Classification of Human White Blood Cells Using Machine Learning for Stain-Free Imaging Flow Cytometry.
Imaging flow cytometry
label-free, stain-free, deep learning, machine learning, classification, white blood cells, leukocytes, eosinophils.
Journal
Cytometry. Part A : the journal of the International Society for Analytical Cytology
ISSN: 1552-4930
Titre abrégé: Cytometry A
Pays: United States
ID NLM: 101235694
Informations de publication
Date de publication:
03 2020
03 2020
Historique:
received:
21
05
2019
revised:
10
09
2019
accepted:
02
10
2019
pubmed:
7
11
2019
medline:
19
8
2021
entrez:
6
11
2019
Statut:
ppublish
Résumé
Imaging flow cytometry (IFC) produces up to 12 spectrally distinct, information-rich images of single cells at a throughput of 5,000 cells per second. Yet often, cell populations are still studied using manual gating, a technique that has several drawbacks, hence it would be advantageous to replace manual gating with an automated process. Ideally, this automated process would be based on stain-free measurements, as the currently used staining techniques are expensive and potentially confounding. These stain-free measurements originate from the brightfield and darkfield image channels, which capture transmitted and scattered light, respectively. To realize this automated, stain-free approach, advanced machine learning (ML) methods are required. Previous works have successfully tested this approach on cell cycle phase classification with both a classical ML approach based on manually engineered features, and a deep learning (DL) approach. In this work, we compare both approaches extensively on the problem of white blood cell classification. Four human whole blood samples were assayed on an ImageStream-X MK II imaging flow cytometer. Two samples were stained for the identification of eight white blood cell types, while two other sample sets were stained for the identification of resting and active eosinophils. For both data sets, four ML classifiers were evaluated on stain-free imagery with stratified 5-fold cross-validation. On the white blood cell data set, the best obtained results were 0.778 and 0.703 balanced accuracy for classical ML and DL, respectively. On the eosinophil data set, this was 0.871 and 0.856 balanced accuracy. We conclude that classifying cell types based on only stain-free images is possible with all four classifiers. Noteworthy, we also find that the DL approaches tested in this work do not outperform the approaches based on manually engineered features. © 2019 International Society for Advancement of Cytometry.
Identifiants
pubmed: 31688997
doi: 10.1002/cyto.a.23920
doi:
Substances chimiques
Coloring Agents
0
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
308-319Subventions
Organisme : Wellcome Trust
Pays : United Kingdom
Informations de copyright
© 2019 International Society for Advancement of Cytometry.
Références
Luminex. Amnis Imaging Flow Cytometers. Austin, TX: Luminex, 2019.
Samsel L, Philip McCoy J. Detection and characterization of rare circulating endothelial cells by imaging flow cytometry. In: Barteneva NS, Vorobjev IA, editors. Imaging Flow Cytometry: Methods and Protocols, Methods in Molecular Biology. New York, NY: Springer New York, 2016; p. 249-264.
Rodrigues MA. Automation of the in vitro micronucleus assay using the Imagestream R imaging flow cytometer. Cytometry A 2018;93(7):706-726.
Thaunat O, Granja AG, Barral P, Filby A, Montaner B, Collinson L, MartinezMartin N, Harwood NE, Bruckbauer A, Batista FD. Asymmetric segregation of polarized antigen on B cell division shapes presentation capacity. Science 2012;335(6067):475-479.
Filby A, Perucha E, Summers H, Rees P, Chana P, Heck S, Lord GM, Davies D. An imaging flow cytometric method for measuring cell division history and molecular symmetry during mitosis. Cytometry A 2011;79A(7):496-506.
Hawkins ED, Oliaro J, Axel Kallies GT, Belz AF, Hogan T, Haynes N, Ramsbottom KM, Van Ham V, Kinwell T, Seddon B, et al. Regulation of asymmetric cell division and polarity by scribble is not required for humoral immunity. Nat Commun 2013;4(1801).
Doan M, Vorobjev I, Rees P, Filby A, Wolkenhauer O, Goldfeld AE, Lieberman J, Barteneva N, Carpenter AE, Hennig H. Diagnostic potential of imaging flow cytometry. Trends Biotechnol 2018;36(7):649-652.
Saeys Y, Van Gassen S, Lambrecht BN. Computational flow cytometry: Helping to make sense of high-dimensional immunology data. Nat Rev Immunol 2016;16(7):449-462.
Filby A, Davies D. Reporting imaging flow cytometry data for publication: Why mask the detail? Cytometry A 2012;81A(8):637-642.
Wojcik K, WDobrucki J. Interaction of a DNA intercalator DRAQ5, and a minor groove binder SYTO17, with chromatin in live cells-influence on chromatin organization and histone-DNA interactions. Cytometry 2008;73(6):555-562.
Chen AY, Yu C, Gatto B, Liu LF. DNA minor groove-binding ligands: A different class of mammalian DNA topoisomerase I inhibitors. Proc Natl Acad Sci 1993;90(17):8131-8135.
Miltenburger HG, Sachse G, Schliermann M. S-phase cell detection with a monoclonal antibody. Dev Biol Stand 1987;66:91-99.
Freudiger CW, Min W, Saar BG, Lu S, Holtom GR, He C, Tsai JC, Kang JX, Xie XS. Label-free biomedical imaging with high sensitivity by stimulated Raman scattering microscopy. Science 2008;322(5909):1857-1861.
Wang S, Shan X, Patel U, Huang X, Lu J, Li J, Tao N. Label-free imaging, detection, and mass measurement of single viruses by surface plasmon resonance. Proc Natl Acad Sci 2010;107(37):16028-16032.
de Wit G, Danial JSH, Kukura P, Wallace MI. Dynamic label-free imaging of lipid nanodomains. Proc Natl Acad Sci 2015;112(40):12299-12303.
Hennig H, Rees P, Blasi T, Kamentsky L, Hung J, Dao D, Carpenter AE, Filby A. An open-source solution for advanced imaging flow cytometry data analysis using machine learning. Methods (San Diego, Calif) 2017;112:201-210.
Kamentsky L, Jones TR, Fraser A, Bray M-A, Logan DJ, Madden KL, Ljosa V, Rueden C, Eliceiri KW, Carpenter AE. Improved structure, function and compatibility for CellProfiler: Modular high-throughput image analysis software. Bioinformatics 2011;27(8):1179-1180.
Gupta A, Harrison PJ, Wieslander H, Pielawski N, Kartasalo K, Partel G, Solorzano L, Suveer A, Klemm AH, Spjuth O, et al. Deep learning in image cytometry: A review. Cytometry A 2018;95:366-380.
Frew AJ, Kay AB. The relationship between infiltrating CD4+ lymphocytes, activated eosinophils, and the magnitude of the allergen-induced late phase cutaneous reaction in man. J Immunol 1988;141(12):4158-4164.
Bentley AM, Menz G, Storz C, Robinson DS, Bradley B, Jeffery PK, Durham SR, Kay AB. Identification of T lymphocytes, macrophages, and activated eosinophils in the bronchial mucosa in intrinsic asthma: Relationship to symptoms and bronchial responsiveness. Am Rev Respir Dis 1992;146(2):500-506.
Amnis. INSPIRE - ImageStream-X MKII User Manual. Seattle, WA: Amnis, 2017.
Krizhevsky A, Sutskever I. And Geoffrey E Hinton. ImageNet classification with deep convolutional neural networks. In: Pereira F, Burges CJC, Bottou L, Weinberger KQ, editors. Advances in Neural Information Processing Systems. Volume 25. Red Hook: Curran Associates, Inc, 2012; p. 1097-1105.
He K, Zhang X, Ren S, and Sun J. Deep residual learning for image recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE: Las Vegas, NV. 2016, pp 770-778.
Rezvantalab A, Safigholi H, and Karimijeshni S. Dermatologist level dermoscopy skin cancer classification using different deep learning convolutional neural networks algorithms. arXiv: 1810.10348 [cs], Stat], October 2018.
Breiman L. Random forests. Mach Learn 2001;45(1):5-32.
Friedman JH. Stochastic gradient boosting. Comput Stat Data Anal 2002;38(4):367-378.
Díaz-Uriarte R, de Andrés SA. Gene selection and classification of microarray data using random forest. BMC Bioinformatics 2006;7(1):3.
Pal M. Random forest classifier for remote sensing classification. Int J Remote Sens 2005;26(1):217-222.
Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, et al. Scikit-learn: Machine learning in Python. J Mach Learn Res 2011;12(Oct):2825-2830.
Eulenberg P, Köhler N, Blasi T, Filby A, Carpenter AE, Rees P, Theis FJ, Wolf FA. Reconstructing cell cycle and disease progression using deep learning. Nat Commun 2017;8(1).
Szegedy C, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A. Going deeper with convolutions. In 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015pp 1-9.
Kingma DP, Ba J. Adam: A method for stochastic optimization. arXiv:1412.6980 [cs], December 2014.
Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L. Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. Attention is all you need. In: Guyon I, Luxburg UV, Bengio S, Wallach H, Fergus R, Vishwanathan S, Garnett R, editors. Advances in Neural Information Processing Systems. Volume 30. Red Hook: Curran Associates, Inc, 2017; p. 5998-6008.
Popel M, Bojar O. Training tips for the transformer model. Prague Bull Math Linguist 2018;110(1):43-70.
Martın Abadi, Ashish Agarwal, Paul Barham, Eugene Brevdo, Zhifeng Chen, Craig Citro, Greg S. Corrado, Andy Davis, Jeffrey Dean, Matthieu Devin et al. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. Technical Report, 2015. Software available from tensorflow.org.
Amnis. IDEAS-Image Data Exploration and Analysis Software, November 2015.
Kamentsky L. Python Bio-Formats (version 1.5.2). Python. Broad Institute, 2019.
Japkowicz N, Stephen S. The class imbalance problem: A systematic study. Intell Data Anal 2002;6(5):429.
Pereira S, Pinto A, Alves V, Silva CA. Brain tumor segmentation using convolutional neural networks in MRI images. IEEE Trans Med Imaging 2016;35(5):1240-1251.
K. H. Brodersen, C. S. Ong, K. E. Stephan, and J. M. Buhmann. The balanced accuracy and its posterior distribution. In 2010 20th International Conference on Pattern Recognition, Pages 3121-3124, August 2010.
McInnes L, John H. UMAP: Uniform manifold approximation and projection for dimension reduction. arXiv:180203426 [cs, stat], February 2018.
Meng N, Lam E, Tsia KKM, So HK. Large-scale multi-class image-based cell classification with deep learning. IEEE J Biomed Health Inform 2019:2091-2098.
Blasi T, Hennig H, Summers HD, Theis FJ, Cerveira J, Patterson JO, Davies D, Filby A, Carpenter AE, Rees P. Label-free cell cycle analysis for high-throughput imaging flow cytometry. Nat Commun 2016;7:10256.
Angermueller C, Pärnamaa T, Parts L, Stegle O. Deep learning for computational biology. Mol Syst Biol 2016;12(7):878.
Ching T, Himmelstein DS, Beaulieu-Jones BK, Kalinin AA, Do BT, Way GP, Ferrero E, Agapow P-M, Zietz M, Hoffman MM, et al. Opportunities and obstacles for deep learning in biology and medicine. J R Soc Interface 2018;15(141).