Evaluating Differentiation Status of Mesenchymal Stem Cells by Label-Free Microscopy System and Machine Learning

Yawei Kong; Jianpeng Ao; Qiushu Chen; Wenhua Su; Yinping Zhao; Yiyan Fei; Jiong Ma; Minbiao Ji; Lan Mi

doi:10.3390/cells12111524

Evaluating Differentiation Status of Mesenchymal Stem Cells by Label-Free Microscopy System and Machine Learning

Cells. 2023 May 31;12(11):1524. doi: 10.3390/cells12111524.

Authors

Yawei Kong¹, Jianpeng Ao², Qiushu Chen¹, Wenhua Su¹, Yinping Zhao³, Yiyan Fei¹, Jiong Ma^{1

4

5}, Minbiao Ji², Lan Mi^{1

4}

Affiliations

¹ Key Laboratory of Micro and Nano Photonic Structures (Ministry of Education), Department of Optical Science and Engineering, Shanghai Engineering Research Center of Ultra-Precision Optical Manufacturing, School of Information Science and Technology, Fudan University, Shanghai 200433, China.
² Department of Physics, Fudan University, Shanghai 200433, China.
³ Human Phenome Institute, Fudan University, Shanghai 200433, China.
⁴ Institute of Biomedical Engineering and Technology, Academy for Engineering and Technology, Fudan University, Shanghai 200433, China.
⁵ Shanghai Engineering Research Center of Industrial Microorganisms, The Multiscale Research Institute of Complex Systems (MRICS), School of Life Sciences, Fudan University, Shanghai 200433, China.

Abstract

Mesenchymal stem cells (MSCs) play a crucial role in tissue engineering, as their differentiation status directly affects the quality of the final cultured tissue, which is critical to the success of transplantation therapy. Furthermore, the precise control of MSC differentiation is essential for stem cell therapy in clinical settings, as low-purity stem cells can lead to tumorigenic problems. Therefore, to address the heterogeneity of MSCs during their differentiation into adipogenic or osteogenic lineages, numerous label-free microscopic images were acquired using fluorescence lifetime imaging microscopy (FLIM) and stimulated Raman scattering (SRS), and an automated evaluation model for the differentiation status of MSCs was built based on the K-means machine learning algorithm. The model is capable of highly sensitive analysis of individual cell differentiation status, so it has great potential for stem cell differentiation research.

Keywords: FLIM; MSCs; SRS; label-free; machine learning.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Adipogenesis*
Cell Differentiation
Mesenchymal Stem Cells*
Microscopy, Fluorescence
Stem Cells

Grants and funding

This research was funded by the National Natural Science Foundation of China (62175036, 62175034, 82030106); the National Key R&D Program of China (2021YFF0502900); the Medical Engineering Fund of Fudan University (yg2021-022); Shanghai Natural Science Foundation (20ZR1405100, 20ZR1403700, 20JC1410900); Shanghai Key Discipline Construction Plan (2020–2022) (GWV-10.1-XK01); Fudan University-CIOMP Joint Fund (Grant No. FC2020-004); Science and Technology Research Program of Shanghai (19DZ2282100); and Pioneering Project of Academy for Engineering and Technology, Fudan University (gyy2018-001, gyy2018-002).