Skip to main content
Log in

Classification of follicular lymphoma images: A holistic approach with symbol-based machine learning methods

Klassifizierung von follikulären Lymphom Bildern: Ein ganzheitlicher Ansatz mit maschinellen – mit Symbolen arbeitenden – Lernverfahren

  • Original article
  • Published:
Wiener klinische Wochenschrift Aims and scope Submit manuscript

Zusammenfassung

Mit Symbolen arbeitende maschinelle Lernverfahren werden nur selten in der Klassifikation und Diagnostik von Bildern eingesetzt. In der vorliegenden Arbeit stellen wir ein solches Verfahren vor, das wir erstmals bei Bildern des follikulären Lymphoms eingesetzt haben. Das Lymphom ist ein weit gestreckter Begriff, der eine Reihe von Karzinomen des lymphatischen Systems beinhaltet. Ein Lymphom wird durch den Zelltyp der sich vermehrenden Zelle und durch die Erscheinungsart des Krebses differenziert. Eine exakte Diagnose des Lymphomtyps ist für die wirksamste Therapie des Patienten von essentieller Bedeutung. Unsere Arbeit war fokussiert auf die Identifikation von Lymphomen durch die Darstellung von Follikeln in Mikrosokop-Bildern, die uns vom Pathologie Labor des Universitäts-Spitals von Tenerifa (Spanien) zur Verfügung gestellt worden sind. Wir teilten unsere Arbeit in zwei Stadien ein: im ersten Stadium führten wir eine Vorverarbeitung der Bilder mit einer Extraktion der Merkmale durch. Im zweiten Stadium verwendeten wir verschiedene Methoden der mit Symbolen maschinell arbeitenden Lernmethoden zur Pixel-Klassifikation. Die mit Symbolen arbeitenden Lernmaschin-Methoden werden bei der Suche nach Bildanalysen oft vernachlässigt. Sie sind anerkannt zur Darstellung gut bekannter Bildern mit, allerdings nur mangelhafter, Einsetzbarkeit in der Verarbeitung durch Computer. Unsere Ergebnisse sind sehr vielversprechend und zeigen, dass Methoden mit Einsatz von Symbolen in der Anwendung zur Bildanalyse erfolgreich sein können.

Summary

It is not very often to see a symbol-based machine learning approach to be used for the purpose of image classification and recognition. In this paper we will present such an approach, which we first used on the follicular lymphoma images. Lymphoma is a broad term encompassing a variety of cancers of the lymphatic system. Lymphoma is differentiated by the type of cell that multiplies and how the cancer presents itself. It is very important to get an exact diagnosis regarding lymphoma and to determine the treatments that will be most effective for the patient's condition. Our work was focused on the identification of lymphomas by finding follicles in microscopy images provided by the Laboratory of Pathology in the University Hospital of Tenerife, Spain. We divided our work in two stages: in the first stage we did image pre-processing and feature extraction, and in the second stage we used different symbolic machine learning approaches for pixel classification. Symbolic machine learning approaches are often neglected when looking for image analysis tools. They are not only known for a very appropriate knowledge representation, but also claimed to lack computational power. The results we got are very promising and show that symbolic approaches can be successful in image analysis applications.

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

Access this article

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

Instant access to the full article PDF.

References

  • Unger F. Health is Wealth – Toward a European Lead Market in Health Care. Acta Medico-Biotechnica 2008;1:11–8

    Google Scholar 

  • Chaganti RSK, Dalla-favera R, Harris NL. The Lymphomas: Etiology, Pathology, Genetics and Treatment. Academia Press 2003

  • Mauch PM, Armitage JO, Harris NL, Dalla-Favera R, Coiffier B. Non-Hodgkin's Lymphomas. N Engl J Med 2004

  • Perner P. Mining Knowledge in Medical Image Databases, In Data Mining and Knowledge Discovery: Theory, Tools, and Technology, Dasarathy BV (Editor), Proceedings of SPIE 2000;4057:359–69

  • Deselaers T, Müller H, Clough P, Ney H, Lehmann TM. The CLEF 2005 Automatic Medical Image Annotation Task. International Journal of Computer Vision archive. 2007;74(1):51–58

    Article  Google Scholar 

  • Lézoray O, Charrier C, Cardot H, Lefèvre S. Machine Learning in Image Processing. EURASIP Journal on Advances in Signal Processing 2008;2008:2

    Article  Google Scholar 

  • Iftikhar S, Bond AR, Wagan AI, Weinberg PD, Bharath AA. Segmentation of Endothelial Cell Boundaries of Rabbit Aortic Images Using a Machine Learning Approach. International Journal of Biomedical Imaging 2011;2011:11

    Article  Google Scholar 

  • Otsu N. A Threshold Selection Method from Gray-Level Histograms. IEEE Transactions on Systems, Man, and Cybernetics 1979;9(1):62–6

    Article  Google Scholar 

  • Thrun S, Pratt L. Learning to Learn. Kluwer Academic Publishers 1998

  • Kokol P, Kokol M, Dinevski D. Teaching evolution using visual simulation. British Journal of Educational Technology 2005;36(3):563–6

    Article  Google Scholar 

  • Fayyad U, Piatetsky-Shapiro G, Smyth P. From data mining to knowledge discovery in databases. AI Magazine 1996;17(3):37–54

    Google Scholar 

  • Shortliffe E. Computer Based Medical Consultations: MYCIN. Elsevier Science Ltd, New York 1996

    Google Scholar 

  • Quinlan JR. C4.5: Programs for Machine Learning. Morgan Kaufmann publishers, San Mateo 1993

    Google Scholar 

  • Quinlan JR. Induction of decision trees, Machine Learning 1986;1:81–106

    Google Scholar 

  • Pawlak Z, Grzymala-Busse J, Slowinski R, Ziarko W. Rough Sets. Communications of the ACM 1995;38(11):89–95

    Article  Google Scholar 

  • Iglesias CJ. The Role of Hybrid Systems in Intelligent Data Management: The Case of Fuzzy/neural Hybrids, Control Engineering Practice 1996;4(6):839–45

    Article  Google Scholar 

  • Podgorelec V, Kokol P, Yamamoto R, Masuda G, Sakamoto N. Knowledge discovery with genetically induced decision trees, International ICSC congress on Computational intelligence: Methods and applications CIMA'2001, University of Wales, Bangor, Wales, United Kingdom 2001

  • Goldberg DE. Genetic Algorithms in Search, Optimization, and Machine Learning. Addison Wesley, Reading MA 1989

    Google Scholar 

  • Zorman M, Hleb Babič Š, Šprogar M. Advanced tool for building decision trees MtDeciT 2.0. International conference on artificial intelligence, June 28 - July 1, 1999, Las Vegas, Nevada, USA. Las Vegas: CSREA, 1999;1:315–8

  • Zorman M, Sigut JF, Sánchez de la Rosa JL, Alayón S, Kokol P, Verlič M. Evolutionary built decision trees for supervised segmentation of follicular lymphoma images. Proceedings of the 9th IASTED International conference on Intelligent systems and control 2006;1:182–7

    Google Scholar 

  • Zorman M, Podgorelec V, Kokol P, Peterson M, Lane J. Decision tree's induction strategies evaluated on a hard real world problem, Proceedings of the 13th IEEE Symposium on Computer-Based Medical Systems CBMS 2000;1:19–24

    Article  Google Scholar 

  • Breiman L. Bagging predictors. Machine Learning 1996;24;123–40

    Google Scholar 

  • Freund Y, Schapire RE. Experiments with a new boosting algorithm. Machine Learning: Proc. Thirteenth International Conference. Morgan Kauffman, San Francisco 1996;1:148–156

    Google Scholar 

  • Breiman L. Random Forests. Machine Learning 2001;45(1):5–32

    Article  Google Scholar 

  • Freund Y, Mason L. The alternating decision tree learning algorithm. Proceeding of the Sixteenth International Conference on Machine Learning, Bled, Slovenia 1999;1:124–33

    Google Scholar 

  • Bazan J, Nguyen HS, Nguyen SH, Synak P, Wróblewski J. Rough set algorithms in classification problem. In L. Polkowski, S. Tsumoto, and T. Lin, editors, Rough Set Methods and Applications, Physica-Verlag, Heidelberg New York 2000;1:49–88

    Google Scholar 

  • Grzymała-Busse J. A New Version of the Rule Induction System LERS Fundamenta Informaticae 1997;31(1):27–39

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Milan Zorman.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Zorman, M., Sánchez de la Rosa, J. & Dinevski, D. Classification of follicular lymphoma images: A holistic approach with symbol-based machine learning methods. Wien Klin Wochenschr 123, 700–709 (2011). https://doi.org/10.1007/s00508-011-0091-z

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00508-011-0091-z

Keywords

Navigation