The Effect of Residual Dentition on the Dynamic Adjustment of Wear Facet Morphology on a Mandibular First Molar Crown

Accuracy of artificial intelligence-designed single-molar dental prostheses: A feasibility study

STATEMENT OF PROBLEM

Computer-aided design and computer-aided manufacturing (CAD-CAM) technology has greatly improved the efficiency of the fabrication of dental prostheses. However, the design process (CAD stage) is still time-consuming and labor intensive.

PURPOSE

The purpose of this feasibility study was to investigate the accuracy of a novel artificial intelligence (AI) system in designing biomimetic single-molar dental prostheses by comparing and matching them to the natural molar teeth.

MATERIAL AND METHODS

A total of 169 maxillary casts were obtained from healthy dentate participants. The casts were digitized, duplicated, and processed with the removal of the maxillary right first molar. A total of 159 pairs of original and processed casts were input into the Generative Adversarial Networks (GANs) for training. In validation, 10 sets of processed casts were input into the AI system, and 10 AI-designed teeth were generated through backpropagation. Individual AI-designed teeth were then superimposed onto each of the 10 original teeth, and the morphological differences in mean Hausdorff distance were measured. True reconstruction was defined as correct matching between the AI-designed and original teeth with the smallest mean Hausdorff distance. The ratio of true reconstruction was calculated as the Intersection-over-Union. The reconstruction performance of the AI system was determined by the Hausdorff distance and Intersection-over-Union.

RESULTS

Data of validation showed that the mean Hausdorff distance ranged from 0.441 to 0.752 mm and the Intersection-over-Union of the system was 0.600 (60%).

CONCLUSIONS

This study demonstrated the feasibility of AI in designing single-molar dental prostheses. With further training and optimization of algorithms, the accuracy of biomimetic AI-designed dental prostheses could be further enhanced.

Morphological design of occlusal wear facets for the mandibular first molar crown using different bite registration methods

PURPOSE

To compare the accuracy of occlusal wear facet morphology designed using different bite registration methods for mandibular first molar crowns.

MATERIALS AND METHODS

The posterior teeth and intraoral intercuspal occlusions of 12 participants were scanned. The abutment shape of the mandibular first molars for complete crowns was virtually designed, and the anatomic coping design method was used to design crowns. In the anatomic coping design, digital wax patterns were constructed by elevating the wear facets on the original surface of first molars and then adjusting the facets with 2 types of virtual occlusions determined by buccal bite registration (BBR) or segmented tooth registration (STR) methods, where the displacement of teeth under bite force was considered (STR) or not (BBR). The occlusal distance between the original wear facets and the antagonists as well as 3D deviations between the facets on the designed crowns and on the surfaces of the original teeth were measured. Paired-samples t-test was used to analyze the results (α = .05).

RESULTS

Regarding occlusal distance, the mean 3D deviation and the root mean square (RMS) values of BBR were greater than those of the STR groups (P<.001 and P = .008). The mean 3D deviations of the crowns of the BBR and STR groups were 0.19 ±0.04 mm and 0.14 ±0.06 mm, respectively and the RMS values were 0.22 ±0.03 mm and 0.18 ±0.04 mm (P<.001), respectively.

CONCLUSIONS

The morphology of occlusal wear facets of mandibular first molar crowns designed with the occlusion constructed using the segmented tooth registration method are more coincident with the original morphology. This article is protected by copyright. All rights reserved.

Artificial intelligence-designed single molar dental prostheses: A protocol of prospective experimental study

Background

Dental prostheses, which aim to replace missing teeth and to restore patients’ appearance and oral functions, should be biomimetic and thus adopt the occlusal morphology and three-dimensional (3D) position of healthy natural teeth. Since the teeth of an individual subject are controlled by the same set of genes (genotype) and are exposed to mostly identical oral environment (phenotype), the occlusal morphology and 3D position of teeth of an individual patient are inter-related. It is hypothesized that artificial intelligence (AI) can automate the design of single-tooth dental prostheses after learning the features of the remaining dentition.

Materials and methods

This article describes the protocol of a prospective experimental study, which aims to train and to validate the AI system for design of single molar dental prostheses. Maxillary and mandibular dentate teeth models will be collected and digitized from at least 250 volunteers. The (original) digitized maxillary teeth models will be duplicated and processed by removal of right maxillary first molars (FDI tooth 16). Teeth models will be randomly divided into training and validation sets. At least 200 training sets of the original and the processed digitalized teeth models will be input into 3D Generative Adversarial Network (GAN) for training. Among the validation sets, tooth 16 will be generated by AI on 50 processed models and the morphology and 3D position of AI-generated tooth will be compared to that of the natural tooth in the original maxillary teeth model. The use of different GAN algorithms and the need of antagonist mandibular teeth model will be investigated. Results will be reported following the CONSORT-AI.

Design of wear facets of mandibular first molar crowns by using patient-specific motion with an intraoral scanner: A clinical study

STATEMENT OF PROBLEM

Although computer-aided design has become popular, restorations are typically designed from static occlusion and dynamically by using an average-value virtual articulator. Patient-specific motion recorded by using an intraoral scanner has rarely been used to design restorations, and its design ability has not been analyzed.

PURPOSE

The purpose of this clinical study was to record patient-specific motion by using an intraoral scanner and to analyze its ability to design the morphology of the wear facets on mandibular first molar crowns.

MATERIAL AND METHODS

An intraoral scanner was used to scan complete arch digital casts and to record patient-specific motion of 11 participants. Right and left mandibular first molars were selected as the target teeth. The complete crown preparations of the target teeth were virtually prepared on the digital mandibular casts by using the Geomagic Studio 2013 software program. High points were created by elevating the wear facets of the target teeth by 0.3 mm in the occlusal direction to generate digital wax patterns. The Dental System software program was used to design crowns with the anatomic coping design method. Occlusal adjustment with static occlusion (STA crown), with the average-value virtual articulator (DYN crown), and with patient-specific motion (FUN crown) was carried out. The crowns adjusted with these 3 methods were compared with the original wear facets. The mean value and root mean square (RMS) of 3D deviation were measured. One-way ANOVA was used to analyze the influence of the occlusal surface design methods on the morphology of the wear facets (α=.05).

RESULTS

The STA crowns had the poorest results with the mean ±standard deviation 3D deviation value of 0.15 ±0.05 mm and RMS value of 0.19 ±0.04 mm. The best results occurred in the FUN group, with the mean ±standard deviation 3D deviation value of 0.05 ±0.06 mm and RMS value of 0.13 ±0.03 mm. Significant differences were found among the 3 groups (P<.01). Except for the RMS value between the STA and DYN groups, significant differences were found between groups from the pairwise comparisons.

CONCLUSIONS

The occlusal surface of the crowns designed by using the patient-specific motion recorded with the intraoral scanner had the best coincidence with the morphology of the wear facets on the original teeth.