Abstract:
Three-dimensional (3D) bioprinting is a computer-controlled technology that combines biological factors and bioinks to print an accurate 3D structure in a layer- by-layer fashion. 3D bioprinting is a new tissue engineering technology based on rapid prototyping and additive manufacturing technology, combined with various disciplines. In addition to the problems in in vitro culture process, the bioprinting procedure is also afflicted with a few issues: (1) difficulty in looking for the appropriate bioink to match the printing parameters to reduce cell damage and mortality; and (2) difficulty in improving the printing accuracy in the printing process. Data- driven machine learning algorithms with powerful predictive capabilities have natural advantages in behavior prediction and new model exploration. Combining machine learning algorithms with 3D bioprinting helps to find more efficient bioinks, determine printing parameters, and detect defects in the printing process. This paper introduces several machine learning algorithms in detail, summarizes the role of machine learning in additive manufacturing applications, and reviews the research progress of the combination of 3D bioprinting and machine learning in recent years, especially the improvement of bioink generation, the optimization of printing parameter, and the detection of printing defect.
摘要:
三维(3D)生物打印是一种计算机控制的技术,它结合了生物因素和生物墨水,以逐层的方式打印出精确的3D结构。3D生物打印技术是一种基于快速成型和增材制造技术的新型组织工程技术,结合各种学科。除了在体外培养过程中存在的问题,生物打印程序也受到一些问题的困扰:(1)难以寻找合适的生物墨水来匹配打印参数以减少细胞损伤和死亡率;和(2)难以在打印过程中提高打印精度。数据驱动的机器学习算法具有强大的预测能力,在行为预测和新模型探索方面具有天然的优势。将机器学习算法与3D生物打印相结合,有助于找到更有效的生物墨水。确定打印参数,并检测打印过程中的缺陷。本文详细介绍了几种机器学习算法,总结了机器学习在增材制造应用中的作用,回顾了近年来3D生物打印与机器学习相结合的研究进展,特别是生物墨水生成的改进,优化打印参数,以及印刷缺陷的检测。