Available online 5 March 2023
Author links open overlay panel, , , AbstractThere are many research studies and emerging tools using artificial intelligence (AI) and machine learning to augment flow and mass cytometry workflows. Emerging AI tools can quickly identify common cell populations with continuous improvement of accuracy, uncover patterns in high-dimensional cytometric data that are undetectable by human analysis, facilitate the discovery of cell subpopulations, perform semi-automated immune cell profiling, and demonstrate potential to automate aspects of clinical multiparameter flow cytometric (MFC) diagnostic workflow. Utilizing AI in the analysis of cytometry samples can reduce subjective variability and assist in breakthroughs in understanding diseases.
Here we review the diverse types of AI that are being applied to clinical cytometry data and how AI is driving advances in data analysis to improve diagnostic sensitivity and accuracy. We review supervised and unsupervised clustering algorithms for cell population identification, various dimensionality reduction techniques, and their utilities in visualization and machine learning pipelines, and supervised learning approaches for classifying entire cytometry samples.Understanding the AI landscape will enable pathologists to better utilize open source and commercially available tools, plan exploratory research projects to characterize diseases, and work with machine learning and data scientists to implement clinical data analysis pipelines.
Section snippetsBackgroundThe World Health Organization's classification of hematopoietic and lymphoid tissue recognizes lineage assignment by immunophenotyping as essential in establishing and subcategorizing hematolymphoid malignancies. Multiparameter flow cytometry (MFC) is a major contributor to establishing immunophenotypes of cell populations. Traditionally, processing and staining of samples for flow cytometry and analysis of flow cytometric data have been labor-intensive processes that require highly trained
Companies using machine learning for clinical cytometryAs we continue to delve deeper into the nuances of the immune system, increasing computational power, dataset sizes, and advanced tuned reagents and instruments can help with disease insights, precision medicine, drug discovery, and disease monitoring. Below are four biotechnology startups that are driving forward the capabilities in clinical cytometry research studies and routine immune profiling and monitoring.
DiscussionFor MFC and mass cytometry, the number of supervised approaches has historically lagged unsupervised approaches but is beginning to see an uptick especially at the sample level. Cheung et al. provided a detailed account in 2020 of supervised and unsupervised algorithms for MFC data analysis, including if the algorithms were implemented inside of a GUI, and whether they were accessible for free or through a paid platform95. While unsupervised approaches can be conceptualized and immediately
References (98)C. AngelettiA method for the interpretation of flow cytometry data using genetic algorithmsJ Pathol Inform
(2018)
M. ZhaoHematologist-level classification of mature B-Cell neoplasm using deep learning on multiparameter flow cytometry dataCytometry A
(2020)
N. AghaeepourCritical assessment of automated flow cytometry data analysis techniquesNat Methods
(2013)
D.P. Ng et al.Augmented human intelligence and automated diagnosis in flow cytometry for hematologic malignanciesAm J Clin Pathol
(2021)
Hastie, T., Tibshirani, R. & Friedman, J. The elements of statistical learning – data mining, inference, and...I. Goodfellow et al.Deep learning(2016)
K. O'Neill et al.Flow cytometry bioinformaticsPLoS Comput Biol
(2013)
Liang, S. & Srikant, R. Why deep neural networks for function approximation? Preprint at...J. CampDeep neural network for cell type differentiation in myelodysplastic syndrome diagnosis performs similarly when trained on compensated or uncompensated data(2022)
Transformation of multicolour flow cytometry data with OTflow prevents misleading multivariate analysis results and...Ellis, B. et al. flowCore: flowCore: Basic structures for flow cytometry data. (2022)...N. GopalakrishnanPackage ‘flowUtils’Cytom Part J Int Soc Anal Cytol
(2008)
F. HahnePer-channel basis normalization methods for flow cytometry dataCytometry A
(2010)
G. MonacoflowAI: automatic and interactive anomaly discerning tools for flow cytometry dataBioinformatics
(2016)
K. Fletez-Brant et al.flowClean: Automated identification and removal of fluorescence anomalies in flow cytometry dataCytometry A
(2016)
D. Sarkar et al.Using flowViz to visualize flow cytometry dataBioinformatics
(2008)
Jiang, M. ggcyto: Visualize Cytometry data with ggplot. (2022)...S. Wang et al.Data-driven flow cytometry analysisMethods Mol Biol Clifton NJ
(2019)
S. Montante et al.Flow cytometry data analysis: Recent tools and algorithmsInt J Lab Hematol
(2019)
R.F. MurphyAutomated identification of subpopulations in flow cytometric list mode data using cluster analysisCytometry
(1985)
K. Lo et al.flowClust: a Bioconductor package for automated gating of flow cytometry dataBMC Bioinformatics
(2009)
G. Finak et al.Merging mixture components for cell population identification in flow cytometryAdv Bioinforma
(2009)
S. PyneAutomated high-dimensional flow cytometric data analysisProc Natl Acad Sci
(2009)
T. Sörensen et al.immunoClust—An automated analysis pipeline for the identification of immunophenotypic signatures in high-dimensional cytometric datasetsCytometry A
(2015)
M. Dundar et al.A non-parametric Bayesian model for joint cell clustering and cluster matching: identification of anomalous sample phenotypes with random effectsBMC Bioinformatics
(2014)
I. NaimSWIFT—scalable clustering for automated identification of rare cell populations in large, high-dimensional flow cytometry datasets, Part 1: Algorithm designCytometry A
(2014)
T.R. MosmannSWIFT—scalable clustering for automated identification of rare cell populations in large, high-dimensional flow cytometry datasets, Part 2: Biological evaluationCytometry A
(2014)
K. Johnsson et al.BayesFlow: latent modeling of flow cytometry cell populationsBMC Bioinformatics
(2016)
Aghaeepour, N. flowMeans: Non-parametric flow cytometry data gating....S Van GassenFlowSOM: Using self-organizing maps for visualization and interpretation of cytometry data: FlowSOMCytometry A
(2015)
K. QuintelierAnalyzing high-dimensional cytometry data using FlowSOMNat Protoc
(2021)
Linderman, M. & Bruggner, R. Rclusterapp: Linkable C++ clustering....P. QiuExtracting a cellular hierarchy from high-dimensional cytometry data with SPADENat Biotechnol
(2011)
M. PagniDensity-based hierarchical clustering of pyro-sequences on a large scale–the case of fungal ITS1Bioinformatics
(2013)
P. BaumgaertnerUnsupervised Analysis of Flow Cytometry Data in a Clinical Setting Captures Cell Diversity and Allows Population DiscoveryFront Immunol
(2021)
H. Zare et al.Data reduction for spectral clustering to analyze high throughput flow cytometry dataBMC Bioinformatics
(2010)
Y. QianElucidation 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 dataCytometry B Clin Cytom
(2010)
Y. Ge et al.flowPeaks: a fast unsupervised clustering for flow cytometry data via K-means and density peak findingBioinformatics
(2012)
N. Samusik et al.Automated mapping of phenotype space with single-cell dataNat Methods
(2016)
View full text© 2023 Elsevier Inc. All rights reserved.
留言 (0)