Accurate extraction of outermost biological characteristic curves in tooth preparations with fuzzy regions

Feasibility Testing of the Automatic Design of Three-Unit Implant Fixed Dental Prostheses with Different Dental CAD Software: A Pre-Clinical Pilot Trial

Background/Objectives: The technical development of implant-supported fixed dental prostheses (iFDP) initially concentrated on the computer-aided manufacturing of prosthetic restorations (CAM). Advances in information technologies have shifted the focus for optimizing digital workflows to AI-based processes for design (CAD). This pre-clinical pilot trial investigated the feasibility of the automatic design of three-unit iFDPs using CAD software (Dental Manger 2021, 3Shape; DentalCAD 3.1 Rijeka, exocad GmbH). Methods: Two clinical scenarios based on a full dentition were created virtually. Physical models were produced and digitized using two intraoral scanners applying quadrant or full-arch scans (Trios3, 3Shape, Copenhagen, Denmark; and Primescan AC, Dentsply Sirona, Bensheim, Germany). For each scenario, iFDP designs were generated automatically using two laboratory software systems (Dental Manger 2021, 3Shape; DentalCAD 3.1 Rijeka, exocad GmbH), resulting in 80 STL datasets (2 scenarios × 2 scan strategies × 2 IOS systems × 5 scan repetitions × 2 software). The files were analyzed clinically for the contact schemes and pontic area. One of the automated designs for each scenario was manually post-processed and one iFDP design for each scenario was manually created by experienced dental technicians (control). The time required for all the design processes was recorded. Results: The automatic design of iFDPs without manual adjustment did not lead to clinically acceptable restorations. The time required for the automatically generated/manually adjusted iFDPs designs was not significantly different to that for the manually designed restorations. Conclusions: Current laboratory software can not automatically generate three-unit iFDPs with clinically acceptable results in terms of the interproximal and occlusal contacts and the pontic design. The automatic iFDP design process currently requires manual adjustment, which means there is no benefit in terms of the working time compared with manually created restorations.

Deep learning-based automated detection of the dental crown finish line: An accuracy study

STATEMENT OF PROBLEM

The marginal fit of dental prostheses is a clinically significant issue, and dental computer-aided design software programs use automated methods to expedite the extraction of finish lines. The accuracy of these automated methods should be evaluated.

PURPOSE

The purpose of this study was to compare the accuracy of a new hybrid method with existing software programs that extract finish lines using fully automated and semiautomated methods.

MATERIAL AND METHODS

A total of 182 jaw scans containing at least 1 natural tooth abutment were collected and divided into 2 groups depending on how the digital data were created. Group DS used desktop scanners to scan casts trimmed for improved finish line visibility, while Group IS used intraoral scans. The method from Dentbird was compared using 3 software packages from 3Shape, exocad, and MEDIT. The Hausdorff and Chamfer distances were used in this study. Three dental laboratory technicians experienced in the digital workflow evaluated clinical finish line acceptance and its Hausdorff and Chamfer distances. For statistical analysis, t tests were performed after the outliers had been removed using the Tukey interquartile range method (α=.05).

RESULTS

Outliers identified by using the Tukey interquartile range method were more numerous in the semiautomatic methods than in the automatic methods. When considering data without outliers, the software performance was found to be similar for desktop scans of the trimmed casts. However, the method from Dentbird demonstrated statistically better results (P<.05) for the posterior tooth with finish lines in concave regions than the 3Shape, exocad, and MEDIT software programs. Furthermore, thresholds coherent with clinical acceptance were determined for the Hausdorff and Chamfer distances. The Hausdorff distance threshold was 0.366 mm for desktop scans and 0.566 mm for intraoral scans. For the Chamfer distance, the threshold was 0.026 for desktop scans and 0.100 for intraoral scans.

CONCLUSIONS

The method from Dentbird demonstrated a comparable or better performance than the other software solutions, particularly excelling in finish line extraction for intraoral scans. Using a hybrid method combining deep learning and computer-aided design approaches enables the robust and accurate extraction of finish lines.

Adaptive Point Learning with Uncertainty Quantification to Generate Margin Lines on Prepared Teeth

During a crown generation procedure, dental technicians depend on commercial software to generate a margin line to define the design boundary for the crown. The margin line generation remains a non-reproducible, inconsistent, and challenging procedure. In this work, we propose to generate margin line points on prepared teeth meshes using adaptive point learning inspired by the AdaPointTr model. We extracted ground truth margin lines as point clouds from the prepared teeth and crown bottom meshes. The chamfer distance (CD) and infoCD loss functions were used for training a supervised deep learning model that outputs a margin line as a point cloud. To enhance the generation results, the deep learning model was trained based on three different resolutions of the target margin lines, which were used to back-propagate the losses. Five folds were trained and an ensemble model was constructed. The training and test sets contained 913 and 134 samples, respectively, covering all teeth positions. Intraoral scanning was used to collect all samples. Our post-processing involves removing outlier points based on local point density and principal component analysis (PCA) followed by a spline prediction. Comparing our final spline predictions with the ground truth margin line using CD, we achieved a median distance of 0.137 mm. The median Hausdorff distance was 0.242 mm. We also propose a novel confidence metric for uncertainty quantification of generated margin lines during deployment. The metric was defined based on the percentage of removed outliers during the post-processing stage. The proposed end-to-end framework helps dental professionals in generating and evaluating margin lines consistently. The findings underscore the potential of deep learning to revolutionize the detection and extraction of 3D landmarks, offering personalized and robust methods to meet the increasing demands for precision and efficiency in the medical field.

Comparison of the morphological accuracy of automatic crowns designed by multiple computer-aided design software programs with different levels of dentition information acquisition

STATEMENT OF PROBLEM

Information on the morphological accuracy of crowns automatically produced by different computer-aided design (CAD) software programs for multilevel dentition defects is limited.

PURPOSE

The purpose of this in vitro study was to compare the morphological accuracy of crowns fabricated using different CAD software programs with different design theories for multilevel dentition defects.

MATERIAL AND METHODS

Four dentition defect types (the standard group, the abrasion group, the adjacent-teeth-missing group, and the antagonist-tooth-missing group, n=10) were fabricated to represent different levels of missing dentition information. Two design modes (the library mode and correlation mode) of 3 common CAD software programs (3Shape [3Shape A/S], CEREC [Dentsply Sirona], and exocad DentalCAD [exocad GmbH]) were used to design crowns automatically, and the morphologies of the generated crowns and original teeth were recorded. The root mean square (RMS) value was calculated to evaluate the morphological deviations between the autogenerated crowns and original teeth using the 3D matching system (Geomagic GmbH). As each group in this study represented 3 factors, the mean differences between the treatment combinations and the interaction effects were analyzed by performing factorial analysis of variance (α=.05).

RESULTS

The RMS values of autogenerated crowns designed using the correlation method were significantly lower than those designed using the library method of each software program in the 4 groups (P<.05). The RMS values of crowns designed by the 3Shape and CEREC software programs in library mode under conditions with dentition information loss were lower than those of crowns designed by the exocad software program (P<.05). Changes in the acquisition of dental information did not decrease the CEREC design accuracy (P>.05), while they did decrease the 3Shape and exocad design accuracy (P<.05).

CONCLUSIONS

The correlation method showed higher accuracy in rebuilding the original morphology of the teeth than the library method. Both the 3Shape and CEREC software programs showed higher accuracy than the exocad software program in library mode under conditions with dentition information loss, while CEREC showed higher stability than the 3Shape and exocad software programs.

Efficient complete denture metal base design via a dental feature-driven segmentation network

BACKGROUND AND OBJECTIVE

Complete denture is a common restorative treatment in dental patients and the design of the core components (major connector and retentive mesh) of complete denture metal base (CDMB) is the basis of successful restoration. However, the automated design process of CDMB has become a challenging task primarily due to the complexity of manual interaction, low personalization, and low design accuracy.

METHODS

To solve the existing problems, we develop a computer-aided Segmentation Network-driven CDMB design framework, called CDMB-SegNet, to automatically generate personalized digital design boundaries for complete dentures of edentulous patients. Specifically, CDMB-SegNet consists of a novel upright-orientation adjustment module (UO-AM), a dental feature-driven segmentation network, and a specific boundary-optimization design module (BO-DM). UO-AM automatically identifies key points for locating spatial attitude of the three-dimensional dental model with arbitrary posture, while BO-DM can result in smoother and more personalized designs for complete denture. In addition, to achieve efficient and accurate feature extraction and segmentation of 3D edentulous models with irregular gingival tissues, the light-weight backbone network is also incorporated into CDMB-SegNet.

RESULTS

Experimental results on a large clinical dataset showed that CDMB-SegNet can achieve superior performance over the state-of-the-art methods. Quantitative evaluation (major connector/retentive mesh) showed improved Accuracy (98.54 ± 0.58 %/97.73 ± 0.92 %) and IoU (87.42 ± 5.48 %/70.42 ± 7.95 %), and reduced Maximum Symmetric Surface Distance (4.54 ± 2.06 mm/4.62 ± 1.68 mm), Average Symmetric Surface Distance (1.45 ± 0.63mm/1.28 ± 0.54 mm), Roughness Rate (6.17 ± 1.40 %/6.80 ± 1.23 %) and Vertices Number (23.22 ± 1.85/43.15 ± 2.72). Moreover, CDMB-SegNet shortened the overall design time to around 4 min, which is one tenth of the comparison methods.

CONCLUSIONS

CDMB-SegNet is the first intelligent neural network for automatic CDMB design driven by oral big data and dental features. The designed CDMB is able to couple with patient's personalized dental anatomical morphology, providing higher clinical applicability compared with the state-of-the-art methods.

Reliability of automatic finish line detection for tooth preparation in dental computer-aided software

PURPOSE

This study aimed to investigate the accuracy of automatic tooth finish line registration compared to manual registration with regard to various finish line configurations and dental computer-aided design (CAD) software.

METHODS

Finish line registrations were performed on 15 digital tooth models with different finish line configurations (edge roundness radius = 0 mm, 0.2 mm, and 0.4 mm; edge angle = 30°, 60°, 90°, 120°, and 150°) using automatic and manual methods for designing virtual copings (N = 150). The discrepancies between the registered finish line extracted from the copings and the actual finish line segmented from the digitized tooth model were measured. Three-way analysis of variance (ANOVA) and post-hoc analyses with Bonferroni correction (α = 0.05) were used to analyze the results.

RESULTS

The finish line configurations, registration methods, and CAD software interacted with the accuracy of the registered finish line (p = 0.001). The automatic finish line registration method exhibited larger error values than the manual method, especially at high finish line edge roundness and obtuse edge angles for both EXOCAD and R2CAD software (p < 0.001). The difference in dental CAD software affected the registration accuracy in the automatic method (p < 0.001), but not in the manual method (p = 0.676).

CONCLUSIONS

Finish line registration errors may occur when the automatic registration method is applied to the indistinct edge of tooth preparation. The accuracy of the automatic finish line registration could differ according to the CAD software program.

Gingival shape analysis using surface curvature estimation of the intraoral scans

Background

Despite many advances in dentistry, no objective and quantitative method is available to evaluate gingival shape. The surface curvature of the optical scans represents an unexploited possibility. The present study aimed to test surface curvature estimation of intraoral scans for objective evaluation of gingival shape.

Methods

The method consists of four main steps, i.e., optical scanning, surface curvature estimation, region of interest (ROI) definition, and gingival shape analysis. Six different curvature measures and three different diameters were tested for surface curvature estimation on central (n = 78) and interdental ROI (n = 88) of patients with advanced periodontitis to quantify gingiva with a novel gingival shape parameter (GS). The reproducibility was evaluated by repeating the method on two consecutive intraoral scans obtained with a scan-rescan process of the same patient at the same time point (n = 8).

Results

Minimum and mean curvature measures computed at 2 mm diameter seem optimal GS to quantify shape at central and interdental ROI, respectively. The mean (and standard deviation) of the GS was 0.33 ± 0.07 and 0.19 ± 0.09 for central ROI using minimum, and interdental ROI using mean curvature measure, respectively, computed at a diameter of 2 mm. The method’s reproducibility evaluated on scan-rescan models for the above-mentioned ROI and curvature measures was 0.02 and 0.01, respectively.

Conclusions

Surface curvature estimation of the intraoral optical scans presents a precise and highly reproducible method for the objective gingival shape quantification enabling the detection of subtle changes. A careful selection of parameters for surface curvature estimation and curvature measures is required.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12903-022-02322-y.

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.