Advertisement

A Clinical Tool for Automated Flow Cytometry Based on Machine Learning Methods

  • Claude Takenga
  • Michael Dworzak
  • Markus Diem
  • Rolf-Dietrich Berndt
  • Erling Si
  • Michael Brandstoetter
  • Leonid Karawajew
  • Melanie Gau
  • Martin Kampel
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10209)

Abstract

Clinical researchers working in flow cytometry (FCM) nowadays experience increasing demands to perform experiments that involve high throughput, rare event analysis and detailed immunophenotyping. Beckman Coulter and Becton Dickinson offer multi-use flow cytometry sorters that can analyze up to 70K EPS (events per seconds) with more than nine parameters enabled. While this multi-parametric feature provides a great power for hypothesis testing, it also generates a vast amount of data, which is analyzed manually through a processing called gating. For large experiments, this manual gating turns out to be time consuming and requires intensive operator training and experience. The lack of required expertise leads to wrong interpretation of data, thus a wrong therapy course for the case of patients with acute lymphoblastic leukemia (ALL) is followed. This paper aims to present a pipeline-software, as a ready-to-use machine learning based automated FCM assessment tool for the daily clinical practice for patients with ALL. The new system increases accuracy in assessment of FCM based on minimal residual disease (MRD) method in samples analyzed by conventional operator-based gating since computer-aided analysis potentially has a higher power due to the use of the whole multi-parametric FCM-data space at once instead of using methods restricted to two-dimensional decision rules. The tool is implemented as a telemedical network for analysis, clinical follow-up, treatment monitoring of leukemia and allows dissemination of automated FCM-MRD analysis to medical centres in the world.

Keywords

Clinical tool Flow cytometry Leukemia Machine learning Telematics platform Telemedicine 

Notes

Acknowledgments

The AutoFLOW project is funded by Marie Curie Industry Academia Partnerships & Pathways (FP7-MarieCurie-PEOPLE-2013- IAPP) under the grant no.610872.

References

  1. 1.
    Reiter, M., Kleber, F., Rota, P., Groeneveld-Krentz, S., Schumich, A., Dworzak, M., Gau, M.: An automated flow cytometry data analysis support system. In: CYTO 2015, Glasgow (2015)Google Scholar
  2. 2.
    Rota, P., Kleber, F., Reiter, M., Groeneveld-Krentz, S., Kampel, M.: The role of machine learning in medical data analysis. A case study: flow cytometry. In: Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISAPP, vol. 3, pp. 303–310. ISBN 978-989-758-175-5. doi: 10.5220/0005675903030310
  3. 3.
    Toedling, J., Rhein, P., Ratei, R., Karawajew, L., Spang, R.: Automated in-silico detection of cell populations in flow cytometry readouts and its application to leukemia disease monitoring. BMC Bioinform. 7, 282 (2006). doi: 10.1186/1471-2105-7-282 CrossRefGoogle Scholar
  4. 4.
    PDQ® Pediatric Treatment Editorial Board: PDQ Childhood Acute Lymphoblastic Leukemia Treatment. National Cancer Institute, Bethesda. http://www.cancer.gov/types/leukemia/patient/child-all-treatment-pdq. [PMID: 26389385]. Accessed 28 Oct 2016
  5. 5.
    Costa, E.S., Arroyo, M.E., Pedreira, C.E., García-Marcos, M.A., Tabernero, M.D., Almeida, J., Orfao, A.: A new automated flow cytometry data analysis approach for the diagnostic screening of neoplastic B-cell disorders in peripheral blood samples with absolute lymphocytosis. J. Leukemia 20, 1221–1230 (2006). doi: 10.1038/sj.leu.2404241. Published online 25 May 2006CrossRefGoogle Scholar
  6. 6.
    Aghaeepour, N., Finak, G., Hoos, H., Mosmann, T.R., Brinkman, R., Gottardo, R., Scheuermann, R.H.: Critical assessment of automated flow cytometry data analysis techniques. Nat. Methods 10(3), 228–238 (2013). doi: 10.1038/nmeth.2365 CrossRefGoogle Scholar
  7. 7.
    Rota, P., Groeneveld-Krentz, S., Reiter, M.: On automated flow cytometric analysis for MRD estimation of acute lymphoblastic leukaemia: a comparison among different approaches. In: The Proceedings of Bioinformatics and Biomedicine (BIBM 2015), pp. 438–441 (2015)Google Scholar
  8. 8.
    AIEOP-BFM ALL 2009 treatment protocol. http://www.bfm-international.org/aieop/aieop_index.html
  9. 9.
    Reiter, M., Kleber, F., Hoffmann, J., Groeneveld-Krentz, S., Groeneveld, T., Dworzak, M., Schuumich, A., Kampel, M., Gau, M.: Status report of the automated software-based MRD-assessment procedure. In: 28th Annual Meeting of the International BFM (Berlin-Frankfurt-Muenster) Study Group, Budapest, Hungary (2015)Google Scholar
  10. 10.
    Reiter, M., Ho-mann, J., Kleber, F., Schumich, A., Peter, G., Kromp, F., Kampel, M., Dworzak, M.: Towards automation of flow cytometric analysis for quality assured follow-up assessment to guide curative therapy for acute lymphoblastic leukaemia in children. Memo Mag. Eur. Med. Oncol. 7(4), 219–226 (2014). SpringerGoogle Scholar
  11. 11.
    Bonner, W.A., Hulett, H.R., Sweet, R.G., Herzenberg, L.A.: Fluorescence activated cell sorting. Rev. Sci. Instrum. 43(3), 404–409 (1972). doi: 10.1063/1.1685647 CrossRefGoogle Scholar
  12. 12.
    Campana, D., Coustan-Smith, E.: Detection of minimal residual disease in acute leukemia by flow cytometry. J. Cytometry Part A 38(4), 139–152 (1999). doi: 10.1002/(SICI)1097-0320(19990815)38:4<139:AID-CYTO1>3.0.CO;2-H CrossRefGoogle Scholar
  13. 13.
    Karawajew, L., Dworzak, M., et al.: Minimal residual disease analysis by eight-color flow cytometry in relapsed childhood acute lymphoblastic leukemia. J. Haematol. 100, 935–944 (2015). doi: 10.3324/haematol.2014.116707 CrossRefGoogle Scholar
  14. 14.
    Verschoor, C.P., Lelic, A., Bramson, J.L., Bowdish, D.M.E.: An introduction to automated flow cytometry gating tools and their implementation. J. Front. Immunol. 8, 1–8 (2015). doi: 10.3389/fimmu.2015.00380. http://www.frontiersin.org Google Scholar
  15. 15.
    Nunes, C., Wong, R., Mason, M., Fegan, C., Man, S., Pepper, C.: Expansion of a CD8(+)PD-1(+) replicative senescence phenotype in early stage CLL patients is associated with inverted CD4: CD8 ratios and disease progression. Clin. Cancer Res. 18(3), 678–687 (2012). doi: 10.1158/1078-0432.CCR-11-2630 CrossRefGoogle Scholar
  16. 16.
    Dalmazzo, L.F.F., Jácomo, R.H., Marinato, A.F., Figueiredo-Pontes, L.L., Cunha, R.L.G., Garcia, A.B., et al.: The presence of CD56/CD16 in T-cell acute lymphoblastic leukaemia correlates with the expression of cytotoxic molecules and is associated with worse response to treatment. Br. J. Haematol. 144(2), 223–229 (2009). doi: 10.1111/j.1365-2141.2008.07457 CrossRefGoogle Scholar
  17. 17.
    Reiter, M., Rota, P., Kleber, F., Diem, M., Groeneveld-Krentz, S., Dworzak, M.: Clustering of cell populations in flow cytometry data using a combination of Gaussian mixtures. J. Pattern Recogn. 60, 1029–1040 (2016). ElsevierCrossRefGoogle Scholar
  18. 18.
    Chu, H., Yang, Y., Li, Q., Xu, Y., Wei, H.: A scalable clinical intelligent decision support system. In: Chang, C.K., Chiari, L., Cao, Yu., Jin, H., Mokhtari, M., Aloulou, H. (eds.) ICOST 2016. LNCS, vol. 9677, pp. 159–165. Springer, Cham (2016). doi: 10.1007/978-3-319-39601-9_14 CrossRefGoogle Scholar
  19. 19.
    Berndt, R.D., Takenga, C., et. al.: SaaS-platform for mobile health applications. In: Proceedings of the IEEE-International Multi-conference on Systems, Signals and Devices, Chemnitz, Germany, pp. 1–4, March 2012, doi: 10.1109/SSD.2012.6198120
  20. 20.
  21. 21.
    Cario, G., Rhein, P.: High CD45 surface expression determines relapse risk in children with precursor B-cell and T-cell acute lymphoblastic leukemia treated according to the ALL-BFM 2000 protocol. Haematologica 99(1), 103–110 (2014). doi: 10.3324/haematol.2013.090225 CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Claude Takenga
    • 1
  • Michael Dworzak
    • 2
    • 3
  • Markus Diem
    • 1
    • 2
  • Rolf-Dietrich Berndt
    • 4
  • Erling Si
    • 4
  • Michael Brandstoetter
    • 5
  • Leonid Karawajew
    • 6
  • Melanie Gau
    • 1
  • Martin Kampel
    • 1
  1. 1.Computer Vision LabTU WienViennaAustria
  2. 2.Labdia Labordiagnostik GmbHViennaAustria
  3. 3.Children’s Cancer Research InstituteMedical University of ViennaViennaAustria
  4. 4.Infokom GmbHNeubrandenburgGermany
  5. 5.CogVis Software and Consulting GmbHViennaAustria
  6. 6.Charité – Universitaetmedizin BerlinBerlinGermany

Personalised recommendations