Format

Send to

Choose Destination
Cytometry A. 2019 Jul 7. doi: 10.1002/cyto.a.23852. [Epub ahead of print]

Automated Flow Cytometric MRD Assessment in Childhood Acute B- Lymphoblastic Leukemia Using Supervised Machine Learning.

Author information

1
Immunological Diagnostics, Children's Cancer Research Institute, Vienna, Austria.
2
Computer Vision Lab, Faculty of Informatics, Technical University of Vienna, Vienna, Austria.
3
Department of Pediatric Oncology/Hematology, Charité Universitätsmedizin Berlin, Berlin, Germany.
4
Cellular Immunology Laboratory, Hospital de Pediatria "Dr. Juan P. Garrahan", Buenos Aires, Argentina.
5
Department of Hematology, Oncology and Tumor Immunology, HELIOS Klinikum Berlin-Buch, Berlin, Germany.
6
Labdia Labordiagnostik GmbH, Vienna, Austria.

Abstract

Minimal residual disease (MRD) as measured by multiparameter flow cytometry (FCM) is an independent and strong prognostic factor in B-cell acute lymphoblastic leukemia (B-ALL). However, reliable flow cytometric detection of MRD strongly depends on operator skills and expert knowledge. Hence, an objective, automated tool for reliable FCM-MRD quantification, able to overcome the technical diversity and analytical subjectivity, would be most helpful. We developed a supervised machine learning approach using a combination of multiple Gaussian Mixture Models (GMM) as a parametric density model. The approach was used for finding the weights of a linear combination of multiple GMMs to represent new, "unseen" samples by an interpolation of stored samples. The experimental data set contained FCM-MRD data of 337 bone marrow samples collected at day 15 of induction therapy in three different laboratories from pediatric patients with B-ALL for which accurate, expert-set gates existed. We compared MRD quantification by our proposed GMM approach to operator assessments, its performance on data from different laboratories, as well as to other state-of-the-art automated read-out methods. Our proposed GMM-combination approach proved superior over support vector machines, deep neural networks, and a single GMM approach in terms of precision and average F 1 -scores. A high correlation of expert operator-based and automated MRD assessment was achieved with reliable automated MRD quantification (F 1 -scores >0.5 in more than 95% of samples) in the clinically relevant range. Although best performance was found, if test and training samples were from the same system (i.e., flow cytometer and staining panel; lowest median F 1 -score 0.92), cross-system performance remained high with a median F 1 -score above 0.85 in all settings. In conclusion, our proposed automated approach could potentially be used to assess FCM-MRD in B-ALL in an objective and standardized manner across different laboratories.

KEYWORDS:

B-ALL; acute lymphoblastic leukemia; algorithm; automated gating; gaussian mixture model; machine learning; minimal residual disease; multiparameter flow cytometry

PMID:
31282025
DOI:
10.1002/cyto.a.23852

Supplemental Content

Full text links

Icon for Wiley
Loading ...
Support Center