|About this Abstract
||2022 TMS Annual Meeting & Exhibition
||Advances in Biomaterials for 3D Printing of Scaffolds and Tissues
||Prediction of Cell Viability in Dynamic Optical Projection Stereolithography-Based Bioprinting Using Machine Learning
||Heqi Xu, Qingyang Liu, Changxue Xu, Dazhong Wu
|On-Site Speaker (Planned)
Stereolithography (SLA)-based bioprinting is capable of fabricating 3D complicated structures such as vascular constructs with high printing accuracy and efficiency. However, maintaining high cell viability during SLA-based bioprinting process remains an unsolved challenge due to the cell damage induced by ultraviolet (UV) irradiation during the SLA printing process. Existing physics-based models have limitations on predicting cell viability with sufficient accuracy due to existing different complex pathways of cell damage. To address this issue, a data-driven predictive modeling approach using ensemble learning algorithm has been developed to predict cell viability under various experimental conditions in SLA-based bioprinting. A full factorial design of experiments has been conducted based on four critical process parameters including UV intensity, UV exposure time, polymer concentration, and layer thickness. The predictive model has been validated by the experimental results showing capability of predicting cell viability with high accuracy.
||Biomaterials, Additive Manufacturing, Machine Learning