IALH Research Fellow Willerth Stephanie has co-authored a new research article entitled Machine Learning Approaches to 3D Models for Drug Screening. Collaborating authors include da Silva Allisson, Sharma Ruchi, Shteinberg Ekaterina, Patel Vaidehi, Bhardwaj Lavanya Garay Tania and Yu Bosco. The article was published in Biomedical Materials and Devices.
Abstract: The creation of precise, functional 3D tissues can enable effective drug screening as well as advancements in regenerative medicine. However, the inherent limitations present during the development of these 3D models pose challenges when manufacturing. This review examines the obstacles associated with the pre-processing, processing, and post-processing phases when bioprinting that must be addressed to overcome these constraints and produce reproducible tissue constructs. These obstacles include critical elements such as cell composition, biomaterial formulation, processing techniques, media conditions, 3D structure design, model conditioning, and 3D model quantification. This review identifies these inherent process limitations when making 3D tissue models. The review then leverages machine learning tools that have proven successful in related contexts and discusses them in the context of 3D tissue models. The review aims to inspire researchers to explore and implement innovative machine learning techniques for developing 3D models by drawing insights from studies taken from a variety of engineering domains. This curated compilation covers a wide array of machine learning solutions to navigate the intricate complexities of 3D model creation, pushing the boundaries of tissue engineering.
To read the full article, see https://doi.org/10.1007/s44174-023-00142-4