Coupling machine learning with 3D bioprinting to fast track optimisation of extrusion printing

Ruberu, Kalani; Senadeera, Manisha; Rana, Santu; Gupta, Sunil Kumar; Chung, Johnson; Yue, Zhilian; Venkatesh, Svetha; Wallace, Gordon G.

doi:10.1016/j.apmt.2020.100914

Cited by 79 publications

(73 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The benefit of using this model was that a specific combination of construct height, support bath material concentration, and retraction distance was found to retain print fidelity while printing at a faster speed. Another iterative study applied Bayesian Optimization on an initial dataset of printability scores based on material and EBB printing parameters, of which parameter combinations were predicted with new experimental results to improve printability scores until an optimal parameter combination was met with the highest possible printability score [11]. This process resulted in needing 4 to 47 experiments to find optimal parameter combinations compared to using a total possible number of experiments ranging from 6000 to 10,000 determined by the Bayesian Optimization algorithm.…”

Section: Introductionmentioning

confidence: 99%

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: Introductionmentioning

confidence: 99%

Machine Assisted Experimentation of Extrusion-Based Bioprinting Systems

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Despite both technologies existing for decades, it was only recently that the two began to merge (Figure 9). ML [181]. Evidently, these will expedite research discoveries and facilitate personalised, on-demand printing of medicines.…”

Section: Applications Of ML In Pharmaceutical 3d Printingmentioning

confidence: 99%

Harnessing artificial intelligence for the next generation of 3D printed medicines

Elbadawi

McCoubrey

Gavins

et al. 2021

Advanced Drug Delivery Reviews

102

View full text Add to dashboard Cite

This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.

show abstract

“…They found various bioink formulations that provide high printing accuracy with high cell viability after 3D printing. More recently, Ruberu et al 106 established the optimal printing conditions and optimal ratio of GelMA and HAMA bioinks. Although there remains much to study in this field, it is certain that machine learning is a promising process for constructing vascularized structures.…”

Section: Future Outlook and Conclusionmentioning

confidence: 99%

Freeform 3D printing of vascularized tissues: Challenges and strategies

et al. 2021

View full text Add to dashboard Cite

In recent years, freeform three-dimensional (3D) printing has led to significant advances in the fabrication of artificial tissues with vascularized structures. This technique utilizes a supporting matrix that holds the extruded printing ink and ensures shape maintenance of the printed 3D constructs within the prescribed spatial precision. Since the printing nozzle can be translated omnidirectionally within the supporting matrix, freeform 3D printing is potentially applicable for the fabrication of complex 3D objects, incorporating curved, and irregular shaped vascular networks. To optimize freeform 3D printing quality and performance, the rheological properties of the printing ink and supporting matrix, and the material matching between them are of paramount importance. In this review, we shall compare conventional 3D printing and freeform 3D printing technologies for the fabrication of vascular constructs, and critically discuss their working principles and their advantages and disadvantages. We also provide the detailed material information of emerging printing inks and supporting matrices in recent freeform 3D printing studies. The accompanying challenges are further discussed, aiming to guide freeform 3D printing by the effective design and selection of the most appropriate materials/processes for the development of full-scale functional vascularized artificial tissues.

show abstract

Coupling machine learning with 3D bioprinting to fast track optimisation of extrusion printing

Cited by 79 publications

References 28 publications

Machine Assisted Experimentation of Extrusion-Based Bioprinting Systems

Machine Assisted Experimentation of Extrusion-Based Bioprinting Systems

Harnessing artificial intelligence for the next generation of 3D printed medicines

Freeform 3D printing of vascularized tissues: Challenges and strategies

Contact Info

Product

Resources

About