SPECIALLY COLLECTED PAPERS
Shimadzu Review 78[3・4] (2021)
Abstract
In cell production processes for regenerative medicine and cell therapy, there is an urgent need to establish monitoring technology that can measure the effects of process parameters non-invasively and in real-time. To date, we have developed technology that uses high-performance liquid chromatography-mass spectrometry to measure culture medium components and metabolites in culture supernatant. Cell morphology analysis by microscopy-based systems is also common in this field, with remarkable results being reported, particularly when machine learning is used. Although machine learning is used routinely for analysis by information engineers, it has yet to become a commonplace tool among cell culture technologists and cell researchers who perform cell culture. Because the practical aspects of aggregating and managing the data needed to train machine learning algorithms pose a major obstacle to its adoption, we developed Cell PocketTM, a web-based system that uses machine learning for cell morphology analysis and also provides a platform for easy sharing, aggregation, and management of data. In this paper, we report on the development of Cell Pocket and present an example application of this system to quantify aging-related morphological changes in mesenchymal stem cells.
1Cell Business Development Section, Life Science Business Development, Analytical & Measuring Instruments Division, Shimadzu Corporation, Kyoto, Japan
2Research & Development Department, Analytical & Measuring Instruments Division, Shimadzu Corporation, Kyoto, Japan
3Research & Development Center for Cell Therapy, Foundation for Biomedical Research and Innovation at Kobe, Kobe, Japan
*The information contained in Shimadzu Review has not been modified since the original publication date. Please be aware that in some cases, products mentioned within the articles are no longer available.