Prediction of cell viability in dynamic optical projection stereolithography-based bioprinting using machine learning

Xu, Heqi; Liu, Qingyang; Casillas, Jazzmin; Mcanally, Mei; Mubtasim, Noshin; Gollahon, Lauren; Wu, Dazhong; Xu, Changxue

doi:10.1007/s10845-020-01708-5

Cited by 48 publications

(32 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared to other ML models created for bioprinting predictions, the regression models created in this study provided lower R 2 values and comparable errors with a similar proportion of training data to test data, and the accuracy of the classification models were lower as well [12,15]. A major reason for this is the difference in experiment variation for the datasets used to create the models.…”

Section: Discussionmentioning

confidence: 83%

“…On top of maintaining suitable shape fidelity, cell-laden scaffolds with optimized material concentrations exhibited increasing cell proliferation and migration up to 28 days after printing. Xu et al developed a model based on ensemble learning for cell viability prediction in stereolithography-based bioprinting [15]. Prediction performance on 10% of the dataset used showed a coefficient of determination (R 2 ) score of 0.953, indicating high goodness-of-fit for viability prediction of new parameter combinations.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine Assisted Experimentation of Extrusion-Based Bioprinting Systems

et al. 2021

View full text Add to dashboard Cite

Optimization of extrusion-based bioprinting (EBB) parameters have been systematically conducted through experimentation. However, the process is time- and resource-intensive and not easily translatable to other laboratories. This study approaches EBB parameter optimization through machine learning (ML) models trained using data collected from the published literature. We investigated regression-based and classification-based ML models and their abilities to predict printing outcomes of cell viability and filament diameter for cell-containing alginate and gelatin composite bioinks. In addition, we interrogated if regression-based models can predict suitable extrusion pressure given the desired cell viability when keeping other experimental parameters constant. We also compared models trained across data from general literature to models trained across data from one literature source that utilized alginate and gelatin bioinks. The results indicate that models trained on large amounts of data can impart physical trends on cell viability, filament diameter, and extrusion pressure seen in past literature. Regression models trained on the larger dataset also predict cell viability closer to experimental values for material concentration combinations not seen in training data of the single-paper-based regression models. While the best performing classification models for cell viability can achieve an average prediction accuracy of 70%, the cell viability predictions remained constant despite altering input parameter combinations. Our trained models on bioprinting literature data show the potential usage of applying ML models to bioprinting experimental design.

show abstract

Section: Discussionmentioning

confidence: 83%

Section: Introductionmentioning

confidence: 99%

Machine Assisted Experimentation of Extrusion-Based Bioprinting Systems

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Hence, to elucidate the effects on light intensity, exposure time, and cell density, the previous studies have created GelMA-printed model phase diagram between 7 – 16 mW/cm 2 and 15 – 45 s, where areas for underexposure and overexposure were plotted[ 47 ]. With the advancement in neural network technology, machine learning has also been used to predict cell viability in SLA bioprinting, with exceptional accuracies in predictions at as low as 10% of total data supplied[ 48 ]. The learning algorithm concluded that exposure time had the greatest effect on cell viability, followed by layer thickness, GelMA concentration, and light intensity.…”

Section: Photo-crosslinkable Hydrogel Bio-ink Systemsmentioning

confidence: 99%

3D Bioprinting Photo-Crosslinkable Hydrogels for Bone and Cartilage Repair

Mei

Rao

Bei

et al. 2024

IJB

View full text Add to dashboard Cite

Three-dimensional (3D) bioprinting has become a promising strategy for bone manufacturing, with excellent control over geometry and microarchitectures of the scaffolds. The bioprinting ink for bone and cartilage engineering has thus become the key to developing 3D constructs for bone and cartilage defect repair. Maintaining the balance of cellular viability, drugs or cytokines’ function, and mechanical integrity is critical for constructing 3D bone and/or cartilage scaffolds. Photo-crosslinkable hydrogel is one of the most promising materials in tissue engineering; it can respond to light and induce structural or morphological transition. The biocompatibility, easy fabrication, as well as controllable mechanical and degradation properties of photo-crosslinkable hydrogel can meet various requirements of the bone and cartilage scaffolds, which enable it to serve as an effective bio-ink for 3D bioprinting. Here, in this review, we first introduce commonly used photo-crosslinkable hydrogel materials and additives (such as nanomaterials, functional cells, and drugs/cytokine), and then discuss the applications of the 3D bioprinted photo-crosslinkable hydrogel scaffolds for bone and cartilage engineering. Finally, we conclude the review with future perspectives about the development of 3D bioprinting photo-crosslinkable hydrogels in bone and cartilage engineering.

show abstract

“…A streolithography-based bioprinting study used ML to develop a predictive cell viability model by considering four critical parameters, including UV intensity, UV exposure time, gelatin methacrylate concentration, and layer thickness. Four algorithms including neural networks [ 151 ] (an algorithm inspired by neurons in the biological brain), K-nearest neighbours [ 152 ] (a nonlinear algorithm working by averaging the output of k neighbours), ridge regression [ 153 ] (a continuous shrinkage algorithm that improves accuracy by adding a penalized term), and random forest [ 154 ] (a tree-based algorithm that builds a forest of uncorrelated regression trees) were combined to achieve an accurate model [ 155 ].…”

Section: Machine Learning Viewmentioning

confidence: 99%

Printability and Cell Viability in Extrusion-Based Bioprinting from Experimental, Computational, and Machine Learning Views

Malekpour

Chen

2022

JFB

View full text Add to dashboard Cite

Extrusion bioprinting is an emerging technology to apply biomaterials precisely with living cells (referred to as bioink) layer by layer to create three-dimensional (3D) functional constructs for tissue engineering. Printability and cell viability are two critical issues in the extrusion bioprinting process; printability refers to the capacity to form and maintain reproducible 3D structure and cell viability characterizes the amount or percentage of survival cells during printing. Research reveals that both printability and cell viability can be affected by various parameters associated with the construct design, bioinks, and bioprinting process. This paper briefly reviews the literature with the aim to identify the affecting parameters and highlight the methods or strategies for rigorously determining or optimizing them for improved printability and cell viability. This paper presents the review and discussion mainly from experimental, computational, and machine learning (ML) views, given their promising in this field. It is envisioned that ML will be a powerful tool to advance bioprinting for tissue engineering.

show abstract

Prediction of cell viability in dynamic optical projection stereolithography-based bioprinting using machine learning

Cited by 48 publications

References 44 publications

Machine Assisted Experimentation of Extrusion-Based Bioprinting Systems

Machine Assisted Experimentation of Extrusion-Based Bioprinting Systems

3D Bioprinting Photo-Crosslinkable Hydrogels for Bone and Cartilage Repair

Printability and Cell Viability in Extrusion-Based Bioprinting from Experimental, Computational, and Machine Learning Views

Contact Info

Product

Resources

About