Format

Send to

Choose Destination
Micromachines (Basel). 2019 May 9;10(5). pii: E311. doi: 10.3390/mi10050311.

Self-Learning Microfluidic Platform for Single-Cell Imaging and Classification in Flow.

Constantinou I1,2,3, Jendrusch M4, Aspert T5,6,7,8, Görlitz F9, Schulze A10, Charvin G11,12,13,14, Knop M15,16.

Author information

1
Zentrum für Molekulare Biologie der Universität Heidelberg (ZMBH), DKFZ-ZMBH Alliance, Universität Heidelberg, 69120 Heidelberg, Germany. i.constantinou@tu-braunschweig.de.
2
Institute of Microtechnology, Technische Universität Braunschweig, 38124 Braunschweig, Germany. i.constantinou@tu-braunschweig.de.
3
Center of Pharmaceutical Engineering (PVZ), Technische Universität Braunschweig, 38106 Braunschweig, Germany. i.constantinou@tu-braunschweig.de.
4
Zentrum für Molekulare Biologie der Universität Heidelberg (ZMBH), DKFZ-ZMBH Alliance, Universität Heidelberg, 69120 Heidelberg, Germany. jendrusch@stud.uni-heidelberg.de.
5
Developmental Biology and Stem Cells Department, Institut de Génétique et de Biologie Moléculaire et Cellulaire, 67400 Illkirch-Graffenstaden, France. aspertt@igbmc.fr.
6
Centre National de la Recherche Scientifique, 67400 Illkirch-Graffenstaden, France. aspertt@igbmc.fr.
7
Institut National de la Santé et de la Recherche Médicale, 67400 Illkirch-Graffenstaden, France. aspertt@igbmc.fr.
8
Université de Strasbourg, 67400 Illkirch, France. aspertt@igbmc.fr.
9
Zentrum für Molekulare Biologie der Universität Heidelberg (ZMBH), DKFZ-ZMBH Alliance, Universität Heidelberg, 69120 Heidelberg, Germany. f.goerlitz@gmx.net.
10
Zentrum für Molekulare Biologie der Universität Heidelberg (ZMBH), DKFZ-ZMBH Alliance, Universität Heidelberg, 69120 Heidelberg, Germany. a.schulze@zmbh.uni-heidelberg.de.
11
Developmental Biology and Stem Cells Department, Institut de Génétique et de Biologie Moléculaire et Cellulaire, 67400 Illkirch-Graffenstaden, France. charvin@igbmc.fr.
12
Centre National de la Recherche Scientifique, 67400 Illkirch-Graffenstaden, France. charvin@igbmc.fr.
13
Institut National de la Santé et de la Recherche Médicale, 67400 Illkirch-Graffenstaden, France. charvin@igbmc.fr.
14
Université de Strasbourg, 67400 Illkirch, France. charvin@igbmc.fr.
15
Zentrum für Molekulare Biologie der Universität Heidelberg (ZMBH), DKFZ-ZMBH Alliance, Universität Heidelberg, 69120 Heidelberg, Germany. m.knop@zmbh.uni-heidelberg.de.
16
Cell Morphogenesis and Signal Transduction, German Cancer Research Center (DKFZ), DKFZ-ZMBH Alliance, 69120 Heidelberg, Germany. m.knop@zmbh.uni-heidelberg.de.

Abstract

Single-cell analysis commonly requires the confinement of cell suspensions in an analysis chamber or the precise positioning of single cells in small channels. Hydrodynamic flow focusing has been broadly utilized to achieve stream confinement in microchannels for such applications. As imaging flow cytometry gains popularity, the need for imaging-compatible microfluidic devices that allow for precise confinement of single cells in small volumes becomes increasingly important. At the same time, high-throughput single-cell imaging of cell populations produces vast amounts of complex data, which gives rise to the need for versatile algorithms for image analysis. In this work, we present a microfluidics-based platform for single-cell imaging in-flow and subsequent image analysis using variational autoencoders for unsupervised characterization of cellular mixtures. We use simple and robust Y-shaped microfluidic devices and demonstrate precise 3D particle confinement towards the microscope slide for high-resolution imaging. To demonstrate applicability, we use these devices to confine heterogeneous mixtures of yeast species, brightfield-image them in-flow and demonstrate fully unsupervised, as well as few-shot classification of single-cell images with 88% accuracy.

KEYWORDS:

3D flow focusing; 3D particle focusing; bioMEMS; microfluidics; neural networks; particle/cell imaging; unsupervised learning; variational inference

Supplemental Content

Full text links

Icon for Multidisciplinary Digital Publishing Institute (MDPI) Icon for PubMed Central
Loading ...
Support Center