Clustering of cell populations in flow cytometry data using a combination of Gaussian mixtures

Reiter, Michael J.; Rota, Paolo; Kleber, Florian; Groeneveld-Krentz, Stefanie; Dworzak, Michael

doi:10.1016/j.patcog.2016.04.004

Cited by 17 publications

(25 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(33) already tackles the problem of postacquisition alignment by incorporating affine transformations into the model (using the simplifying assumption of linearity), however, resulting in a optimization procedure with increased algorithmic costs. Depending on the machine settings, the dynamic range of the data might vary considerably.…”

Section: Discussionmentioning

confidence: 99%

“…However, the higher average precision p and F 1 -score of the new model is mainly due to a better performance on low MRD samples (Fig. (33) required iterative gradient-descent In addition, the proposed approach uses considerably less GMMs (2,5) and is faster by a factor of 70 (0.83 s/sample analysis versus 57.9 s with the previous 10-5-3 GMM solution (33)).…”

Section: Comparison To Established Supervised Approachesmentioning

confidence: 98%

“…In the context of automated FCM analysis, Gaussian Mixture Models (GMMs) have been successfully applied (23,26,(29)(30)(31). There are only a few supervised approaches for automated FCM analysis (30,(32)(33)(34). There are only a few supervised approaches for automated FCM analysis (30,(32)(33)(34).…”

mentioning

confidence: 99%

“…There are only a few supervised approaches for automated FCM analysis (30,(32)(33)(34). More recently, we used a combination of GMMs that were obtained from a labeled training set using non-negative matrix factorization (33). FlowGM (30) forms a GMM from a representative sample, which is manually labeled.…”

mentioning

confidence: 99%

“…Averaged median F 1 -scores (vertical axis) of the composite 10-5-3-GMM method(33), and the proposed method are depicted for the 176 VIE Routine samples tested by both methods and herein ordered by increasing operator-based "true" MRD levels (horizontal axis). Averaged median F 1 -scores (vertical axis) of the composite 10-5-3-GMM method(33), and the proposed method are depicted for the 176 VIE Routine samples tested by both methods and herein ordered by increasing operator-based "true" MRD levels (horizontal axis).…”

mentioning

confidence: 99%

See 4 more Smart Citations

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

Reiter

Diem

Schumich³

et al. 2019

Cytometry Pt A

Self Cite

View full text Add to dashboard Cite

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 readout 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.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Comparison To Established Supervised Approachesmentioning

confidence: 98%

mentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations

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

Reiter

Diem

Schumich³

et al. 2019

Cytometry Pt A

Self Cite

View full text Add to dashboard Cite

show abstract

Current trends in flow cytometry automated data analysis software

et al. 2021

View full text Add to dashboard Cite

Automated flow cytometry (FC) data analysis tools for cell population identification and characterization are increasingly being used in academic, biotechnology, pharmaceutical, and clinical laboratories. The development of these computational methods is designed to overcome reproducibility and process bottleneck issues in manual gating, however, the take‐up of these tools remains (anecdotally) low. Here, we performed a comprehensive literature survey of state‐of‐the‐art computational tools typically published by research, clinical, and biomanufacturing laboratories for automated FC data analysis and identified popular tools based on literature citation counts. Dimensionality reduction methods ranked highly, such as generic t‐distributed stochastic neighbor embedding (t‐SNE) and its initial Matlab‐based implementation for cytometry data viSNE. Software with graphical user interfaces also ranked highly, including PhenoGraph, SPADE1, FlowSOM, and Citrus, with unsupervised learning methods outnumbering supervised learning methods, and algorithm type popularity spread across K‐Means, hierarchical, density‐based, model‐based, and other classes of clustering algorithms. Additionally, to illustrate the actual use typically within clinical spaces alongside frequent citations, a survey issued by UK NEQAS Leucocyte Immunophenotyping to identify software usage trends among clinical laboratories was completed. The survey revealed 53% of laboratories have not yet taken up automated cell population identification methods, though among those that have, Infinicyt software is the most frequently identified. Survey respondents considered data output quality to be the most important factor when using automated FC data analysis software, followed by software speed and level of technical support. This review found differences in software usage between biomedical institutions, with tools for discovery, data exploration, and visualization more popular in academia, whereas automated tools for specialized targeted analysis that apply supervised learning methods were more used in clinical settings.

show abstract