Skip to main content

ORIGINAL RESEARCH article

Front. Bioeng. Biotechnol.
Sec. Synthetic Biology
Volume 12 - 2024 | doi: 10.3389/fbioe.2024.1468738
This article is part of the Research Topic Recent advancements in microfluidic droplet platform for high-throughput single-cell analysis View all articles

Deep learning enabled label-free microfluidic droplet classification for single cell functional assays Authors

Provisionally accepted
Thibault Vanhoucke Thibault Vanhoucke 1,2Angga Perima Angga Perima 1Lorenzo Zolfanelli Lorenzo Zolfanelli 1,3Pierre Bruhns Pierre Bruhns 1,4*Matteo Broketa Matteo Broketa 1,2,5
  • 1 Institut Pasteur, Paris, France
  • 2 Sorbonne Universités, Paris, France
  • 3 École Supérieure de Physique et de Chimie Industrielles de la Ville de Paris, Paris, France
  • 4 Université Paris-Est Créteil Val de Marne, Créteil, Ile-de-France, France
  • 5 Evexta Bio, Paris, France

The final, formatted version of the article will be published soon.

    Droplet-based microfluidics techniques coupled to microscopy allow for the characterization of cells at the single-cell scale. However, such techniques generate substantial amounts of data and microscopy images that must be analyzed. Droplets on these images usually need to be classified depending on the number of cells they contain. This verification, when visually carried out by the experimenter image-per-image, is time-consuming and impractical for analysis of many assays or when an assay yields many putative droplets of interest. Machine learning models have already been developed to classify cell-containing droplets within microscopy images, but not in the context of assays in which non-cellular structures are present inside the droplet in addition to cells. Here we develop a deep learning model using the neural network ResNet-50 that can be applied to functional droplet-based microfluidic assays to classify droplets according to the number of cells they contain with >90% accuracy in a very short time.This model performs high accuracy classification of droplets containing both cells with noncellular structures and cells alone and can accommodate several different cell types, for generalization to a broader array of droplet-based microfluidics applications.

    Keywords: Droplet-based microfluidic, convolutional neural network, image classification, machine learning, Image preprocessing, Resnet 50

    Received: 22 Jul 2024; Accepted: 30 Aug 2024.

    Copyright: © 2024 Vanhoucke, Perima, Zolfanelli, Bruhns and Broketa. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Pierre Bruhns, Institut Pasteur, Paris, France

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.