Towards automation of flow cytometric analysis for quality-assured follow-up assessment to guide curative therapy for acute lymphoblastic leukaemia in children
- 119 Downloads
Minimal residual disease (MRD) is of high prognostic value in risk stratification in childhood acute lymphoblastic leukaemia. Flow cytometry (FCM) was shown to yield reliable results in MRD measurement. However, the interpretation of FCM data relies largely on operator skills and experience. While sample preparation, antibody panels, staining procedures and flow cytometric acquisition can be standardized, easily controlled and be made available worldwide, the availability of experienced operators represents the current bottleneck to a growing number of laboratories to the benefit of an increasing number of patients with leukaemia. Currently, international paediatric studies—throughout Europe, South America, to Australia—aim at stratifying the treatment according to the FCM-MRD methodology. The measurements are still operator-dependent leading to substantial costs regarding training and quality control. This article introduces a new European Union-funded project (AutoFLOW) aiming at the standardization and automation of FCM-MRD analysis by machine-learning technology.
KeywordsAcute lymphoblastic leukaemia Flow cytometry Minimal residual disease Gaussian mixture model Kernel density estimation
The AutoFLOW project is funded by Marie Curie Industry Academia Partnerships & Pathways (FP7-Marie Curie–PEOPLE-2013-IAPP) under the grant no. 610872. The authors would like to thank Nuno Andrade and Melanie Gau for their valuable contributions to the project. Furthermore, the authors would like to thank the R community.
Conflict of interest
Michael Reiter, Jana Hoffmann, Florian Kleber, Angela Schumich, Gerald Peter, Florian Kromp, Martin Kampel and Michael Dworzak declare that there is no conflict of interest.
- 3.Eckert C, Henze G, Seeger K, et al. Use of allogeneic hematopoietic stem-cell transplantation based on minimal residual disease response improves outcomes for children with relapsed acute lymphoblastic leukemia in the intermediate-risk group. J Clin Oncol. 2013;31(21):2736–42.PubMedCrossRefGoogle Scholar
- 6.Schrappe M. Minimal residual disease: optimal methods, timing, and clinical relevance for an individual patient. Hematol Educ Program Am Soc Hematol. 2012;2012:137–42.Google Scholar
- 7.Naim I, Datta S, Rebhahn J, Cavenaugh JS, Mosmann TR, Sharma G. SWIFT-scalable clustering for automated identification of rare cell populations in large, high-dimensional flow cytometry datasets, part 1: algorithm design: SWIFT Flow Cytometry Clustering—Part 1. Cytometry A. 2014;85(5):408–21.PubMedCentralPubMedCrossRefGoogle Scholar
- 11.Costa ES, Pedreira CE, Barrena S, et al. Automated pattern-guided principal component analysis vs expert-based immunophenotypic classification of B-cell chronic lymphoproliferative disorders: a step forward in the standardization of clinical immunophenotyping. Leukemia. 2010;24(11):1927–33.PubMedCentralPubMedCrossRefGoogle Scholar
- 12.Finak G, Bashashati A, Brinkman R, Gottardo R. Merging mixture components for cell population identification in flow cytometry. Adv Bioinformatics. 2009;2009:247646.Google Scholar
- 17.Qian Y, Wei C, Eun-Hyung Lee F, et al. Elucidation of seventeen human peripheral blood B-cell subsets and quantification of the tetanus response using a density-based method for the automated identification of cell populations in multidimensional flow cytometry data. Cytometry B Clin Cytom. 2010;78(Suppl. 1):S69–82.PubMedCentralPubMedCrossRefGoogle Scholar
- 20.Bishop C. Pattern recognition and machine learning (information science and statistics). Secaucus: Springer-Verlag New York, Inc.; 2006.Google Scholar