EMSIG - Event driven Microscopy for Smart mIcrofluidic sinGle-cell analysis
Microfluidic live-cell analysis provides bio(techno)logists with unique insights into growth diversity and population heterogeneity of single microbial cell factories. Recently developed deep-learning based image analysis methods and tools from the SATOMI project provide powerful tools for an off-line analysis of high-quality data. In contrast to flow cytometry, which has majored as a convenient single-cell screening tool, microfluidic live-cell technology is facing challenges in acquiring high-quality data sets over days and weeks.
The EMSIG project aims to bring unsupervised event detection (ED) capabilities to microfluidic live-cell analysis, being able to detect predefined event triggers from live-cell microscopy data, classifying these triggers in event types and connect the results with a computerized control of the microscopic imaging components. This will allow to live-detect not only, for instance, gradually deteriorating imaging quality, but also biological events of interest.
In a first phase, we will realize ED in a human assistance system, while in the second phase, automated control will be implemented to autonomously counter image quality deterioration and to focus on specific biological events in an increased spatio-temporal resolution.
The distinct high-risk factor of the second phase is in the robust and accurate classification of the event triggers at the interface between imaging and stochastic biological components, where, if successful, we expect high-returns by boosting information gain per experimental time, enabling completely new insights to characterize fast processes, increasing the level of live-cell automation, as well as raising the Technology Readiness Level (TRL) of microfluidic live-cell microscopy.
Katharina Nöh, Forschungszentrum Jülich, IBG‐1: Biotechnology
Dietrich Kohlheyer, Forschungszentrum Jülich, IBG‐1: Biotechnology
Ralf Mikut, Karlsruhe Institute of Technology (KIT), Institute for Automation and Applied Informatics (IAI)