Advanced search
1 file | 2.07 MB Add to list

Machine learning issues and opportunities in ultrafast particle classification for label-free microflow cytometry

Alessio Lugnan (UGent) , Emmanuel Gooskens (UGent) , Jeremy Vatin, Joni Dambre (UGent) and Peter Bienstman (UGent)
Author
Organization
Project
Abstract
Machine learning offers promising solutions for high-throughput single-particle analysis in label-free imaging microflow cytomtery. However, the throughput of online operations such as cell sorting is often limited by the large computational cost of the image analysis while offline operations may require the storage of an exceedingly large amount of data. Moreover, the training of machine learning systems can be easily biased by slight drifts of the measurement conditions, giving rise to a significant but difficult to detect degradation of the learned operations. We propose a simple and versatile machine learning approach to perform microparticle classification at an extremely low computational cost, showing good generalization over large variations in particle position. We present proof-of-principle classification of interference patterns projected by flowing transparent PMMA microbeads with diameters of 15.2 mu m and 18.6 mu m. To this end, a simple, cheap and compact label-free microflow cytometer is employed. We also discuss in detail the detection and prevention of machine learning bias in training and testing due to slight drifts of the measurement conditions. Moreover, we investigate the implications of modifying the projected particle pattern by means of a diffraction grating, in the context of optical extreme learning machine implementations.
Keywords
FLOW-CYTOMETRY

Downloads

  • pub 2602.pdf
    • full text (Published version)
    • |
    • open access
    • |
    • PDF
    • |
    • 2.07 MB

Citation

Please use this url to cite or link to this publication:

MLA
Lugnan, Alessio, et al. “Machine Learning Issues and Opportunities in Ultrafast Particle Classification for Label-Free Microflow Cytometry.” SCIENTIFIC REPORTS, vol. 10, no. 1, 2020, doi:10.1038/s41598-020-77765-w.
APA
Lugnan, A., Gooskens, E., Vatin, J., Dambre, J., & Bienstman, P. (2020). Machine learning issues and opportunities in ultrafast particle classification for label-free microflow cytometry. SCIENTIFIC REPORTS, 10(1). https://doi.org/10.1038/s41598-020-77765-w
Chicago author-date
Lugnan, Alessio, Emmanuel Gooskens, Jeremy Vatin, Joni Dambre, and Peter Bienstman. 2020. “Machine Learning Issues and Opportunities in Ultrafast Particle Classification for Label-Free Microflow Cytometry.” SCIENTIFIC REPORTS 10 (1). https://doi.org/10.1038/s41598-020-77765-w.
Chicago author-date (all authors)
Lugnan, Alessio, Emmanuel Gooskens, Jeremy Vatin, Joni Dambre, and Peter Bienstman. 2020. “Machine Learning Issues and Opportunities in Ultrafast Particle Classification for Label-Free Microflow Cytometry.” SCIENTIFIC REPORTS 10 (1). doi:10.1038/s41598-020-77765-w.
Vancouver
1.
Lugnan A, Gooskens E, Vatin J, Dambre J, Bienstman P. Machine learning issues and opportunities in ultrafast particle classification for label-free microflow cytometry. SCIENTIFIC REPORTS. 2020;10(1).
IEEE
[1]
A. Lugnan, E. Gooskens, J. Vatin, J. Dambre, and P. Bienstman, “Machine learning issues and opportunities in ultrafast particle classification for label-free microflow cytometry,” SCIENTIFIC REPORTS, vol. 10, no. 1, 2020.
@article{8692736,
  abstract     = {{Machine learning offers promising solutions for high-throughput single-particle analysis in label-free imaging microflow cytomtery. However, the throughput of online operations such as cell sorting is often limited by the large computational cost of the image analysis while offline operations may require the storage of an exceedingly large amount of data. Moreover, the training of machine learning systems can be easily biased by slight drifts of the measurement conditions, giving rise to a significant but difficult to detect degradation of the learned operations. We propose a simple and versatile machine learning approach to perform microparticle classification at an extremely low computational cost, showing good generalization over large variations in particle position. We present proof-of-principle classification of interference patterns projected by flowing transparent PMMA microbeads with diameters of 15.2 mu m and 18.6 mu m. To this end, a simple, cheap and compact label-free microflow cytometer is employed. We also discuss in detail the detection and prevention of machine learning bias in training and testing due to slight drifts of the measurement conditions. Moreover, we investigate the implications of modifying the projected particle pattern by means of a diffraction grating, in the context of optical extreme learning machine implementations.}},
  articleno    = {{20724}},
  author       = {{Lugnan, Alessio and Gooskens, Emmanuel and Vatin, Jeremy and Dambre, Joni and Bienstman, Peter}},
  issn         = {{2045-2322}},
  journal      = {{SCIENTIFIC REPORTS}},
  keywords     = {{FLOW-CYTOMETRY}},
  language     = {{eng}},
  number       = {{1}},
  pages        = {{13}},
  title        = {{Machine learning issues and opportunities in ultrafast particle classification for label-free microflow cytometry}},
  url          = {{http://dx.doi.org/10.1038/s41598-020-77765-w}},
  volume       = {{10}},
  year         = {{2020}},
}

Altmetric
View in Altmetric
Web of Science
Times cited: