Multi‐Object Detector YOLOv4‐Tiny Enables High‐Throughput Combinatorial and Spatially‐Resolved Sorting of Cells in Microdroplets

Abstract

The encapsulation of cells together with micro‐objects in monodispersed water‐in‐oil microdroplets offers a powerful means to perform quantitative biological studies within large cell populations. In such applications, accurate object detection is crucial to ensure control over the content for every compartment. In particular, the ability to rapidly count and localize objects is key to future applications in single‐cell ‐omics, cellular aggregation, and cell‐to‐cell interactions. In this paper, the authors combine the Deep Learning object detector YOLOv4‐tiny with microfluidic Image‐Activated Droplet Sorting (DL‐IADS), to perform flexible, label‐free classification, counting, and localization of multiple micro‐objects simultaneously and at high‐throughput. They trained YOLOv4‐tiny to detect SH‐SY5Y cells, polyacrylamide beads, and cellular aggregates in a single model, with a precision of 92% for cells, 98% for beads, and 81% for aggregates. They exploit this accuracy and counting ability to implement a closed‐loop feedback that enables controlled loading of microbeads via the automated adjustment of flow rates. They subsequently demonstrate the combinatorial sorting of co‐encapsulated single cells and single beads based on real‐time classification at up to 111 Hz, with enrichment factors of up to 145. Finally, they demonstrate spatially‐resolved sorts by evaluating cell‐to‐cell distances in real‐time to isolate cell doublets with high purity.

Deep learning detector for high precision monitoring of cell encapsulation statistics in microfluidic droplets

“…† A high precision was reached for all classes in both droplet and cell models. Specifically, a precision of 98% was realized from the cell model for both YOLOv3 and YOLOv5, 6% higher than previously reported single cell detection and 17% higher than cell aggregates in Howell et al 35 Our method can detect every cell in the droplet, allowing for cell aggregation events to be realized with distance analysis. Thus, both models together can not only detect the droplet itself containing different number of cells but a single cell or cell aggregates with high precision.…”

“…For example, Howell et al used YOLOv4-tiny to detect cells, beads, and cell doublets in microfluidic droplets and performed ML-assisted sorting. 34,35 The present work follows closely the studies in the second group that involve cell encapsulation. Rather than training a model on single droplets, here, we increase the throughput of detection by training the model on a collection of droplets present in the expansion chamber of the microfluidic device.…”

“…For example, Howell et al used YOLOv4-tiny to detect cells, beads, and cell doublets in microfluidic droplets and performed ML-assisted sorting. 34,35…”

Phenotyping single-cell motility in microfluidic confinement

“…Contrary to traditional assays that use flow channels to deliver concentration gradients, our design applies real-time control and localised perturbations to single microbes. Further developments and extensions are on the way, including augmentation of on-demand single cell encapsulation with active cell sorting ( Anagnostidis et al, 2020 ; Howell et al, 2022 ). The integration of lab-on-chip technologies, high-speed microscopy and computer vision has significant potential for reconstructing the species-specific sensorimotor pathways of microorganisms, and revealing their response thresholds to dynamic environmental perturbations.…”

Functions and applications of artificial intelligence in droplet microfluidics

“…5a). 135 In addition to characterizing cell morphology, AI-assisted droplet sorting also allows the detection of single-cell secretions, which is unachievable by other continuous-flow methods due to cross-contamination. For instance, a CNN model was developed to identify the extracellular acidification induced by circulating tumor cells (CTCs).…”