Application of a deep learning-based image analysis and live-cell imaging system for quantifying adipogenic differentiation kinetics of adipose-derived stem/stromal cells.

Researchers

Journal

Modalities

Models

Abstract

Quantitative methods for assessing the differentiative potency of adipose-derived stem/stromal cells may lead to improved clinical application for this multipotent stem cell type, by advancing our understanding of specific processes such as adipogenic differentiation. Conventional cell staining methods are used to determine the formation of adipose areas during adipogenesis as a qualitative representation of adipogenic potency. Staining methods such as oil-red-O are quantifiable using absorbance measurements, but the steps included in these assays are time and material consuming. Detection methods for cell characteristics using advanced image analysis by machine learning are emerging. In this study, live-cell imaging was combined with an easy-to-implement deep learning-based detection tool to quantify the presence of adipose areas and lipid droplet formation during adipogenic differentiation of adipose-derived stem/stromal cells. Detection masks were able to detect adipose area and lipid droplet formation, and detection at different time points indicated kinetics during adipogenesis and showed differences between individual donors. Whereas CEBPA and PPARG expression seems to precede the increase in adipose area and lipid droplets, it might be able to predict expression of ADIPOQ. The applied method is a proof of concept, demonstrating that deep learning methods can be used to investigate adipogenic differentiation and kinetics in vitro using specific detection masks based on algorithm produced from annotation of a moderate amount of image data.