Morphology and mechanical performance of dental crown designed by 3D-DCGAN

Ding, Hao; Cui, Zhiming; Maghami, Ebrahim; Chen, Yanning; Matinlinna, Jukka Pekka; Pow, Ehn; Fok, Alex; Burrow, Michael F.; Wang, Wenping; Tsoi, James Kit Hon

doi:10.1016/j.dental.2023.02.001

Cited by 31 publications

(15 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Logistic Regression methodologies associated with Maximum Likelihood (Chen, 2023), Trainable Weka Segmentation (TWS) plug-in (Ding 2022 andVyas, 2016), 3D-DCGAN (Ding, 2023), Convolutional Neural Networks (CNNs) (Engels 2022, Karatas, 2021, Regression Models (Kose, 2023), Extra Trees (ET) , Gradient Boosting Decision Tree (GBDT) , LightGBM and XGBoost (Extreme Gradient Boosting ) Vyas et al 2016), Multilayer Perception (MLP) (Vyas et al 2016) and K-Nearest Neighbors (KNN) (Vyas et al 2016) of ML were applied in the selected studies (Table 1).…”

Section: Resultsmentioning

confidence: 99%

Biotecnologia: Fonte De Novas Moléculas Antimicrobianas Para O Tratamento De Infecções Bacterianas Multirresistentes

Pereira,

Jinga,

Oliveira

et al. 2023

A Pesquisa Em Saúde: Desafios Atuais E Perspectivas Futuras 2

View full text Add to dashboard Cite

show abstract

Section: Resultsmentioning

confidence: 99%

Biotecnologia: Fonte De Novas Moléculas Antimicrobianas Para O Tratamento De Infecções Bacterianas Multirresistentes

Pereira,

Jinga,

Oliveira

et al. 2023

A Pesquisa Em Saúde: Desafios Atuais E Perspectivas Futuras 2

View full text Add to dashboard Cite

show abstract

“…When assessing the fracture resistance of dental materials, it is essential to consider the entire study design, including the characteristics of the test material, the abutment design and its material properties, and the parameters of the fracture loading [48][49][50]. Furthermore, the cement layer and its thickness can affect the values for maximum occlusal force on the crowns [51][52][53].…”

Section: Discussionmentioning

confidence: 99%

The Clinical Potential of 3D-Printed Crowns Reinforced with Zirconia and Glass Silica Microfillers

Alshamrani

Alhotan

Owais

et al. 2023

JFB

View full text Add to dashboard Cite

The development of 3D-printed crown resin materials with improved mechanical and physical properties is an area of growing interest in dentistry. This study aimed to develop a 3D-printed crown resin material modified with zirconia glass (ZG) and glass silica (GS) microfillers to enhance overall mechanical and physical properties. A total of 125 specimens were created and divided into five groups: control unmodified resin, 5% either ZG or GS reinforced 3D-printed resin, and 10% either ZG or GS reinforced 3D-printed resin. The fracture resistance, surface roughness, and translucency parameter were measured, and fractured crowns were studied under a scanning electron microscope. The results showed that 3D-printed parts that were strengthened with ZG and GS microfillers demonstrated comparable mechanical performance to unmodified crown resin but resulted in greater surface roughness, and only the group that contained 5% ZG showed an increase in translucency. However, it should be noted that increased surface roughness may impact the aesthetics of the crowns, and further optimisation of microfillers concentrations may be necessary. These findings suggest that the newly developed dental-based resins that incorporate microfillers could be suitable for clinical applications, but further studies are necessary to optimise the nanoparticle concentrations and investigate their long-term clinical outcomes.

show abstract

“…The input data was represented as a point cloud. Chau et al ( 2023 ) and Ding et al ( 2023 ) opted for a 3D-GAN architecture (Wu et al, 2016 ). While the exact data format was not specified, voxelized points are assumed to be utilized due to the employed architecture (Wu et al, 2016 ).…”

Section: Introductionmentioning

confidence: 99%

“…While the exact data format was not specified, voxelized points are assumed to be utilized due to the employed architecture (Wu et al, 2016 ). The selection of teeth for reconstruction varies, ranging from an arbitrary tooth (Zhu et al, 2022 ) to specific molars (Chau et al, 2023 ; Ding et al, 2023 ) or incisors (Feng et al, 2023 ). Unlike 2D methods, the input data is no longer confined to the occlusal surfaces of a limited number of teeth.…”

Section: Introductionmentioning

confidence: 99%

A data-driven approach for the partial reconstruction of individual human molar teeth using generative deep learning

Broll,

Rosentritt,

Schlegl

et al. 2024

Front. Artif. Intell.

View full text Add to dashboard Cite

Background and objectiveDue to the high prevalence of dental caries, fixed dental restorations are regularly required to restore compromised teeth or replace missing teeth while retaining function and aesthetic appearance. The fabrication of dental restorations, however, remains challenging due to the complexity of the human masticatory system as well as the unique morphology of each individual dentition. Adaptation and reworking are frequently required during the insertion of fixed dental prostheses (FDPs), which increase cost and treatment time. This article proposes a data-driven approach for the partial reconstruction of occlusal surfaces based on a data set that comprises 92 3D mesh files of full dental crown restorations.MethodsA Generative Adversarial Network (GAN) is considered for the given task in view of its ability to represent extensive data sets in an unsupervised manner with a wide variety of applications. Having demonstrated good capabilities in terms of image quality and training stability, StyleGAN-2 has been chosen as the main network for generating the occlusal surfaces. A 2D projection method is proposed in order to generate 2D representations of the provided 3D tooth data set for integration with the StyleGAN architecture. The reconstruction capabilities of the trained network are demonstrated by means of 4 common inlay types using a Bayesian Image Reconstruction method. This involves pre-processing the data in order to extract the necessary information of the tooth preparations required for the used method as well as the modification of the initial reconstruction loss.ResultsThe reconstruction process yields satisfactory visual and quantitative results for all preparations with a root mean square error (RMSE) ranging from 0.02 mm to 0.18 mm. When compared against a clinical procedure for CAD inlay fabrication, the group of dentists preferred the GAN-based restorations for 3 of the total 4 inlay geometries.ConclusionsThis article shows the effectiveness of the StyleGAN architecture with a downstream optimization process for the reconstruction of 4 different inlay geometries. The independence of the reconstruction process and the initial training of the GAN enables the application of the method for arbitrary inlay geometries without time-consuming retraining of the GAN.

show abstract

Morphology and mechanical performance of dental crown designed by 3D-DCGAN

Cited by 31 publications

References 37 publications

Biotecnologia: Fonte De Novas Moléculas Antimicrobianas Para O Tratamento De Infecções Bacterianas Multirresistentes

Biotecnologia: Fonte De Novas Moléculas Antimicrobianas Para O Tratamento De Infecções Bacterianas Multirresistentes

The Clinical Potential of 3D-Printed Crowns Reinforced with Zirconia and Glass Silica Microfillers

A data-driven approach for the partial reconstruction of individual human molar teeth using generative deep learning

Contact Info

Product

Resources

About