Annals of Biomedical Engineering

, Volume 38, Issue 4, pp 1473–1482 | Cite as

Classification of Leukemia Blood Samples Using Neural Networks

  • Malek Adjouadi
  • Melvin Ayala
  • Mercedes Cabrerizo
  • Nuannuan Zong
  • Gabriel Lizarraga
  • Mark Rossman
Article
First Online:
Received:
Accepted:

Abstract

Pattern recognition applied to blood samples for diagnosing leukemia remains an extremely difficult task which frequently leads to misclassification errors due in large part to the inherent problem of data overlap. A novel artificial neural network (ANN) algorithm is proposed for optimizing the classification of multidimensional data, focusing on acute leukemia samples. The programming tool established around the ANN architecture focuses on the classification of normal vs. abnormal blood samples, namely acute lymphocytic leukemia (ALL) and acute myeloid leukemia (AML). There were 220 blood samples considered with 60 abnormal samples and 160 normal samples. The algorithm produced very high sensitivity results that improved up to 96.67% in ALL classification with increased data set size. With this type of accuracy, this programming tool provides information to medical doctors in the form of diagnostic references for the specific disease states that are considered for this study. The results obtained prove that a neural network classifier can perform remarkably well for this type of flow-cytometry data. Even more significant is the fact that experimental evaluations in the testing phase reveal that as the ALL data considered is gradually increased from small to large data sets, the more accurate are the classification results.

Keywords

Blood cell classification Leukemia diagnosis Acute lymphocytic leukemia Acute myeloid leukemia Artificial neural networks 
This is a preview of subscription content, log in to check access.

Notes

Acknowledgments

The authors appreciate the support provided by the National Science Foundation under Grants CNS-0426125, HRD-0833093, CNS-0520811, CNS-0540592. The authors are grateful for the clinical support provided through the Ware Foundation and the joint Neuro-Engineering Program with Miami Children’s Hospital. We also thank Beckman-Coulter Corporation for providing us the flow-cytometry data, which was critical for this research.

References

  1. 1.
    Adjouadi, M., and M. Ayala. Introducing neural studio: an artificial neural networks simulator for educational purposes. Comput. Educ. J. 14(3):33–40, 2004.Google Scholar
  2. 2.
    Adjouadi, M., and N. Fernandez. An orientation-independent imaging technique for the classification of blood cells. J. Part. Part. Syst. Charact. 18(2):91–98, 2001.CrossRefGoogle Scholar
  3. 3.
    Adjouadi, M., C. Reyes, J. Riley, and P. Vidal. Adaptive filtering for flow-cytometric particles. J. Part. Part. Syst. Charact. 17(3):126–133, 2000.CrossRefGoogle Scholar
  4. 4.
    Adjouadi, M., C. Reyes, P. Vidal, and A. Barreto. An analytical approach to signal reconstruction using Gaussian approximations applied to randomly generated data and flow cytometric data. IEEE Trans. Signal Process. 48(10):2839–2849, 2000.CrossRefGoogle Scholar
  5. 5.
    Adjouadi, M., N. Zong, and M. Ayala. Multidimensional pattern recognition and classification of white blood cells using support vector machines. Part. Part. Syst. Charact. 22:107–118, 2005.CrossRefGoogle Scholar
  6. 6.
    Ahlstrom, C., P. Hult, P. Rask, et al. Feature extraction for systolic heart murmur classification. Ann. Biomed. Eng. 34(11):1666–1677, 2006.CrossRefPubMedGoogle Scholar
  7. 7.
    Albitar, M., T. Manshouri, Y. Shen, et al. Myelodysplastic syndrome is not merely “preleukemia”. Blood 100(3):791–798, 2002.CrossRefPubMedGoogle Scholar
  8. 8.
    Beckman-Coulter Corp., FL. AcV Differential and Case Studies, Monograph. Available: http://www.beckmancoulter.com/literature/ClinDiag/AcT5diffCaseStudies.pdf, Bulletin 9151, 2000.
  9. 9.
  10. 10.
    Bohnke, A., F. Westphal, A. Schmidt, R. A. El-Awady, and J. Dahm-Daphi. Role of p53 mutations, protein function and DNA damage for the radiosensitivity of human tumour cells. Int. J. Radiat. Biol. 80(1):53–63, 2004.CrossRefPubMedGoogle Scholar
  11. 11.
    Buño, I., W. A. Wyatt, A. R. Zinsmeister, J. Dietz-Band, and R. T. Silver. A special fluorescent in situ hybridization technique to study peripheral blood and assess the effectiveness of interferon therapy in chronic myeloid leukemia. Blood 92(7):2315–2321, 1998.PubMedGoogle Scholar
  12. 12.
    Burges, C. J. C. A tutorial on support vector machines for pattern recognition. Data Min. Knowl. Disc. 2(2):121–167, 1998.CrossRefGoogle Scholar
  13. 13.
    Chiu, A. W. L., E. E. Kang, M. Derchansky, et al. Online prediction of onsets of seizure-like events in hippocampal neural networks using wavelet artificial neural networks. Ann. Biomed. Eng. 34(2):282–294, 2006.CrossRefPubMedGoogle Scholar
  14. 14.
    Cristianini, N., and J. Shawe-Taylor. An Introduction to support vector machines and other kernel-based learning methods. New York: Cambridge University Press, 2000.Google Scholar
  15. 15.
    De Paz, J. F., S. Rodríguez, J. Bajo, and J. M. Corchado. Case-based reasoning as a decision support system for cancer diagnosis: a case study. Int. J. Hybrid Intell. Syst. 6(2):97–110, 2009.Google Scholar
  16. 16.
    Feki, S., H. El Omri, M. A. Laatiri, S. Ennabli, K. Boukef, and F. Jenhani. Contribution of flow cytometry to acute leukemia classification in Tunisia. Dis. Markers 16(3–4):131–133, 2000.PubMedGoogle Scholar
  17. 17.
    Foran, D. J., D. Dorin Comaniciu, P. Meer, and L. A. Goodell. Computer-assisted discrimination among malignant lymphomas and leukemia using immunophenotyping, intelligent image repositories, and telemicroscopy. IEEE Trans. Inform. Technol. Biomed. 4(4):265–273, 2000.CrossRefGoogle Scholar
  18. 18.
    Haferlach, T., A. Kohlmann, S. Schnittger, M. Dugas, W. Hiddemann, W. Kern, and C. Schoch. Global approach to the diagnosis of leukemia using gene expression profiling. Blood 106(4):1189–1198, 2005.CrossRefPubMedGoogle Scholar
  19. 19.
    Horsch, K., M. L. Giger, L. A. Venta, and C. J. Vyborny. Computerized diagnosis of breast lesions on ultrasound. Med. Phys. 29(2):157–164, 2002.CrossRefPubMedGoogle Scholar
  20. 20.
    Kohavi, R., and F. Provost. Glossary of terms. Mach. Learn. 30:271–274, 1998.CrossRefGoogle Scholar
  21. 21.
    Kurth, C., F. Gillam, and B. J. Steinhoff. EEG spike detection with a Kohonen feature map. Ann. Biomed. Eng. 28(11):1362–1369, 2000.CrossRefPubMedGoogle Scholar
  22. 22.
    Liu, B., Q. Cui, T. Jiang, and S. Ma. A combinational feature selection and ensemble neural network method for classification of gene expression data. BMC Bioinform. 5:136, 2004. doi: 10.1186/1471-2105-5-136.
  23. 23.
    Lopes Ferrari, M., J. S. Rodrigues Oliveira, M. Romeo, and J. Kerbauy. Fluorescent in situ hybridization (FISH) for BCR/ABL in chronic myeloid leukemia after bone marrow transplantation. Sao Paulo Med. J./Rev. Paul Med. 119(1):8–16, 2001.Google Scholar
  24. 24.
    Mark, H. F., W. Sikov, H. Safran, T. C. King, and R. C. Griffith. Fluorescent in situ hybridization for assessing the proportion of cells with trisomy 4 in a patient with acute non-lymphoblastic leukemia. Ann. Clin. Lab. Sci. 25(4):330–335, 1995.PubMedGoogle Scholar
  25. 25.
    O’Neill, M. C., and L. Song. Neural network analysis of lymphoma microarray data: prognosis and diagnosis near-perfect. BMC Bioinform. 4:13, 2003. doi: 10.1186/1471-2105-4-13.
  26. 26.
    Prasad, B., and W. Badawy. High-throughput identification and classification algorithm for leukemia population statistics. J. Imaging Sci. Technol. 52(3):030509.1–030509.23, 2008.Google Scholar
  27. 27.
    Reyes, C., and M. Adjouadi. A directional clustering technique for random data classification. J. Cytometry 27(2):126–135, 1997.CrossRefGoogle Scholar
  28. 28.
    Rifkin, R., and A. Klautau. In defense of one-vs-all classification. J. Mach. Learn. Res. 5:101–141, 2004.Google Scholar
  29. 29.
    Sabino, D. M. U., Ld. F. Costa, E. G. Rizzatti, and M. A. Zago. A texture approach to leukocyte recognition. Imaging Bioinform. III 10(4):205–216, 2004.Google Scholar
  30. 30.
    Tilbury, J., P. Eetvelt, J. Garibaldi, J. Curnow, and E. Ifeachor. Receiver operating characteristic analysis for intelligent medical systems—a new approach for finding confidence intervals. IEEE Trans. Biomed. Eng. 47(7):952–963, 2000.CrossRefPubMedGoogle Scholar
  31. 31.
    Tung, W., and C. Quek. GenSo-FDSS: a neural-fuzzy decision support system for pediatric ALL cancer subtype identification using gene expression data. Artif. Intell. Med. 33(1):61–88, 2004.CrossRefGoogle Scholar
  32. 32.
    University of Leicester, Department of Microbiology & Immunology, Cells of the Blood. www.micro.msb.le.ac.uk/MBChB/bloodmap.
  33. 33.
    Vapnik, V. N. The Ature of Statistical Learning Theory. New York: Springer, 1995.Google Scholar
  34. 34.
    Zhang, X. S., R. J. Roy, D. Schwender, et al. Discrimination of anesthetic states using mid-latency auditory evoked potential and artificial neural networks. Ann. Biomed. Eng. 29(5):446–453, 2001.CrossRefPubMedGoogle Scholar

Copyright information

© Biomedical Engineering Society 2009

Authors and Affiliations

  • Malek Adjouadi
    • 1
  • Melvin Ayala
    • 1
  • Mercedes Cabrerizo
    • 1
  • Nuannuan Zong
    • 1
  • Gabriel Lizarraga
    • 1
  • Mark Rossman
    • 1
  1. 1.Department of Electrical & Computer, Center for Advanced Technology and EducationFlorida International UniversityMiamiUSA

Personalised recommendations