., Alexandridis C.: Nuclear fractal dimension as a prognostic factor in oral squamous cell carcinoma, Oral Oncology 44, pp. 345-353, 2008, doi: 10.1016/j.oraloncology.2007.04.005.
• [8] Kaye B. H.: A Random Walk Through Fractal Dimensions, VCH 1994.
• [9] Mazurek P., Oszutowska D.: Estimation of Fractal Dimension According to Optical Density of Cell Nuclei in Papanicolaou Smears, Information Technologies in Biomedicine (Pietka E. ed.), Lecture Notes in Computer Science, 2012.
• [10] McKenna S. J.: Automated analysis of Papanicolaou smears. PhD Thesis, University of Dundee, 1994.
• [11] Oszutowska D., Waker-Wójciuk G., Mazurek P.: Fractal analysis limitations in digital analysis of Papanicolaou cytological images, Measurement Automation and Monitoring, pp. 52-54, 2012.
• [12] Peitgen H. O., Jurgens H., Saupe D.: Fractal for the Class-rooms, Part1: Introduction to Fractals and Chaos, Springer-Verlag, 1992.
• [13] Seuront L.: Fractals and Multifractals in Ecology and Aquatic Science, CRC Press, 2010.
• [14] Steven I.: Linear Richardson Plots from Non-Fractal Data Sets, Dutch Mathematical Geology, Vol. 25, No. 6, pp. 737-751, 1993. doi: 10.1007/BF00893176.
• [15] Yokoyama T., Kawahar A., Kage M., Kojiro M., Takayasu H., Sato T.: Image analysis of irregularity of cluster shape in cytological diagnosis of breast tumors: Cluster analysis with 2D-fractal dimension, Diagn Cytopathol 2005, 33(2) pp. 71-77, PMID: 16007648.
• [16] Zieliński K. W., Strzelecki M.: Komputerowa analiza obrazu biomedycznego. Wstęp do morfometrii i patrologii ilościowej. Wydawnictwo Naukowe PWN, 2002.