EAP4EMSIG -- Enhancing Event-Driven Microscopy for Microfluidic Single-Cell Analysis
This work addresses real-time analysis delays in microfluidic single-cell experiments, offering incremental improvements in automation and segmentation for microbial cell factory research.
The paper tackled the challenge of real-time insights in microfluidic live-cell imaging by introducing an experiment automation pipeline with an MLP-based autofocusing method achieving a MAE of 0.105 μm and inference times from 87 ms, and evaluated segmentation methods like Cellpose reaching a PQ of 93.36%.
Microfluidic Live-Cell Imaging (MLCI) yields data on microbial cell factories. However, continuous acquisition is challenging as high-throughput experiments often lack real-time insights, delaying responses to stochastic events. We introduce three components in the Experiment Automation Pipeline for Event-Driven Microscopy to Smart Microfluidic Single-Cell Analysis (EAP4EMSIG): a fast, accurate Multi-Layer Perceptron (MLP)-based autofocusing method predicting the focus offset, an evaluation of real-time segmentation methods and a real-time data analysis dashboard. Our MLP-based autofocusing achieves a Mean Absolute Error (MAE) of 0.105 $μ$m with inference times from 87 ms. Among eleven evaluated Deep Learning (DL) segmentation methods, Cellpose reached a Panoptic Quality (PQ) of 93.36 %, while a distance-based method was fastest (121 ms, Panoptic Quality 93.02 %).