Deep Learning-Guided Single-Cell Encapsulation through photo-crosslinking for Advanced 3D Culture

Encapsulating single cells in hydrogels provides them with a relatively autonomous and controllable three-dimensional extracellular environment. This environment can facilitate cell interaction and proliferation, making it highly valuable in fields such as tissue engineering and single-cell research. However, traditional methods of single-cell encapsulation encounter limitations in terms of single-cell encapsulation rate and topography control, which hinder of the progress of single-cell encapsulation research. In this paper, we propose a novel method for printing microgel-encapsulated single cells using deep learning-guided DLP printing. By leveraging deep learning algorithms, we accurately capture and translate the real-time positional data of single cells into the printing system's coordinate framework. Based on the single-cell positional information, a virtual digital mask is created via the OpenCV algorithm, which is then input into the digital microscope to complete the single-cell encapsulation. The single-cell encapsulation rate achieved by this method is 86.3%, which is about 2.87 times higher than that of the traditional method. Experimental results show that our method achieves high accuracy in single-cell encapsulation and the fabrication of microgels with arbitrary shapes, which hold significant importance for biological and medical applications.