Reconstruction-Based Digital Dental Occlusion of the Partially Edentulous Dentition

Generative deep learning approaches for the design of dental restorations: A narrative review

OBJECTIVES

This study aims to explore and discuss recent advancements in tooth reconstruction utilizing deep learning (DL) techniques. A review on new DL methodologies in partial and full tooth reconstruction is conducted.

DATA/SOURCES

PubMed, Google Scholar, and IEEE Xplore databases were searched for articles from 2003 to 2023.

STUDY SELECTION

The review includes 9 articles published from 2018 to 2023. The selected articles showcase novel DL approaches for tooth reconstruction, while those concentrating solely on the application or review of DL methods are excluded. The review shows that data is acquired via intraoral scans or laboratory scans of dental plaster models. Common data representations are depth maps, point clouds, and voxelized point clouds. Reconstructions focus on single teeth, using data from adjacent teeth or the entire jaw. Some articles include antagonist teeth data and features like occlusal grooves and gap distance. Primary network architectures include Generative Adversarial Networks (GANs) and Transformers. Compared to conventional digital methods, DL-based tooth reconstruction reports error rates approximately two times lower.

CONCLUSIONS

Generative DL models analyze dental datasets to reconstruct missing teeth by extracting insights into patterns and structures. Through specialized application, these models reconstruct morphologically and functionally sound dental structures, leveraging information from the existing teeth. The reported advancements facilitate the feasibility of DL-based dental crown reconstruction. Beyond GANs and Transformers with point clouds or voxels, recent studies indicate promising outcomes with diffusion-based architectures and innovative data representations like wavelets for 3D shape completion and inference problems.

CLINICAL SIGNIFICANCE

Generative network architectures employed in the analysis and reconstruction of dental structures demonstrate notable proficiency. The enhanced accuracy and efficiency of DL-based frameworks hold the potential to enhance clinical outcomes and increase patient satisfaction. The reduced reconstruction times and diminished requirement for manual intervention may lead to cost savings and improved accessibility of dental services.

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.

Accuracy of maximum intercuspal position located by using four intraoral scanners and an artificial intelligence-based program

STATEMENT OF PROBLEM

Maxillary and mandibular scans can be articulated in maximum intercuspal position (MIP) by using an artificial intelligence (AI) based program; however, the accuracy of the AI-based program locating the MIP relationship is unknown.

PURPOSE

The purpose of the present clinical study was to assess the accuracy of the MIP relationship located by using 4 intraoral scanners (IOSs) and an AI-based program.

MATERIAL AND METHODS

Conventional casts of a participant mounted on an articulator in MIP were digitized (T710). Four groups were created based on the IOS used to record a maxillary and mandibular scan of the participant: TRIOS4, iTero, i700, and PrimeScan. Each pair of nonarticulated scans were duplicated 20 times. Three subgroups were created: IOS, AI-articulated, and AI-IOS-corrected subgroups (n=10). In the IOS-subgroup, 10 duplicated scans were articulated in MIP by using a bilateral occlusal record. In the AI-articulated subgroup, the remaining 10 duplicated scans were articulated in MIP by using an AI-based program (BiteFinder). In the AI-IOS-corrected subgroup, the same AI-based program was used to correct the occlusal collisions of the articulated specimens obtained in the IOS-subgroup. A reverse engineering program (Geomagic Wrap) was used to calculate 36 interlandmark measurements on the digitized articulated casts (control) and each articulated specimen. Two-way ANOVA and pairwise multiple comparison Tukey tests were used to analyze trueness (α=.05). The Levene and pairwise multiple comparison Wilcoxon rank tests were used to analyze precision (α=.05).

RESULTS

Significant trueness discrepancies among the groups (P<.001) and subgroups (P<.001) were found, with a significant interaction group×subgroup (P<.001). The Levene test showed significant precision discrepancies among the groups (P<.001) and subgroups (P=.005). The TRIOS4 and iTero groups obtained better trueness and lower precision than the i700 and PrimeScan systems. Additionally, the AI-articulated subgroup showed worse trueness and precision than the IOS and AI-IOS-corrected subgroups. The AI-based program improved the MIP trueness of the scans articulated by using the iTero and PrimeScan systems but reduced the MIP trueness of the articulated scans obtained by using the TRIOS4 and i700.

CONCLUSIONS

The trueness and precision of the maxillomandibular relationship was impacted by the IOS system and program used to locate the MIP.

Evaluation of the efficiency, trueness, and clinical application of novel artificial intelligence design for dental crown prostheses

OBJECTIVE

The unique structure of human teeth limits dental repair to custom-made solutions. The production process requires a lot of time and manpower. At present, artificial intelligence (AI) has begun to be used in the medical field and improve efficiency. This study attempted to design a variety of dental restorations using AI and evaluate their clinical applicability.

METHODS

Using inlay and crown restoration types commonly used in dental standard models, we compared differences in artificial wax-up carving (wax-up), artificial digital designs (digital) and AI designs (AI). The AI system was designed using computer calculations, and the other two methods were designed by humans. Restorations were made by 3D printing resin material. Image evaluations were compared with cone beam computed tomography (CBCT) by calculating the root mean squared error.

RESULTS

Surface truth results showed that AI (68.4 µm) and digital-designed crowns (51.0 µm) had better reproducibility. Using AI for the crown reduced the time spent by 400% (compared to digital) and 900% (compared to wax-up). Optical microscopic and CBCT images showed that AI and digital designs had close margin gaps (p < 0.05). The margin gap of the crown showed that the wax-up group was 4.1 and 4.3 times greater than those of the AI and digital crowns, respectively. Therefore, the utilization of artificial intelligence can assist in the production of dental restorations, thereby enhancing both production efficiency and accuracy.

SIGNIFICANCE

It is expected that the development of AI can contribute to the reproducibility, efficiency, and goodness of fit of dental restorations.

TranSDFNet: Transformer-Based Truncated Signed Distance Fields for the Shape Design of Removable Partial Denture Clasps

The ever-growing aging population has led to an increasing need for removable partial dentures (RPDs) since they are typically the least expensive treatment options for partial edentulism. However, the digital design of RPDs remains challenging for dental technicians due to the variety of partially edentulous scenarios and complex combinations of denture components. To accelerate the design of RPDs, we propose a U-shape network incorporated with Transformer blocks to automatically generate RPD clasps, one of the most frequently used RPD components. Unlike existing dental restoration design algorithms, we introduce the voxel-based truncated signed distance field (TSDF) as an intermediate representation, which reduces the sensitivity of the network to resolution and contributes to more smooth reconstruction. Besides, a selective insertion scheme is proposed for solving the memory issue caused by Transformer blocks and enables the algorithm to work well in scenarios with insufficient data. We further design two weighted loss functions to filter out the noisy signals generated from the zero-gradient areas in TSDF. Ablation and comparison studies demonstrate that our algorithm outperforms state-of-the-art reconstruction methods by a large margin and can serve as an intelligent auxiliary in denture design.

The use of artificial intelligence and game-based learning in removable partial denture design: A comparative study

PURPOSE

The purpose of this study was to compare student performance in removable partial denture (RPD) design during a pre-clinical RPD course with and without using a recently developed computer software named AiDental. Additionally, student perceptions associated with the use of this software were assessed.

METHODS

The AiDental software consists of a learning environment containing an RPD design system that automatically designs RPDs based on the user's input. The software also contains an RPD game component that compares the user's RPD Design to an automatically generated RPD ideal design. The study was conducted in two phases. In phase one, pre-clinical second-year dental students who participated in the study were randomly divided into two groups: The AiDental group with AiDental software access (n = 36), and the conventional group without software access (n = 37). Both groups received conventional RPD instruction and practice, however, the AiDental group had additional access to the AiDental software. After 2 weeks, both groups took a mock practical test, which was collected and graded by the principal investigator (PI). The PI was blinded from group assignment and no identifying information was used in the mock practical. In phase two, all students were granted access to the AiDental software for the remainder of the pre-clinical course duration. At the conclusion of the course, all students were given a survey to evaluate their perceptions of the AiDental software. Descriptive statistics were calculated and analyzed. Variables related to perceptions of both the AiDental designer and game were assessed using Spearman's rank correlation test, the chi-square test, Fisher's exact test, and the non-parametric Wilcoxon rank-sum test as appropriate. In addition, a thematic analysis of the responses to the optional comments section was conducted using the Braun and Clarke method.

RESULTS

Phase one results showed that subjects in the AiDental group were more likely than subjects in the conventional group to receive a final grade of A or B. Phase two results showed generally favorable student perceptions towards the software, and additionally, the results showed that age was significantly negatively correlated with ease of use of the software, improving decision-making, and critical thinking relative to RPD design choices. However, no correlation between age and using the software as a reference were noted.

CONCLUSIONS

The use of AiDental's automated feedback and gamification techniques in RPD education had a positive effect on student grades and it was well-liked by students. Thus, the results suggest that AiDental has the potential to be a useful adjunct to pre-clinical teaching.

Artificial intelligence in dentistry—A review

Artificial Intelligence (AI) is the ability of machines to perform tasks that normally require human intelligence. AI is not a new term, the concept of AI can be dated back to 1950. However, it has not become a practical tool until two decades ago. Owing to the rapid development of three cornerstones of current AI technology—big data (coming through digital devices), computational power, and AI algorithm—in the past two decades, AI applications have been started to provide convenience to people's lives. In dentistry, AI has been adopted in all dental disciplines, i.e., operative dentistry, periodontics, orthodontics, oral and maxillofacial surgery, and prosthodontics. The majority of the AI applications in dentistry go to the diagnosis based on radiographic or optical images, while other tasks are not as applicable as image-based tasks mainly due to the constraints of data availability, data uniformity, and computational power for handling 3D data. Evidence-based dentistry (EBD) is regarded as the gold standard for the decision-making of dental professionals, while AI machine learning (ML) models learn from human expertise. ML can be seen as another valuable tool to assist dental professionals in multiple stages of clinical cases. This review narrated the history and classification of AI, summarised AI applications in dentistry, discussed the relationship between EBD and ML, and aimed to help dental professionals to understand AI as a tool better to assist their routine work with improved efficiency.

[Research progress of digital occlusion setup in orthognathic surgery]

Objective

To review the research progress of digital occlusion setup in orthognathic surgery.

Methods

The literature related to digital occlusion setup in orthognathic surgery in recent years was consulted, and the imaging basis, methods, clinical applications as well as existing problems were reviewed.

Results

Digital occlusion setup in orthognathic surgery includes manual, semi-automatics, and fully automatic methods. The manual method mainly relies on visual cues for operation, which is difficult to ensure the best occlusion set up, though relatively flexible. The semi-automatic method utilizes the computer software for partial occlusion set up and adjustment, but the occlusion result is still largely depended by manual operation. The fully automatic method completely depends on the operation of computer software, and targeted algorithms for different occlusion reconstruction situations are needed.

Conclusion

The preliminary research results have confirmed the accuracy and reliability of digital occlusion setup in orthognathic surgery, but there are still some limitations. Further research is needed in terms of postoperative outcomes, doctor and patient acceptance, planning time and cost-effectiveness.

Artificial intelligence models for tooth-supported fixed and removable prosthodontics: A systematic review

STATEMENT OF PROBLEM

Artificial intelligence applications are increasing in prosthodontics. Still, the current development and performance of artificial intelligence in prosthodontic applications has not yet been systematically documented and analyzed.

PURPOSE

The purpose of this systematic review was to assess the performance of the artificial intelligence models in prosthodontics for tooth shade selection, automation of restoration design, mapping the tooth preparation finishing line, optimizing the manufacturing casting, predicting facial changes in patients with removable prostheses, and designing removable partial dentures.

MATERIAL AND METHODS

An electronic systematic review was performed in MEDLINE/PubMed, EMBASE, Web of Science, Cochrane, and Scopus. A manual search was also conducted. Studies with artificial intelligence models were selected based on 6 criteria: tooth shade selection, automated fabrication of dental restorations, mapping the finishing line of tooth preparations, optimizing the manufacturing casting process, predicting facial changes in patients with removable prostheses, and designing removable partial dentures. Two investigators independently evaluated the quality assessment of the studies by applying the Joanna Briggs Institute Critical Appraisal Checklist for Quasi-Experimental Studies (nonrandomized experimental studies). A third investigator was consulted to resolve lack of consensus.

RESULTS

A total of 36 articles were reviewed and classified into 6 groups based on the application of the artificial intelligence model. One article reported on the development of an artificial intelligence model for tooth shade selection, reporting better shade matching than with conventional visual selection; 14 articles reported on the feasibility of automated design of dental restorations using different artificial intelligence models; 1 artificial intelligence model was able to mark the margin line without manual interaction with an average accuracy ranging from 90.6% to 97.4%; 2 investigations developed artificial intelligence algorithms for optimizing the manufacturing casting process, reporting an improvement of the design process, minimizing the porosity on the cast metal, and reducing the overall manufacturing time; 1 study proposed an artificial intelligence model that was able to predict facial changes in patients using removable prostheses; and 17 investigations that developed clinical decision support, expert systems for designing removable partial dentures for clinicians and educational purposes, computer-aided learning with video interactive programs for student learning, and automated removable partial denture design.

CONCLUSIONS

Artificial intelligence models have shown the potential for providing a reliable diagnostic tool for tooth shade selection, automated restoration design, mapping the preparation finishing line, optimizing the manufacturing casting, predicting facial changes in patients with removable prostheses, and designing removable partial dentures, but they are still in development. Additional studies are needed to further develop and assess their clinical performance.

A Dual Discriminator Adversarial Learning Approach for Dental Occlusal Surface Reconstruction

Objective. Restoring the correct masticatory function of partially edentulous patient is a challenging task primarily due to the complex tooth morphology between individuals. Although some deep learning-based approaches have been proposed for dental restorations, most of them do not consider the influence of dental biological characteristics for the occlusal surface reconstruction. Description. In this article, we propose a novel dual discriminator adversarial learning network to address these challenges. In particular, this network architecture integrates two models: a dilated convolutional-based generative model and a dual global-local discriminative model. While the generative model adopts dilated convolution layers to generate a feature representation that preserves clear tissue structure, the dual discriminative model makes use of two discriminators to jointly distinguish whether the input is real or fake. While the global discriminator focuses on the missing teeth and adjacent teeth to assess whether it is coherent as a whole, the local discriminator aims only at the defective teeth to ensure the local consistency of the generated dental crown. Results. Experiments on 1000 real-world patient dental samples demonstrate the effectiveness of our method. For quantitative comparison, the image quality metrics are used to measure the similarity of the generated occlusal surface, and the root mean square between the generated result and the target crown calculated by our method is 0.114 mm. In qualitative analysis, the proposed approach can generate more reasonable dental biological morphology. Conclusion. The results demonstrate that our method significantly outperforms the state-of-the-art methods in occlusal surface reconstruction. Importantly, the designed occlusal surface has enough anatomical morphology of natural teeth and superior clinical application value.