Data-driven prediction of stem cell expansion cultures

Abstract

Stem cell expansion culture aims to generate sufficient number of clinical-grade cells for cell-based therapies. One challenge for ex vivo expansion is to decide the appropriate time to perform subculture. Traditionally, this decision has been reliant on human estimation of cell confluency and predicting when confluency will approach a desired threshold. However, the use of human operators results in highly subjective decision-making and is prone to inter- and intra-operator variability. Using a real-time cell image analysis system, we propose a data-driven approach to model the cell growth process and predict the cell confluency levels, signaling times to subculture. This approach has great potential as a tool for adaptive real-time control of subculturing, and it can be integrated with robotic cell culture systems to achieve complete automation.