Application of a deep learning-based image analysis and live-cell imaging system for quantifying adipogenic differentiation kinetics of adipose-derived stem/stromal cells.
Patrick Terrence Brooks, Lea Munthe-Fog, Klaus Rieneck, Frederik Banch Clausen, Olga Ballesteros Rivera, Eva Kannik Haastrup, Anne Fischer-Nielsen, Jesper Dyrendom Svalgaard
{"title":"Application of a deep learning-based image analysis and live-cell imaging system for quantifying adipogenic differentiation kinetics of adipose-derived stem/stromal cells.","authors":"Patrick Terrence Brooks, Lea Munthe-Fog, Klaus Rieneck, Frederik Banch Clausen, Olga Ballesteros Rivera, Eva Kannik Haastrup, Anne Fischer-Nielsen, Jesper Dyrendom Svalgaard","doi":"10.1080/21623945.2021.2000696","DOIUrl":null,"url":null,"abstract":"ABSTRACT Quantitative methods for assessing differentiative potency of adipose-derived stem/stromal cells may lead to improved clinical application of this multipotent stem cell, 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 these assays are time and material consuming. Detection methods for cell characteristics using advanced image analysis by machine learning are emerging. Here, live-cell imaging was combined with a 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. Different detection masks quantified adipose area and lipid droplet formation at different time points indicating kinetics of 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 image data.","PeriodicalId":7226,"journal":{"name":"Adipocyte","volume":null,"pages":null},"PeriodicalIF":3.5000,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8632106/pdf/","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Adipocyte","FirstCategoryId":"99","ListUrlMain":"https://doi.org/10.1080/21623945.2021.2000696","RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENDOCRINOLOGY & METABOLISM","Score":null,"Total":0}
引用次数: 3
Abstract
ABSTRACT Quantitative methods for assessing differentiative potency of adipose-derived stem/stromal cells may lead to improved clinical application of this multipotent stem cell, 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 these assays are time and material consuming. Detection methods for cell characteristics using advanced image analysis by machine learning are emerging. Here, live-cell imaging was combined with a 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. Different detection masks quantified adipose area and lipid droplet formation at different time points indicating kinetics of 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 image data.
期刊介绍:
Adipocyte recognizes that the adipose tissue is the largest endocrine organ in the body, and explores the link between dysfunctional adipose tissue and the growing number of chronic diseases including diabetes, hypertension, cardiovascular disease and cancer. Historically, the primary function of the adipose tissue was limited to energy storage and thermoregulation. However, a plethora of research over the past 3 decades has recognized the dynamic role of the adipose tissue and its contribution to a variety of physiological processes including reproduction, angiogenesis, apoptosis, inflammation, blood pressure, coagulation, fibrinolysis, immunity and general metabolic homeostasis. The field of Adipose Tissue research has grown tremendously, and Adipocyte is the first international peer-reviewed journal of its kind providing a multi-disciplinary forum for research focusing exclusively on all aspects of adipose tissue physiology and pathophysiology. Adipocyte accepts high-profile submissions in basic, translational and clinical research.