Abstract

Early, high-throughput, and accurate recognition of osteogenic differentiation of stem cells is urgently required in stem cell therapy, tissue engineering, and regenerative medicine. In this study, we established an automatic deep learning algorithm, i.e., osteogenic convolutional neural network (OCNN), to quantitatively measure the osteogenic differentiation of rat bone marrow mesenchymal stem cells (rBMSCs). rBMSCs stained with F-actin and DAPI during early differentiation (day 0, 1, 4, and 7) were captured using laser confocal scanning microscopy to train OCNN. As a result, OCNN successfully distinguished differentiated cells at a very early stage (24 h) with a high area under the curve (AUC) (0.94 ± 0.04) and correlated with conventional biochemical markers. Meanwhile, OCNN exhibited better prediction performance compared with the single morphological parameters and support vector machine. Furthermore, OCNN successfully predicted the dose-dependent effects of small-molecule osteogenic drugs and a cytokine. OCNN-based online learning models can further recognize the osteogenic differentiation of rBMSCs cultured on several material surfaces. Hence, this study initially demonstrated the foreground of OCNN in osteogenic drug and biomaterial screening for next-generation tissue engineering and stem cell research.

Highlights

  • BMSCs are the most frequently used subtype of stem cells with a vigorous proliferative and differential capacity, making them a promising tool in tissue engineering, biomedicine, biomaterials, and many other fields (Mauney et al, 2005; Guan et al, 2012; Chiu et al, 2014; Yang et al, 2017; Farokhi et al, 2018; Qi et al, 2020)

  • To investigate the morphological changes of the rat bone marrow mesenchymal stem cells (rBMSCs) during the early stages of osteogenic differentiation, we collected the rBMSCs cultured in osteogenic (OS) and basal (BA) mediums and took laser scanning confocal microscope (LSCM) images on days 0, 1, 4, and 7

  • By depositing 25 objective morphological parameters into two-dimensional t-SNE (Van der Maaten et al, 2008), we found a clear left-toright shift of group OS starting from day 1, while group BA exhibited a more randomized distribution, which partially overlapped with the OS group

Read more

Summary

Introduction

BMSCs are the most frequently used subtype of stem cells with a vigorous proliferative and differential capacity, making them a promising tool in tissue engineering, biomedicine, biomaterials, and many other fields (Mauney et al, 2005; Guan et al, 2012; Chiu et al, 2014; Yang et al, 2017; Farokhi et al, 2018; Qi et al, 2020). Assessing the osteogenic differentiation of BMSCs is of great importance for these applications, but is challenging because of the timeconsuming process and low temporal-spatial resolution of conventional methods. An accurate, early-stage, and single-cell resolution method is urgently required to assess the osteogenic differentiation of BMSCs for next-generation biomedical applications. The direct modulation of cellular adhesive areas and cytoskeletal texture substantially influence osteogenic differentiation (McBeath et al, 2004; Engler et al, 2006; Zhang et al, 2015). The cellular morphology of BMSCs provides invaluable information for osteogenic differentiation prediction (Thomas et al, 2002; Marklein et al, 2016)

Methods
Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call