Classification of fetal and adult red blood cells based on hydrodynamic deformation and deep video recognition

Peter Johannes Tejlgaard Kampen; Gustav Ragnar Støttrup-Als; Nicklas Bruun-Andersen; Joachim Secher; Freja Høier; Anne Todsen Hansen; Morten Hanefeld Dziegiel; Anders Nymark Christensen; Kirstine Berg-Sørensen

doi:10.1007/s10544-023-00688-6

Classification of fetal and adult red blood cells based on hydrodynamic deformation and deep video recognition

Peter Johannes Tejlgaard Kampen, Gustav Ragnar Støttrup-Als, Nicklas Bruun-Andersen, Joachim Secher, Freja Høier, Anne Todsen Hansen, Morten Hanefeld Dziegiel, Anders Nymark Christensen, Kirstine Berg-Sørensen^*

^*Corresponding author for this work

Research output: Contribution to journal › Journal article › Research › peer-review

18 Downloads (Pure)

Abstract

Flow based deformation cytometry has shown potential for cell classification. We demonstrate the principle with an injection moulded microfluidic chip from which we capture videos of adult and fetal red blood cells, as they are being deformed in a microfluidic chip. Using a deep neural network - SlowFast - that takes the temporal behavior into account, we are able to discriminate between the cells with high accuracy. The accuracy was larger for adult blood cells than for fetal blood cells. However, no significant difference was observed between donors of the two types.

Original language	English
Article number	5
Journal	Biomedical Microdevices
Volume	26
Issue number	1
Number of pages	9
ISSN	1387-2176
DOIs	https://doi.org/10.1007/s10544-023-00688-6
Publication status	Published - 2024

Bibliographical note

Publisher Copyright:
© 2023, The Author(s).

Keywords

Deformation
Microfluidic flow cytometry
Neural network
Red blood cell
SlowFast

Access to Document

10.1007/s10544-023-00688-6Licence: CC BY

FulltextFinal published version, 1.44 MBLicence: CC BY

Cite this

Classification of fetal and adult red blood cells based on hydrodynamic deformation and deep video recognition. / Kampen, Peter Johannes Tejlgaard; Støttrup-Als, Gustav Ragnar; Bruun-Andersen, Nicklas; Secher, Joachim; Høier, Freja; Hansen, Anne Todsen; Dziegiel, Morten Hanefeld; Christensen, Anders Nymark; Berg-Sørensen, Kirstine.

In: Biomedical Microdevices, Vol. 26, No. 1, 5, 2024.

Research output: Contribution to journal › Journal article › Research › peer-review

Kampen, Peter Johannes Tejlgaard ; Støttrup-Als, Gustav Ragnar ; Bruun-Andersen, Nicklas ; Secher, Joachim ; Høier, Freja ; Hansen, Anne Todsen ; Dziegiel, Morten Hanefeld ; Christensen, Anders Nymark ; Berg-Sørensen, Kirstine. / Classification of fetal and adult red blood cells based on hydrodynamic deformation and deep video recognition. In: Biomedical Microdevices. 2024 ; Vol. 26, No. 1.

@article{0dc85e6517454b66850854b06a605210,

title = "Classification of fetal and adult red blood cells based on hydrodynamic deformation and deep video recognition",

abstract = "Flow based deformation cytometry has shown potential for cell classification. We demonstrate the principle with an injection moulded microfluidic chip from which we capture videos of adult and fetal red blood cells, as they are being deformed in a microfluidic chip. Using a deep neural network - SlowFast - that takes the temporal behavior into account, we are able to discriminate between the cells with high accuracy. The accuracy was larger for adult blood cells than for fetal blood cells. However, no significant difference was observed between donors of the two types.",

keywords = "Deformation, Microfluidic flow cytometry, Neural network, Red blood cell, SlowFast",

author = "Kampen, {Peter Johannes Tejlgaard} and St{\o}ttrup-Als, {Gustav Ragnar} and Nicklas Bruun-Andersen and Joachim Secher and Freja H{\o}ier and Hansen, {Anne Todsen} and Dziegiel, {Morten Hanefeld} and Christensen, {Anders Nymark} and Kirstine Berg-S{\o}rensen",

note = "Publisher Copyright: {\textcopyright} 2023, The Author(s).",

year = "2024",

doi = "10.1007/s10544-023-00688-6",

language = "English",

volume = "26",

journal = "Biomedical Microdevices",

issn = "1387-2176",

publisher = "Springer",

number = "1",

}

TY - JOUR

T1 - Classification of fetal and adult red blood cells based on hydrodynamic deformation and deep video recognition

AU - Kampen, Peter Johannes Tejlgaard

AU - Støttrup-Als, Gustav Ragnar

AU - Bruun-Andersen, Nicklas

AU - Secher, Joachim

AU - Høier, Freja

AU - Hansen, Anne Todsen

AU - Dziegiel, Morten Hanefeld

AU - Christensen, Anders Nymark

AU - Berg-Sørensen, Kirstine

PY - 2024

Y1 - 2024

N2 - Flow based deformation cytometry has shown potential for cell classification. We demonstrate the principle with an injection moulded microfluidic chip from which we capture videos of adult and fetal red blood cells, as they are being deformed in a microfluidic chip. Using a deep neural network - SlowFast - that takes the temporal behavior into account, we are able to discriminate between the cells with high accuracy. The accuracy was larger for adult blood cells than for fetal blood cells. However, no significant difference was observed between donors of the two types.

AB - Flow based deformation cytometry has shown potential for cell classification. We demonstrate the principle with an injection moulded microfluidic chip from which we capture videos of adult and fetal red blood cells, as they are being deformed in a microfluidic chip. Using a deep neural network - SlowFast - that takes the temporal behavior into account, we are able to discriminate between the cells with high accuracy. The accuracy was larger for adult blood cells than for fetal blood cells. However, no significant difference was observed between donors of the two types.

KW - Deformation

KW - Microfluidic flow cytometry

KW - Neural network

KW - Red blood cell

KW - SlowFast

U2 - 10.1007/s10544-023-00688-6

DO - 10.1007/s10544-023-00688-6

M3 - Journal article

C2 - 38095813

AN - SCOPUS:85179627695

VL - 26

JO - Biomedical Microdevices

JF - Biomedical Microdevices

SN - 1387-2176

IS - 1

M1 - 5

ER -