Skip to main content
SpringerLink
Log in

Classification of image objects in Epo doping control using fuzzy decision tree

  • Theoretical Advances
  • Published:
Pattern Analysis and Applications Aims and scope Submit manuscript

Abstract

Erythropoietin (Epo) is a hormone which can be misused as a doping substance. Its detection involves analysis of images containing specific objects (bands), whose position and intensity are critical for doping positivity. Within a research project of the World Anti-Doping Agency (WADA) we are implementing the GASepo software that serves for Epo testing in doping control laboratories worldwide. For identification of the bands we have developed a segmentation procedure based on a sequence of filters. Whereas all true bands are properly segmented, the procedure generates a number of false positives (artefacts). To separate these artefacts we suggested a post-segmentation supervised classification using real-valued geometrical measures of objects. The method is based on a fuzzy modification of Ross Quinlan’s ID3 method, included in the mlf™ software (Machine Learning Framework). It provides a framework that generates fuzzy decision trees, as well as fuzzy sets for input data. Initially used training set of segmented objects has been replaced by a new one prepared by more accurate expertise using the latest release of the GASepo software. The new fuzzy decision trees (FDT) have been generated for a set of five and nine fuzzy sets. The comparison of the results on testing set of segmented objects shows that the classification based on the new FDTs outperforms other classification methods.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14

Similar content being viewed by others

References

  1. Wide L, Bengtsson C, Berglund B, Ekblom B (1995) Detection in blood and urine of recombinant erythropoietin administered to healthy men. Med Sci Sports Exerc 27:1569–1576

    Google Scholar 

  2. Cazzola M (2002) Further concerns about the medical risk of blood doping. Haematologica 87:232–239

    Google Scholar 

  3. Berglund B, Ekblom B (1991) Effect of recombinant human erythropoietin treatment on blood pressure and some haematological parameters in healthy men. J Intern Med 229:125–130

    Article  Google Scholar 

  4. Roberts D, Smith DJ (1994) Erythropoietin: induction of synthesis to signal transduction, Protein electrophoresis. J Mol Endocrinol 12:131–148

    Article  Google Scholar 

  5. Lasne F, de Ceaurriz J (2000) Recombinant erythropoietin in urine. Nature 405–435

  6. Bajla I, Holländer I, Gmeiner G, Reichel Ch (2004) Analysis of Epo images after isoelectric focusing and double blotting. In: Proceedings of 2nd IASTED international conference BIOMED04, Innsbruck, Austria, paper N.417-164, CDROM, pp 228-233

  7. Holländer I, Bajla I, Minichmayr M, Gmeiner G, Reichel Ch (2004) GASEpo—system for analysis of images generated in Epo Doping-Control. In: Jan J, Kozumplik J, Provaznik I (eds) Proceedings of 17th Biennal International EURASIP conference BIOSIGNAL 2004, Brno, Czech Republic, VUTIUM Press, pp 273–277

  8. Bajla I, Holländer I, Minichmayr M, Gmeiner G, Reichel Ch (2005) GASepo—a software solution for quantitative analysis of digital images in Epo doping control. Comput Meth Prog Biomed 80:246–270

    Article  Google Scholar 

  9. Bajla I, Holländer I, Gmeiner G, Reichel Ch (2005) Quantitative analysis of images in erythropoietin doping control. Med Biol Eng Comput 43:403–409

    Article  Google Scholar 

  10. Suri JS, Singh S, Reden L (2002) Fusion of region and boundary/surface-based computer vision and pattern recognition techniques for 2-D and 3-D MR cerebral cortical segmentation (Part II): a state-of-the-art review. Patt Anal Appl 5:77–98

    Article  MathSciNet  Google Scholar 

  11. Carvalho BM, Gau CJ, Herman GT, Kong TY (1999) Algorithms for fuzzy segmentation. Patt Anal Appl 1:73–81

    Article  Google Scholar 

  12. Ramoser H, Biber J, Bajla I, Holländer I (2004) Segmentation of electrophoretic images in doping control. In: Proceedings of the 2004 international conference on mathematics and engineering techniques in medicine and biological sciences (METMBS’04), June 21–24, 2004 Las Vegas, USA, CSREA Press, pp 467–470

  13. Shapiro LG, Stockman GC (2001) Computer vision. Prentice-Hall, Upper Saddle River

    Google Scholar 

  14. Quinlan JR (1986) Induction on decision trees. Mach Learn 1:81–106

    Google Scholar 

  15. Umano M et.al (1994) Fuzzy decision tree by fuzzy ID3 algorithm and its application to diagnosis systems. In: Proceedings of the 1994 IEEE international conference on fuzzy systems, June 26–29, pp 2113-2118

  16. Yuan Y, Shaw MJ (1995) Induction of fuzzy decision trees. Fuzzy Sets Syst 69:125–139

    Article  MathSciNet  Google Scholar 

  17. Yeung DS, Wang XZ, Tsang ECC (1999) Learning weighted fuzzy rules from examples with mixed attributes by fuzzy decision trees. In: Proceedings of the 1999 IEEE international conference on SMC, Tokyo, Japan, October 12–15, pp 349–354

  18. Wang XZ, Yeung DS, Tsang ECC (2001) IEEE Trans. on SMC-B 31:215–226

    Google Scholar 

  19. Bhatt RB, Gopal M (2004) Proceedings of the 13th IEEE international conference on fuzzy systems (IEEE-FUZZY 04), July 26–29, 2004, Budapest, Hungary, IEEE Press, New York, pp 1337–1342

  20. Mitra S, Konwar KM, Pal SK (2002) Fuzzy decision tree, linguistic rules and fuzzy knowledge-based network: generation and evaluation. IEEE Trans Syst Man Cybern Part C Appl Rev 32:328–339

    Article  Google Scholar 

  21. Hayashi I, Maeda T, Bastian A, Jain LC (1998) Generation of fuzzy decision trees by fuzzy ID3 with adjusting mechanism of and/or operators. In: Proceedings of the international conference on fuzzy systems, May 4–9, 1998, Anchorage, USA, pp 681–685

  22. Drobics M, Winiwarter W, Bodenhofer U (2000) Interpretation of self-organizing maps with fuzzy rules. In: Proceedings of the 12th IEEE international conference on tools with artificial intelligence (ICTAI’00), IEEE Press, New York, pp 304–411

  23. Drobics M et al (2007) Documentation of the “Machine learning framework—mlf" software package: http://www.unisoftwareplus.com/products/mlf/

  24. Pal SK, Majumder DKD (1987) Fuzzy mathematical approach to pattern recognition. Wiley, New York

    Google Scholar 

  25. Drobics M (2004) Choosing the best predicates for data-driven fuzzy modelling. In: Proceedings of the 13th IEEE international conference on fuzzy systems (IEEE-FUZZY 04), July 26–29, 2004, Budapest, Hungary, IEEE Press, pp 245–249

  26. Bradley PS, Fayyad UM (1998) Refining initial points for k-means clustering. In: J.Shavlik (ed) Proceedings of the 15th international conference on machine learning, 1998, San Francisco, USA, pp 91–99

  27. Zeidler J, Schlosser M (1996) Continuos valued attributes in fuzzy decision trees. In: Proceedings of the 8th international conference on information processing and management of uncertainty in knowledge-based systems, pp 395-400

  28. Burduk R, Kurzyński M (2006) Two-stage binary classification with fuzzy-valued loss function. Patt Anal Appl 9:353–358

    Article  Google Scholar 

  29. Chmelewski LJ (2006) Fuzzy histograms, weak fuzzification and accumulation of periodic quantities. Patt Anal Appl 9:189–210

    Article  Google Scholar 

  30. Marsala C (2000) Fuzzy decision trees to help flexible querying. Kybernetika 36(6):689–705

    Google Scholar 

  31. Peng Y, Flach PA (2001) Soft discretization to enhance the continuous decision tree induction. In: Proceedings of ECML/PKDD01 workshop integrating aspects of data mining. Decision Support and Meta-Learning, pp 109–118

  32. Klir GJ, Yuan B (eds) (1996) Fuzzy sets, fuzzy logic, and fuzzy systems. Selected papers by Lotfi A.Zadeh. World Scientific, Berkley series

  33. Bajla I, Holländer I, Heiss D, Granec R, Minichmayr M (2005) Object classification in images for Epo doping control based on fuzzy decision trees. In: Rizvi SA (ed) Proceedings of the international conference electronic imaging, applications of neural networks and machine learning in image processing IX, January 19–20, 2005, San Jose, USA, SPIE vol 5673, Nasrabadi NM, pp 42-56 (invited lecture)

  34. Witkovský V, Farkaš I, Arendacká B, Rublík F, Štolc S, Hornišová K (2005) Refined classification of bands in Epo images. Technical report, Institute of Measurement Science, Slovak Academy of Sciences, Slovak Republic, 54 pp

  35. Hand DJ (1981) Discrimination and classification. Wiley, Chichester

    MATH  Google Scholar 

  36. Arendacká B (2005) Classification of objects in segmented EPO images of objects in segmented EPO images. In: Frollo I, Tyšler M, Juráš V (eds) Proceedings of the 5th international conference measurement 2005, May 15–19, 2005 Smolenice, Slovak Republic,IMS SAS, pp 194–198

  37. Haykin S (1994) Neural networks: a comprehensive foundation. Macmillan College Publishing Company, New York

    MATH  Google Scholar 

  38. Møller M (1993) A scaled conjugate gradient algorithm for fast supervised learning. Neural Netw 6:525–533

    Article  Google Scholar 

  39. Nabney I, Bishop C (2003) NETLAB toolbox (release 3). http://www.ncrg.aston.ac.uk/netlab/index.php Neural Computing Research Group, Aston University, Birmingham

  40. Randles R, Broffitt J, Ramberg J, Hogg R (1978) Discriminant analysis based on ranks. J Am Stat Assoc 73:379–384

    Article  MathSciNet  Google Scholar 

  41. Hsu Ch-W, Chang Ch-Ch, Lin Ch-J (2001) A practical guide to support vector classification. National Taiwan University, Taipei

  42. Chang Ch-Ch, Lin Ch-J (2001) LIBSVM: a library for support vector machines. http://www.csie.ntu.edu.tw/ cjlin/papers/libsvm.ps.gz and the software url http://www.csie.ntu.edu.tw/cjlin/libsvm

Download references

Acknowledgements

This project has been carried out with the support of World Anti-Doping Agency. The authors express their thanks to Dr.Mario Drobics, Software Competence Center Hagenberg GmbH, Austria, for his valuable assistance with the mlf software application to the problem of band classification in GASepo. The thanks are also addressed to anonymous reviewers who contributed to an improvement of the manuscript.

Author information

Authors and Affiliations

  1. Austrian Research Centers GmbH-ARC, Smart System Division, 2444, Seibersdorf, Austria

    Ivan Bajla, Igor Holländer, Dorothea Czedik-Heiss & Reinhard Granec

Authors
  1. Ivan Bajla
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Igor Holländer
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Dorothea Czedik-Heiss
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Reinhard Granec
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ivan Bajla.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Bajla, I., Holländer, I., Czedik-Heiss, D. et al. Classification of image objects in Epo doping control using fuzzy decision tree. Pattern Anal Applic 12, 285–300 (2009). https://doi.org/10.1007/s10044-008-0122-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10044-008-0122-1

Keywords

Search

Navigation