@article {pub4502,
	title = {Towards an automatic analysis of CHO-K1 suspension growth in microfluidic single cell 
cultivation},
	author = {Jan Philip Goepfert AND Barbara Hammer},
	year = {2021},
	abstract = {Motivation: Innovative microfluidic systems carry the promise to greatly facilitate spatio-
temporal analysis of single cells under well-defined environmental conditions, allowing novel 
insights into population heterogeneity and opening new opportunities for advanced 
bioprocess development. Microfluidics experiments, however, are accompanied by vast 
amounts of data such as time series of microscopic images, for which manual evaluation is 
infeasible due to its sheer number. While classical image processing technologies do not lead 
to satisfactory results in this domain, modern deep learning technologies such as 
convolutional networks carry great promises for diverse tasks such as  automatic cell 
tracking and counting or an  extraction of relevant parameters such as growth rate. Yet, 
current deep learning technologies require supervised label information such as an 
annotation of images by the number or position of cells for training, which is hard to obtain 
in this setting. 
Results: We propose a novel Machine Learning architecture together with 
a specialized training procedure, which allows us to infuse a deep neural 
network with human-powered abstraction on the level of data, leading to a 
high-performing regression model that requires only a very small amount of labeled 
data. Specifically, we train a generative model simultaneously on natural and 
synthetic data, so that it learns a shared representation, from which a target 
variable such as the cell count can be reliably estimated. 
Availability: The project is cross-platform, open-source and free (MIT 
licensed) software. The source code is available at 
https://github.com/cell\_cultivation\_analysis, the data set is available at https://pub.uni-
bielefeld.de/record/2945513 },
	publisher = {Oxford University Publishing},
	journal = {Bioinformatics},
	volume = {37},
	number = {20},
	pages = {3632{\textendash}3639}
}