skip to main content


Title: Compensating the cell-induced light scattering effect in light-based bioprinting using deep learning
Abstract Digital light processing (DLP)-based three-dimensional (3D) printing technology has the advantages of speed and precision comparing with other 3D printing technologies like extrusion-based 3D printing. Therefore, it is a promising biomaterial fabrication technique for tissue engineering and regenerative medicine. When printing cell-laden biomaterials, one challenge of DLP-based bioprinting is the light scattering effect of the cells in the bioink, and therefore induce unpredictable effects on the photopolymerization process. In consequence, the DLP-based bioprinting requires extra trial-and-error efforts for parameters optimization for each specific printable structure to compensate the scattering effects induced by cells, which is often difficult and time-consuming for a machine operator. Such trial-and-error style optimization for each different structure is also very wasteful for those expensive biomaterials and cell lines. Here, we use machine learning to learn from a few trial sample printings and automatically provide printer the optimal parameters to compensate the cell-induced scattering effects. We employ a deep learning method with a learning-based data augmentation which only requires a small amount of training data. After learning from the data, the algorithm can automatically generate the printer parameters to compensate the scattering effects. Our method shows strong improvement in the intra-layer printing resolution for bioprinting, which can be further extended to solve the light scattering problems in multilayer 3D bioprinting processes.  more » « less
Award ID(s):
1907434
NSF-PAR ID:
10333666
Author(s) / Creator(s):
; ; ; ; ; ; ;
Date Published:
Journal Name:
Biofabrication
Volume:
14
Issue:
1
ISSN:
1758-5082
Page Range / eLocation ID:
015011
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Abstract

    Recapitulation of complex tissues signifies a remarkable challenge and, to date, only a few approaches have emerged that can efficiently reconstruct necessary gradients in 3D constructs. This is true even though mimicry of these gradients is of great importance to establish the functionality of engineered tissues and devices. Here, a composable‐gradient Digital Light Processing (DLP)‐based (bio)printing system is developed, utilizing the unprecedented integration of a microfluidic mixer for the generation of either continual or discrete gradients of desired (bio)inks in real time. Notably, the precisely controlled gradients are composable on‐the‐fly by facilely by adjusting the (bio)ink flow ratios. In addition, this setup is designed in such a way that (bio)ink waste is minimized when exchanging the gradient (bio)inks, further enhancing this time‐ and (bio)ink‐saving strategy. Various planar and 3D structures exhibiting continual gradients of materials, of cell densities, of growth factor concentrations, of hydrogel stiffness, and of porosities in horizontal and/or vertical direction, are exemplified. The composable fabrication of multifunctional gradients strongly supports the potential of the unique bioprinting system in numerous biomedical applications.

     
    more » « less
  2. Abstract 3D bioprinting is a fabrication method with many biomedical applications, particularly within tissue engineering. The use of freezing during 3D bioprinting, aka "3D cryoprinting," can be utilized to create micopores within tissue-engineered scaffolds to enhance cell proliferation. When used with alginate bioinks, this type of 3D cryoprinting requires three steps: 3D printing, crosslinking, and freezing. This study investigated the influence of crosslinking order and cooling rate on the microstructure and mechanical properties of sodium alginate scaffolds. We designed and built a novel modular 3D printer in order to study the effects of these steps separately and to address many of the manufacturing issues associated with 3D cryoprinting. With the modular 3D printer, 3D printing, crosslinking, and freezing were conducted on separate modules yet remain part of a continuous manufacturing process. Crosslinking before the freezing step produced highly interconnected and directional pores, which are ideal for promoting cell growth. By controlling the cooling rate, it was possible to produce pores with diameters from a range of 5 μm to 40 μm. Tensile and firmness testing found that the use of freezing does not decrease the tensile strength of the printed objects, though there was a significant loss in firmness for strands with larger pores. 
    more » « less
  3. Abstract Three-dimensional bioprinting is a promising field in regenerating patient-specific tissues and organs due to its inherent capability of releasing biocompatible materials encapsulating living cells in a predefined location. Due to the diverse characteristics of tissues and organs in terms of microstructures and cell types, a multinozzle extrusion-based 3D bioprinting system has gained popularity. The investigations on interactions between various biomaterials and cell-to-material can provide relevant information about the scaffold geometry, cell viability, and proliferation. Natural hydrogels are frequently used in bioprinting materials because of their high-water content and biocompatibility. However, the dominancy of liquid characteristics of only-hydrogel materials makes the printing process challenging. Polycaprolactone (PCL) is the most frequently used synthetic biopolymer. It can provide mechanical integrity to achieve dimensionally accurate fabricated scaffolds, especially for hard tissues such as bone and cartilage scaffolds. In this paper, we explored various multimaterial bioprinting strategies with our recently proposed bio-inks and PCL intending to achieve dimensional accuracy and mechanical aspects. Various strategies were followed to coprint natural and synthetic biopolymers and interactions were analyzed between them. Printability of pure PCL with various molecular weights was optimized with respect to different process parameters such as nozzle temperature, printing pressure, printing speed, porosity, and bed temperature to coprint with natural hydrogels. The relationship between the rheological properties and shape fidelity of natural polymers was investigated with a set of printing strategies during coprinting with PCL. The successful application of this research can help achieve dimensionally accurate scaffolds. 
    more » « less
  4. Abstract

    Additive manufacturing (AM) is rapidly revolutionizing modern manufacturing with recent progress in advanced printing methods and improved properties of printed materials. However, traditional AM methods are limited by their input‐oriented nature, which demands tedious trial‐and‐error tuning of printing parameters to achieve desired output properties. Here, an output‐oriented artificial intelligence‐integrated AM (AIAM) method is reported that enables an user to specify desired output properties while the printer autonomously discovers the optimal input printing parameters by integrating hybrid machine learning models and in situ measurements. Based on a predictive mapping between the input printing parameters and the output properties of interests established with <20 experiments designed by active learning, inverse design tasks are performed to intelligently generate the printing parameter settings that lead to desired outcomes using reinforcement learning. This method is demonstrated by autonomous aerosol jet printing (AJP) of conductive polymer films and achieving user‐defined electrical resistances with an ultralow error of 3.7%. The AIAM method, with its output‐oriented nature, holds the potential to significantly improve the autonomy, predictability, efficiency, and accessibility of the AM processes, which will unlock new possibilities in the autonomous and intelligent printing of a broad range of functional materials and devices.

     
    more » « less
  5. Abstract

    The majority of 3D‐printed biodegradable biomaterials are brittle, limiting their application to compliant tissues. Poly(glycerol sebacate) acrylate (PGSA) is a synthetic biocompatible elastomer and compatible with light‐based 3D printing. In this article, digital‐light‐processing (DLP)‐based 3D printing is employed to create a complex PGSA network structure. Nature‐inspired double network (DN) structures consisting of interconnected segments with different mechanical properties are printed from the same material in a single shot. Such capability has not been demonstrated by any other fabrication techniques so far. The biocompatibility of PGSA is confirmed via cell‐viability analysis. Furthermore, a finite‐element analysis (FEA) model is used to predict the failure of the DN structure under uniaxial tension. FEA confirms that the DN structure absorbs 100% more energy before rupture by using the soft segments as sacrificial elements while the hard segments retain structural integrity. Using the FEA‐informed design, a new DN structure is printed and tensile test results agree with the simulation. This article demonstrates how geometrically‐optimized material design can be easily and rapidly constructed by DLP‐based 3D printing, where well‐defined patterns of different stiffnesses can be simultaneously formed using the same elastic biomaterial, and overall mechanical properties can be specifically optimized for different biomedical applications.

     
    more » « less