Abstract
The paper considers the problem of the diagnostic analysis of blood system tumors (hemoblastosis) using special techniques. Images of lymph node specimen are taken from three groups of patients with such diagnoses as indolent chronic lymphatic leukemia, transformed chronic lymphatic leukemia, and de novo large and mixed cell lymphomas serving as source data. The analysis of the feature description showed that different sets of informative features correspond to different diagnoses. Thus, special techniques of image analysis and recognition, which allow taking into account the informative nature of images when selecting image transformation algorithms are required. Such possibilities are offered by the technique of image transformation selection when solving recognition problems. This technique allows taking into account the description peculiarities of each class of images and utilizing the recognition algorithm appropriate for the given class. The paper shows that application of this technique helps substantially improve the accuracy of the recognition.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
I. B. Gurevich, “Pattern Recognition Problem,” in Recognition, Classification, Forecast. Mathematical Methods and Their Application: Annals, Ed. by Yu. I. Zhuravlev (Nauka, Moscow, 1988), issue 1, pp. 280–329 [in Russian].
Yu. I. Zhuravlev, “On Algebraic Approach to Solve Recognition and Classification Problems,” in Cybernetics Problems (Nauka, Moscow, 1978), issue 33, pp. 5–68 [in Russian].
I. Gurevich, D. Kharazishvili, D. Murasov, O. Salvetti, and I. Vorobjev, “Technology for Automated Morphologic Analysis of Cytological Slides. Methods and Results,” in Proc. 18th Intern. Conf. on Pattern Recognition (ICPR2006) (The Institute of Electrical and Electronics Engineers, Inc., Hong Kong, Aug. 20–24 2006), pp. 711–714.
I. V. Koryabkina, “Efficient Methods and Means of Image Description in Recognition Problems,” Candidate’s Dissertation in Technical Sciences (Moscow, 2006).
A. A. Trykova, “Diagnostic Analysis of Hematological Medications Images on the Base of Combined Application of Statistical Methods,” Graduate Work (Moscow, 2005).
I. B. Gurevich, “Descriptive Technique for Image Description, Representation and Recognition,” Pattern Recognition and Image Analysis: Advances in Mathematical Theory and Applications in the USSR 1(1), 50–53 (1991).
I. Gurevich, “The Descriptive Approach to Image Analysis. Current State and Prospects. Image Analysis,” in Proc. 14th Scandinavian Conf. SCIA2005, Joensuu, June 2005, Ed. by Heikki Kalviainen, Jussi PArkkinen, and Arto Kaarna (LNCS 3540, Springer-Verlag, Berlin, Heidelberg, 2005), pp. 214–223.
I. B. Gurevitch, “The Descriptive Framework for an Image Recognition Problem,” in Proc. 6th Scandinavian Conf. on Image Analysis. In 2 Vols. Pattern Recognition Society of Finland (Oulu, June 19–22 1989), vol. 1, pp. 220–227.
I. Gurevich, D. Kharazishvili, I. Jernova, A. Khilkov, A. Nefyodov, and I. Vorobjev, “Information Technology for the MorphologicalAnalysis of the Lymphoid Cell Nuclei,” in Proc. 13th Scandinvian Conf. on Image Analysis (SCIA2003), Ed. by J. Bigun and T. Gustavsson (Halmstad, 29 June–2 July 2003), LNCS 2749, pp. 541–548.
I. B. Gurevich and Yu. I. Zhuravlev, “An Image Algebra Accepting Image Models and Image Transforms,” in Proc. 7th Intern. Workshop “Vision, Modeling, and Visualization 2002” (VMV2002), Erlangen, Nov. 20–22 2002, Ed. by G. Greiner, H. Niemann, T. Ertl, B. Girod, and H.-P. Seidel (IOS Press, B. V. Amsterdam, Infix Akademische Verlagsgasellschaft, Aka GMBH, Berlin, 2002), pp. 21–26.
I. Koryabkina, “Method for Image Informational Properties Exploitation in Pattern Recognition,” in Proc. 13th Scandinavian Conf. on Image Analysis (SCIA2003), Ed. by J. Bigun and T. Gustavsson (29 June–2 July 2003), LNCS 2749, pp. 1006–1013.
Atlas “Tumors of Lymphatic Systems,” Ed. by A. I. Vo-rob’ev (Hematological Scientific Center of the Russian Academy of Medical Sciences, Moscow, 2001) [in Russian].
Yu. I. Zhuravlev, V. V. Ryazanov, O. V. Senko, A. S. Biryukov, D. P. Vetrov, A. A. Dokukin, N. N. Katerinochkina, D. A. Kropotov, A. S. Obukhov, M. Yu. Romanov, I. V. Ryazanov, I. V. Tolstov, and F. B. Chelnokov, “Recognition: A Universal Software System for Recognition, Data Mining, and Forecasting,” Pattern Recognition and Image Analysis 15(2), 476–478 (2005).
Author information
Authors and Affiliations
Corresponding author
Additional information
Igor B. Gurevich (born August 24, 1938), Dr. Sci. in Engineering (specialty: Automatic control and Electrical Engineering), 1961, Moscow Power Engineering Institute, Moscow, USSR; Dr. Sci. in Theoretical Computer Science/Mathematical Cybernetics, 1975, Moscow Institute of Physics and Technology, Moscow, USSR. Head of Department at the Dorodnicyn Computing Centre of the Russian Academy of Sciences, Moscow, Assistant Professor at the Faculty of Computer Science at the Lomonosov State University. Since 1960 he has worked as an engineer and researcher in industry and medicine, at universities and the Russian Academy of Sciences. Areas of Expertise: Image Analysis, Image Understanding, Mathematical Theory of Pattern Recognition, Theoretical Computer Science, Application of Pattern Recognition and Image Analysis Techniques in Medicine, Nondestructive Testing, Process Control, Knowledge Bases, and Knowledge-Based Systems. Two monographs (in coauthorship), 135 papers on Pattern Recognition, Image Analysis, Theoretical Computer Sciences and Applications in peer reviewed International and Russian journals, conference and workshop proceedings; 1 USSR patent and 4 RF patents. Executive Secretary of “The Russian federation Association for Pattern Recognition and Image Analysis,” member of International Association for Pattern Recognition Governing Board (representative from Russian Federation), IAPR Fellow. He has been the PI of many research and development projects as part of national research (applied and basic research) programs of the Russian Academy of Sciences, the Ministry of Education and Science of Russian Federation, the Russian Foundation for Basic Research, the Soros Foundation, and INTAS. Vice Editor-in Chief of “Pattern Recognition and Image Analysis,” International Academic Publishing Company “NAUKA/INTERPERIODICA” Pleiades Publishing.
Irina V. Koryabkina (born 1978). Graduated from the Faculty of Computational Mathematics and Cybernatics with the Lomonosov Moscow State University in 2000. In 2006, she received a Ph.D in Engineering (specialty: Theoretical Foundations of Informatics). Researcher at the Dorodnicyn Computing Centre of the Russian Academy of Sciences, Moscow; Head of the Secretariat of the National Committee on image recognition and analysis of the Russian Academy of Sciences. Fields of scientific interests: mathematical theory of image recognition and analysis, image features, and medical applications. The author of more than 20 papers in peer reviewed journals and conference proceedings. Awarded with diplomas in the nomination of “The best report delivered by a young scientist” at four international conferences and workshops. Scientific Secretary at the 6th and 7th International Conferences “Pattern recognition and image analysis: new informational technologies” and the 6th Russian-German workshop “Pattern recognition and image understanding.” Executor and head executor of a number of research projects within the framework of national and international programs.
Rights and permissions
About this article
Cite this article
Gurevich, I.B., Koryabkina, I.V. Selection of image transformations in the computer analysis of cytological specimens. Pattern Recognit. Image Anal. 20, 73–80 (2010). https://doi.org/10.1134/S1054661810010074
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S1054661810010074