Removing artefacts from microscopic images of cytological smears

• Autorzy: Piętka B. D. , Dulewicz A. , Jaszczak P.
• Języki publikacji: EN

Abstrakty

EN

This paper gives an overview of authors' attempts to design a computer-assisted urine smear screening system, focusing on the nastiest issues hampering its successful practical implementation. There are many valuable works concerning more or less sophisticated image processing and data mining algorithms which are capable of automatically detecting pathological morphology of cytological objects and distinguishing them from normal ones. Unfortunately, most of the attempts to implement those smart ideas in real world are likely to fail because of one but fundamental obstacle - artefacts. If not properly identified and removed from the analysis, they tend to generate so many false-positive warnings that the automated support is going to be useless because of its dramatically low specificity. Our paper addresses this neglected problem, trying to point out some general rules and implementation details that should be followed to reduce the influence of artefacts on overall system performance.

Słowa kluczowe

EN

computer-aided digital cytology; urologic oncology; microscopic smears screening systems; urinary bladder cancer

• Wydawca: Institute of Information Technology of the Warsaw University of Life Sciences – SGGW
• Czasopismo: Machine Graphics and Vision
• Rocznik: 2008
• Tom: Vol. 17, No. 1/2
• Strony: 131--152
• Opis fizyczny: Bibliogr. 18 poz., rys., tab., wykr.

Twórcy

autor

Piętka B. D.

autor

Dulewicz A.

autor

Jaszczak P.

• Image Processing Systems Laboratory Biomedical Information Processing Methods Departament Institute of Biocybernetics and Biomedical Engineering, Polish Academy of Sciences, 4 Trojdena str., 01-211 Warsaw, Poland,

Bibliografia

• [1] Haralick R. M., Shanmugam K. and Dinstein L: Textural features for image classification. IEEE Transactions on Systems, Man and Cybernetics. SMC-3 (6):610-620, 1973.
• [2] Haralick R. M.: Statistical and Structural Approaches to Texture. Proceedings of the IEEE, 67:786-804, 1979.
• [3] Kakizoe T, Matumoto K, Nishio Y, Ohtani M, Kishi K.: Significance of carcinoma in situ and dysplasia in association with bladder cancer, J Uroi. 1985 Mar; 133 (3): 395-8.
• [4] Gonzalez R. C., Wintz P.: Digital image processing. 2nd edn. Addison-Wesley Publishing Company, 1987.
• [5] Rao A. R. and Lohse G. L.: Identifying high level features of texture perception. CVGIP: Graph. Models Image Process., 55 (3):218-233, 1993.
• [6] Intersociety Working Group for Cytology Technologies: Proposed Guidelines for Primary Screening Instruments for Gynecologic Cytology, Acta Cytologica, Volume 41, Number 3/May-June 1997.
• [7] Intersociety Working Group for Cytology Technologies: A Proposed Methodology for Evaluating Secondary Screening (Rescreening) Instruments for Gynecologic Cytology, Acta Cytologica, Volume 41, Number 3/May-June 1997.
• [8] Patlak M.: New devices aim at improving pap test accuracy, FDA 1997.
• [9] O'Leary T., Tellado M., Buchner S.: PAPNET- Assisted rescreening of cervical smears, JAMA, January 21, 1998, Vol 279, No.3.
• [10] Kok M., Boon M., Conseąuences of Neural NetworkTechnology for Cervical Screening - Increase in Diagnostic Consistency and Positive Scores, American Cancer Society, 1999.
• [11] Dulewicz A., Piętka D., Jaszczak P., Nechay A.: Selective acquisition of images in the process of automatic scaning of microscopic slides, Proceedings of the World Congress on Medical Physics and Biomedical Engineering, Chicago, July 23-28, 2000.
• [12] Dulewicz A., Piętka D., Jaszczak P., Nechay A., Sawicki W., Pykao R., Koźmińska E., Borkowski A.: Computer Identification of Neoplastic Urothelial Nuclei from the Bladder, Analiytical and Quan-titative Cytology And Histology, October 2001, Vol. 23, No. 5, 2001.
• [13] Jaszczak P., Dulewicz A., Nechay A., Piętka D.: Selected algorithms for computer analysis of mi-croscope seans in the system for early detection of urinary bladder cancer, 6th European Conference on Engineering and Medicine - ESEM-2001, Belfast, May 3-5 2001, 214-217.
• [14] Oosterlinck W, Lobel B, Jakse G, Malmstrom PU, Stockle M, Sternberg C.: European Association of Urology (EAU) Working Group on Oncological Urology. Guidelines on bladder cancer. Eur Uroi 2002; 24: 105-112.
• [15] Dulewicz A., Piętka D., Jaszczak P.: A trial of a new approach to computer analysis of urothelial nuclei for cancer detection, Proceedings of the Computer Recognition Systems Conference, Technical University of Wrocaw, May 2003., 15-20.
• [16] Oosterlinck W., Solsona E., van der Meijden A. P. M., Sylvester R., Boehle A., Rintala E., Lobel B.: European Association of Urology. EAU guidelines on diagnosis and treatment of upper urinary tract transitional celi carcinoma. Eur Uroi 2004; 46: 147-154.
• [17] Dulewicz A., Piętka B. D. and. Jaszczak P.: A Trial of Practical Computer Analysis of Urothelial Nuclei for Cancer Detection, Horizons in Cancer Research, Vol.6: Progress in Bladder Cancer Research, Malloroy A.M. (Editor) Nova Biomedical Books, New York, 2005.
• [18] Piętka D., Dulewicz M., Jaszczak P.: Removing artefacts from microscopic images of cytological smears. A Shape-Based Approach, CORES 2005.