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

Iordania Constantinou,Gilles Charvin,Michael Jendrusch,Théo Aspert,André Schulze,Michael Knop,Frederik Görlitz

doi:10.3390/mi10050311

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.

Highlights

Phenotypic profiling of cell populations is routinely performed in research and diagnostic laboratories using flow cytometry [1,2,3]
We evaluated the suitability of our learned representation for this task of unsupervised classification by using it to distinguish between images of S. cerevisiae and S. pombe cells captured in-flow in our microfluidic devices
We have demonstrated 3D flow focusing in simple microfluidic devices for applications in imaging flow cytometry

Summary

Introduction

Phenotypic profiling of cell populations is routinely performed in research and diagnostic laboratories using flow cytometry [1,2,3]. Flow cytometry provides cellular analysis at an unparalleled throughput and allows for the screening of diverse samples and the isolation of cell subpopulations for further study. Standard applications of flow cytometry employ multi-channel fluorescence detection and sample characterization based on light scattering and fluorescence signal intensity, which provide limited spatial resolution [4]. While imaging flow cytometry gives researchers the opportunity to conduct multiparametric analysis of cell populations based on single-cell images, acquiring high-resolution images at throughputs common in flow cytometry remains challenging. This is primarily due to the difficulty of precisely positioning cells, and the challenges associated with imaging fast moving objects [6]

Objectives

Results

Discussion

Conclusion