Wpływ technik rozpoznawania wzorców na ocene złośliwości nowotworów piersi

• Autorzy: Jeleń, Ł. , Krzyżak, A. , Fevens, T. , Jeleń, M.

Warianty tytułu

EN

Influence of Pattern Recognition Techniques on Breast Cytology Grading

• Języki publikacji: EN

Abstrakty

PL

W ninieszym artykule prezentujemy zastosowania technik rozpoznawania wzorców oraz analizy obrazu do automatycznej obróbki i analizy obrazów cytologicznych. W celu wskazania nowych wyzwań w tej dziedzinie przegląd literatury zwiazanej z tym zagadnieniem został zaprezentowany. Ocena złośliwości nowotworów piersi jest skomplikowanym problemem gdzie doświadczenie jest bardzo istotne i może mieć wpływ na końcową diagnozę. Zastosowanie komputerowego systemu oceny pozwoli na zobiektywizowanie tego procesu. Artykuł prezentuje liczne zastosowania technik rozpozanwania wzorców w odniesieniu do zdjęć cytologicznych nowowtworów piersi w celu lepszej separowalności nietylko między komórkami nowtworowymi i zdrowymi, ale także między stpniami złośliwości. Wyznaczenie stopnia złośliwości jest bardzo istotne w diagnostyc, ponieważ ma wpływ na wybór sposobu leczenia. W niniejszym artykule prezentujemy także porównanie trzech sieci neuronowych wykorzystanych do oceny zdjęć cytologicznych piersi oraz porównujemy ich działanie z perceptronem wielowarstwowym opisanym w literaturze.

EN

In this paper we discuss applications of pattern recognition and image processing to automatic processing and analysis of cytological images. The literature survey of the problem is presented to point out new chalenges. The brest cancer malignancy grading is a difficult procedure that involves a lot of experiance which can have an impact on the diagnosis. A role of the computerized system is to help to make the diagnosis process more objective. The paper presents numerous applications of the patteren recognition techniques to breast cancer cytology to produce better discriminations not only between cancerous and helthy cells but also malignancy grades. Determination of the maligancy grade is crutial during the diagnosis because it will have an impact on the patient treatment. In the paper we also present a comparison of three neural networks applied to the breast cytology and compare them to the multilayer approach from the literature.

Słowa kluczowe

PL

biopsja aspiracyjna cienkoigłowa; ocena złośliwości nowotworów piersi; rozpoznawanie wzorców

EN

fine needle aspirates; breast cancer malignancy grading; pattern recognition

• Czasopismo: Biuletyn Naukowy Wrocławskiej Wyższej Szkoły Informatyki Stosowanej. Informatyka
• Rocznik: 2012
• Tom: vol. 2
• Strony: 16--23
• Opis fizyczny: Bibliogr. 57 poz., rys.

Twórcy

autor

Jeleń, Ł.

• Wrocław School of Applied Informatics, Wejherowska 28, 54-239 Wrocław, Poland,

autor

Krzyżak, A.

• Department of Computer Science and Software Engineering, Concordia University, 1455 De Maisonneuve Blvd. West, Montréal, Québec, Canada H3G 1M8,

autor

Fevens, T.

• Department of Computer Science and Software Engineering, Concordia University, 1455 De Maisonneuve Blvd. West, Montréal, Québec, Canada H3G 1M8,

autor

Jeleń, M.

• Department of Pathology and Clinical Cytology, Medical University of Wrocław Borowska 213, 50-556 Wrocław, Poland,

Bibliografia

• [1] Duda, R., Hart, P., and Stork, D. (2000) Pattern Classification. Wiley Interscience Publishers, 2nd ed.
• [2] Cheng, H., Shi, X., Min, R., Cai, X., and H.N., D. (2006) Approaches for Automated Detection and Classification of Masses in Mammograms. Pattern Recognition, 39(4), 646-668.
• [3] Bottema, M. and Slavotinek, J. (2000) Detection and Classification of Lobular and DCIS (small cell) Microcalcifications in Digital Mammograms . Pattern Recognition Letters, 21(13-14), 1209-1214.
• [4] Cheng, H. and Cui, M. (2004) Mass Lesion Detection with a Fuzzy Neural Network. Pattern Recognition, 37, 1189-1200.
• [5] Cheng, H., Wang, J., and Shi, X. (2004) Microcalcification Detection using Fuzzy Logic and Scale Space Approaches. Pattern Recognition, 37(2), 363-375.
• [6] De Santo, M., Molinara, M., Tortorella, F., and Vento, M. (2003) Automatic Classification of Clustered Microcalcifications by a Multiple Expert System . Pattern Recognition, 36(7), 1467-1477.
• [7] Grohman, W. and Dhawan, A. (2001) Fuzzy Convex Set-based Pattern Classification for Analysis of Mammographic Microcalcifications. Pattern Recognition, 34(7), 1469-1482.
• [8] Zhang, P., Verma, B., and Kumar, K. (2005) Neural vs. Statistical Classifier in Conjunction with Genetic Algorithm Based Feature Selection. Pattern Recognition Letters, 26(7), 909-919.
• [9] Wolberg, W. and Mangasarian, O. (1990) Multisurface Method of Pattern Separation for Medical Diagnosis Applied to Breast Cytology. Proceedings of National Academy of Science, USA, 87, 9193-9196.
• [10] Mangasarian, O., Setiono, R., and Wolberg, W. (1990) Pattern Recognition via Linear Programming: Theory and Application to Medical Diagnosis. Large-Scale Num. Opt., Philadelphia:SIAM, pp.22-31.
• [11] Street, W. N., Wolberg, W. H., and Mangasarian, O. L. (1993) Nuclear Feature Extraction for Breast Tumor Diagnosis. Imaging Science and Technology/Society of Photographic Instrumentation Engineers 1993 International Symposium on Electronic Imaging: Science and Technology, San Jose, California, vol. 1905, pp. 861-870.
• [12] Street, N. (1994) Cancer Diagnosis and Prognosis via Linear-Programming-Based Machine Learning. Ph.D. thesis, University of Wisconsin.
• [13] Lee, K. and Street, W. (1999) A Fast and Robust Approach for Automated Segmentation of Breast Cancer Nuclei. Proceedings of the Second IASTED International Conference on Computer Graphics and Imaging, Palm Springs, CA, pp. 42-47.
• [14] Lee, K. and Street, W. (2003) Model-based Detection, Segmentation and Classification for Image Analysis using On-line Shape Learning. Machine Vision and Applications, 13(4), 222-233.
• [15] Wolberg, W. H., Street, W. N., and Mangasarian, O. L. (1993) Breast Cytology Diagnosis Via Digital Image Analysis. Analytical and Quantitative Cytology and Histology, 15, 396-404.
• [16] Wolberg, W. H., Street, W. N., and Mangasarian, O. L. (1994) Machine Learning Techniques to Diagnose Breast Cancer from Image-Processed Nuclear Features of Fine Needle Aspirates. Cancer Letters, 77, 163-171.
• [17] Walker, H. J., Albertelli, L., Titkov, Y., Kaltsatis, P., and Seburyano, G. (1998) Evolution of Neural Networks for the Detection of Breast Cancer. Proceedings of International Joint Symposia on Intelligence and Systems, pp. 34-40.
• [18] Walker, H. J. and Albertelli, L. (1998) Breast Cancer Screening Using Evolved Neural Networks. IEEE International Conference on Systems, Man, and Cybernetics, 2, 1619-1624.
• [19] Nezafat, R., Tabesh, A., Akhavan, S., Lucas, C., and Zia, M. (1998) Feature Selection and Classification for Diagnosing Breast Cancer. Proceedings of International Association of Science and Technology for Development International Conference, pp. 310-313.
• [20] Estevez, J., Alayon, S., and Moreno, L. (2002) Cytological Breast Cancer Fine Needle Aspirate Images Analysis with a Genetic Fuzzy Finite State Machine. Conference Board of the Mathematical Sciences, CBMS 2002, pp. 21-26.
• [21] Bagui, S., Bagui, S., Pal, K., and Pal, N. (2003) Breast Cancer Detection using Rank Nearest Neighbor Classification Rules. Pattern Recognition, 36(1), 25-34.
• [22] Weyn, B., van de Wouwer, G., van Daele, A., Scheunders, P., van Dyck, D., van Marck, E., and Jackob, W. (1998) Automated Breast Tumor Diagnisis and Grading Based on Wavelet Chromatin Texture Description. Cytometry, 33, 32-40.
• [23] Schnorrenberg, F., Pattichis, C., Kyriacou, K., and Schizas, C. (1994) Detection of Cell Nuclei in Breast Cancer Biopsies using Receptive Fields. IEEE Proceedings of Engineering in Medicine and Biology Society, pp. 649-650.
• [24] Schnorrenberg, F., Pattichis, C., Kyriacou, K., and Schizas, C. (1996) Content-based Description of Breast Cancer Biopsy Slides. Proc. Intl. EuroPACS Mtg., pp. 136-140.
• [25] Schnorrenberg, F., Pattichis, C., Kyriacou, K., Vassiliou, M., and Schizas, C. (1996) Computer-aided Classification of Breast Cancer Nuclei. Technology & Health Care, 4(2), 147-161.
• [26] Schnorrenberg, F., Tsapatsoulis, N., Pattichis, C., Schizas, C., Kollias, S., Vassiliou, M., Adamou, A., and Kyriacou, K. (2000) A modular neural network system for the analysis of nuclei in histopathological sections. IEEE Engineering in Medicine and Biology Magazine, 19, 48-63.
• [27] Belhomme, P., Elmoataz, A., Herlin, P., and Bloyet, D. (1997) Generalized region growing operator with optimal scanning: application to segmentation of breast cancer images. Journal of Microscopy, 186, 41-50.
• [28] Adams, R. and Bischof, L. (1994) Seeded region growing. IEEE Transactions on Pattern Analysis and Machine Intelligence, 16, 641-647.
• [29] Beucher, S. (1990) Segmentation d’images et morphologie mathématique. Ph.D. thesis, Ecole National Supérieur des Mines de Paris.
• [30] Beucher, S. and Meyer, F. (1992) Mathematical Morphology in Image Processing, Chapter 12. Marcel Dekker, New York, pp. 433-481.
• [31] Lezoray, O., Elmoataz, A., Cardot, H., Gougeon, G., Lecluse, M., and Revenu, M. (1998) Segmentation of cytological images using color and mathematical morphology. European Conference on Stereology, Amsterdam, Netherlands, p. 52.
• [32] Schüpp, S., Elmoataz, A., Fadili, J., Herlin, P., and Bloyet, D. (2000) Image segmentation via multiple active contour models and fuzzy clustering with biomedical applications. The 15th International Conference on Pattern Recognition, ICPR’00, Barcelona, Spain, vol. 1, pp. 622-625.
• [33] Bloom, H. and Richardson, W. (1957) Histological Grading and Prognosis in Breast Cancer. British Journal of Cancer, 11, 359-377.
• [34] Mangasarian, O., Street, W., and Wolberg, W. (1994) Breast Cancer Diagnosis and Prognosis via Linear Programming. Operations Research, 43(4), 570-576.
• [35] Cheng, H., Li, X., Riodan, D., and J.N., S. (1991) A Parallel Approach to Tubule Grading in Breast Cancer Lesions and its VLSI Implementation. Fourth Annual IEEE Symposium on Computer-Based Medical Systems, pp. 322-329.
• [36] Cheng, H., Wu, C., and Hung, D. (1998) VLSI for Moment Computation and its Application to Breast Cancer Detection. Pattern Recognition, 31(8), 1391-1406.
• [37] MacAulay, M., Scrimger, J., Riodan, D., and Cheng, H. (1991) An Interactive Graphics Package with Standard Examples of the Bloom and Richardson Histological Grading Technique. Fourth Annual IEEE Symposium on Computer-Based Medical Systems, pp. 108-112.
• [38] Gurevich, I. and Murashov, D. (2004) Method for early diagnostics of lymphatic system tumors on the basis of the analysis of chromatin constitution in cell nucleus images. The 17th International Conference on Pattern Recognition, ICPR’04, Cambridge, UK, pp. 806-809.
• [39] Florack, L. and Kuijper, A. (2000) The topological structure of scale-space images. Journal of Mathematical Imaging and Vision, 12(1), 65-80.
• [40] Rodenacker, K. (1993) Applications of topology for evaluating pictorial structures. Theoretical Foundations of Computer Vision, Akademie-Verlag, Berlin, pp. 35-46.
• [41] Rodenacker, K. (1995) Quantitative microscope image analysis for improved diagnosis and prognosis of tumors in pathology. Creaso Info Medical Imaging, Creaso GmbH, Gilching, 22.
• [42] Rodenacker, K. and Bengtsson, E. (2003) A feature set for cytometry on digitized microscopic images. Anal Cell Pathol, 25(1), 1-36.
• [43] Weyn, B., Van de Wouwer, G., Koprowski, M., and et al. (1999) Value of morphometry, texture analysis, densitometry and histometry in the differential diagnosis and prognosis of malignant mesthelioma. Journal of Pathology, 4(189), 581-589.
• [44] Young, I., Verbeek, P., and Mayall, B. (1986) Characterization of chromatin distribution in cell nuclei. Cytometry, 7(5), 467-474.
• [45] Gurevich, I., Kharazishvili, D., Murashov, D., Salvetti, O., and Vorobjev, I. (2006) Technology for automated morphologic analysis of cytological slides. methods and results. The 18th International Conference on Pattern Recognition, ICPR’06, Hong Kong, China, pp. 711-714.
• [46] Churakova, Z., Gurevich, I., Jernova, I., and et al. (2003) Selection of diagnostically valuable features for morphological analysis of blood cells. Pattern Recognition and Image Analysis: Advances in Mathematical Theory and Applications, 13(2), 381-383.
• [47] QinetiQ (2005) Automated Histopathology Breast Cancer Analysis and Diagnisis System. Data Sheet, http://www.qinetiq.com/.
• [48] Jeleń, Ł. (2009) Computerized Cancer Malignancy Grading of Fine Needle Aspirates. Ph.D. thesis, Concordia University.
• [49] Naik, S., Doyle, S., Agner, S., Madabhushi, A., Feldman, M., and Tomaszewski, J. (2008) Automated gland and nuclei segmentation for grading of prostate and breast cancer histopathology. Proceedings of the IEEE International Symposium on Biomedical Imaging, pp. 284-287.
• [50] Jeleń, Ł., Fevens, T., and Krzyżak, A. (2008) Classification of breast cancer malignancy using cytological images of fine needle aspiration biopsies. Int. J. Math. Comput. Sci., 18, 75-83.
• [51] Jeleń, Ł., Krzyżak, A., and Fevens, T. (2008) Comparison of pleomorphic and structural features used for breast cancer malignancy classification. Lecture Notes in Computer Science, Advances in Artificial Intelligence, 5032/2008, 138-149.
• [52] Jeleń, Ł., Fevens, T., Krzyżak, A., and Jeleń, M. (2008) Discriminatory power of cells grouping features for breast cancer malignancy classification. Proceedings of the International Federation for Medical and Biological Engineering, vol. 21(3), pp. 559-562, Springer Berlin/Heidelberg.
• [53] Jeleń, Ł., Fevens, T., and Krzyżak, A. (2009) Influence of nuclei segmentation on breast cancer malignancy classification. Proceedings of SPIE, vol. 7260, pp. 726014-726014-9.
• [54] Jeleń, Ł., Lipiński, A., Detyna, J., and Jeleń, M. (2010) Clinical verification of computerized breast cancer malignancy grading. Bio-Algorithms and Med-Systems, 6 No. 12 Suppl. 1, 81-82.
• [55] Cofiño, A.S., José, M., Gutiérrez (2001) Optimal Modular Feedforward Neural Nets based on Functional Network Architectures. Lecture Notes in Computer Science, 2084, 308-315.
• [56] Park, J., Sandberg, I.W. (1991) Universal Approximation Using Radial-Basis-Function Networks. Neural Computing, 3(2), 246-257
• [57] Williams, R., Zipser, D. (1989) A learning algorithm for continually running fully recurrent neural networks. Neural Computation, Vol. 1, 270-280