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.

Quantitative evaluation of the proximal contact area gap change characterization under intercuspal occlusion by intraoral 3D scanning: Food impaction with tight proximal contact.

OBJECTIVE: This study aimed to present three indicators that represent the proximal contact area gap change under intercuspal occlusion and to see if and how these indicators influence food impaction with tight proximal contact. MATERIALS AND METHODS: Ninety volunteers were recruited for bite force measurement and intraoral scanning. Three-dimensional surface data and buccal bite data were obtained for 60 impacted and 60 non-impacted teeth. The scanning data were imported into the Geomagic Studio 2013 to measure three indicators, which included the gap change maximum (Δdm, µm), the buccolingual position of Δdm (P), and the gap expanded buccolingual range (S, mm). The difference between two groups of three indicators and their relationship with food impaction with tight proximal contact were analyzed by the t test, the Pearson chi-squared test, the nonparametric Mann-Whitney U test, and the binary logistic regression analysis (a = 0.05). RESULTS: All indicators (Δdm, P, and S) were statistically different (p < 0.001, p = 0.002, and p < 0.001) in the impacted and non-impacted groups. Food impaction with tight proximal contact was affected by Δdm and S (p < 0.001, p = 0.039), but not by P (p = 0.409). CONCLUSION: The excessive increase of the gap change maximum and the gap expanded buccolingual range under bite force promoted the occurrence of food impaction with tight proximal contact. CLINICAL SIGNIFICANCE: The use of intraoral scanning to measure the characteristics of the proximal contact area gap change under bite force may help to deepen our understanding of the pathogenesis of food impaction with tight proximal contact. Importantly it can provide a reference basis for individualizing and quantifying occlusal adjustment treatment.

LA-ViT: A Network With Transformers Constrained by Learned-Parameter-Free Attention for Interpretable Grading in a New Laryngeal Histopathology Image Dataset.

Grading laryngeal squamous cell carcinoma (LSCC) based on histopathological images is a clinically significant yet challenging task. However, more low-effect background semantic information appeared in the feature maps, feature channels, and class activation maps, which caused a serious impact on the accuracy and interpretability of LSCC grading. While the traditional transformer block makes extensive use of parameter attention, the model overlearns the low-effect background semantic information, resulting in ineffectively reducing the proportion of background semantics. Therefore, we propose an end-to-end network with transformers constrained by learned-parameter-free attention (LA-ViT), which improve the ability to learn high-effect target semantic information and reduce the proportion of background semantics. Firstly, according to generalized linear model and probabilistic, we demonstrate that learned-parameter-free attention (LA) has a stronger ability to learn highly effective target semantic information than parameter attention. Secondly, the first-type LA transformer block of LA-ViT utilizes the feature map position subspace to realize the query. Then, it uses the feature channel subspace to realize the key, and adopts the average convergence to obtain a value. And those construct the LA mechanism. Thus, it reduces the proportion of background semantics in the feature maps and feature channels. Thirdly, the second-type LA transformer block of LA-ViT uses the model probability matrix information and decision level weight information to realize key and query, respectively. And those realize the LA mechanism. So, it reduces the proportion of background semantics in class activation maps. Finally, we build a new complex semantic LSCC pathology image dataset to address the problem, which is less research on LSCC grading models because of lacking clinically meaningful datasets. After extensive experiments, the whole metrics of LA-ViT outperform those of other state-of-the-art methods, and the visualization maps match better with the regions of interest in the pathologists' decision-making. Moreover, the experimental results conducted on a public LSCC pathology image dataset show that LA-ViT has superior generalization performance to that of other state-of-the-art methods.

Intelligent Point Cloud Processing, Sensing, and Understanding.

Point clouds are considered one of the fundamental pillars for representing the 3D digital landscape [...].

Accuracy of digital implant impressions using a novel structured light scanning system assisted by a planar mirror in the edentulous maxilla: An in vitro study.

OBJECTIVES: This study aimed to develop a structured light scanning system with a planar mirror to enhance the digital full-arch implant impression accuracy and to compare it with photogrammetry and intraoral scanner methods. MATERIALS AND METHODS: An edentulous maxillary stone cast with six scan bodies was scanned as the reference model using a laboratory scanner. Three scanning modalities were compared (n = 10): (1) self-developed structured light scanning with a mirror (SSLS); (2) intraoral scanner (IOS); and (3) photogrammetry system (PG). The scanners were stopped for 1 min after each scan. Six scan bodies were analysed within each scan model. Linear deviations between the scan bodies (1-2, 1-3, 1-4, 1-5, and 1-6) and 3D mucosal deviations were established. The overall deviation was calculated as the mean of all linear deviations. "Trueness" represented the discrepancy between the test and reference files, while "precision" denoted the consistency among the test files. Kruskal-Wallis and Mann-Whitney U tests were used for statistical analyses. RESULTS: Significant overall linear discrepancies were noted among the SSLS, PG, and IOS groups (p < .001). SSLS showed the best overall trueness and precision (6.6, 5.7 µm), followed by PG (58.4, 6.8 µm) and IOS (214.6, 329.1 µm). For the 3D mucosal deviation, the trueness (p < .001) and precision (p < .001) of the SSLS group were significantly better than those of the IOS group. CONCLUSIONS: The SSLS exhibited higher accuracy in determining the implant positions than the PG and IOS. Additionally, it demonstrated better accuracy in capturing the mucosa than IOS.

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.

Mechanical properties of multilayer combined gradient cellular structure and its application in the WLL.

In order to improve the buffering performance of a walkable lunar lander (WLL), an optimization method of multi-layer combined gradient cellular structure (MCGCS) is proposed. The impact load, impact action time, impact overload, and deformation amount are analyzed. The buffering performance of the material is evaluated and verified effectively with the simulation data. The overload acceleration of the WLL, the volume, and mass of the buffer material were set as the space-time solution to the optimal buffer problem, and the complex relationship between the material structure parameters and the buffer energy absorption (EA) parameters was established based on the sensitivity analysis method, and the buffer structure parameters were automatically optimized. The buffer energy absorption characteristics of the MCGCS are like the simulation results, and it has a good buffering effect, which provides a new research perspective for the excellent landing buffering mechanical properties of the WLL and a new idea for the application of engineering materials.

The Swin-Transformer network based on focal loss is used to identify images of pathological subtypes of lung adenocarcinoma with high similarity and class imbalance.

PURPOSE: The classification of primary lung adenocarcinoma is complex and varied. Different subtypes of lung adenocarcinoma have different treatment methods and different prognosis. In this study, we collected 11 datasets comprising subtypes of lung cancer and proposed FL-STNet model to provide the assistance for improving clinical problems of pathologic classification in primary adenocarcinoma of lung. METHODS: Samples were collected from 360 patients diagnosed with lung adenocarcinoma and other subtypes of lung diseases. In addition, an auxiliary diagnosis algorithm based on Swin-Transformer, which used Focal Loss for function in training, was developed. Meanwhile, the diagnostic accuracy of the Swin-Transformer was compared to pathologists. RESULTS: The Swin-Transformer captures not only information in the overall tissue structure but also the local tissue details in the images of lung cancer pathology. Furthermore, training FL-STNet with the Focal Loss function can further balance the difference in the amount of data between different subtypes, improving recognition accuracy. The average classification accuracy, F1, and AUC of the proposed FL-STNet reached 85.71%, 86.57%, and 0.9903. The average accuracy of the FL-STNet was higher by 17% and 34%, respectively, than in the senior pathologist and junior pathologist group. CONCLUSION: The first deep learning based on an 11-category classifier was developed for classifying lung adenocarcinoma subtypes based on WSI histopathology. Aiming at the deficiencies of the current CNN and Vit, FL-STNet model is proposed in this study by introducing Focal Loss and combining the advantages of Swin-Transformer model.

Interpretable laryngeal tumor grading of histopathological images via depth domain adaptive network with integration gradient CAM and priori experience-guided attention.

Tumor grading and interpretability of laryngeal cancer is a key yet challenging task in the clinical diagnosis, mainly because of the commonly used low-magnification pathological images lack fine cellular structure information and accurate localization, the diagnosis results of pathologists are different from those of attentional convolutional network -based methods, and the gradient-weighted class activation mapping method cannot be optimized to create the best visualization map. To address this problem, we propose an end-to-end depth domain adaptive network (DDANet) with integration gradient CAM and priori experience-guided attention to improve the tumor grading performance and interpretability by introducing the pathologist's a priori experience in high-magnification into the depth model. Specifically, a novel priori experience-guided attention (PE-GA) method is developed to solve the traditional unsupervised attention optimization problem. Besides, a novel integration gradient CAM is proposed to mitigate overfitting, information redundancies and low sparsity of the Grad-CAM graphs generated by the PE-GA method. Furthermore, we establish a set of quantitative evaluation metric systems for model visual interpretation. Extensive experimental results show that compared with the state-of-the-art methods, the average grading accuracy is increased to 88.43% (↑4.04%), the effective interpretable rate is increased to 52.73% (↑11.45%). Additionally, it effectively reduces the difference between CV-based method and pathology in diagnosis results. Importantly, the visualized interpretive maps are closer to the region of interest of concern by pathologists, and our model outperforms pathologists with different levels of experience.

ASI-DBNet: An Adaptive Sparse Interactive ResNet-Vision Transformer Dual-Branch Network for the Grading of Brain Cancer Histopathological Images.

Brain cancer is the deadliest cancer that occurs in the brain and central nervous system, and rapid and precise grading is essential to reduce patient suffering and improve survival. Traditional convolutional neural network (CNN)-based computer-aided diagnosis algorithms cannot fully utilize the global information of pathology images, and the recently popular vision transformer (ViT) model does not focus enough on the local details of pathology images, both of which lead to a lack of precision in the focus of the model and a lack of accuracy in the grading of brain cancer. To solve this problem, we propose an adaptive sparse interaction ResNet-ViT dual-branch network (ASI-DBNet). First, we design the ResNet-ViT parallel structure to simultaneously capture and retain the local and global information of pathology images. Second, we design the adaptive sparse interaction block (ASIB) to interact the ResNet branch with the ViT branch. Furthermore, we introduce the attention mechanism in ASIB to adaptively filter the redundant information from the dual branches during the interaction so that the feature maps delivered during the interaction are more beneficial. Intensive experiments have shown that ASI-DBNet performs best in various baseline and SOTA models, with 95.24% accuracy in four grades. In particular, for brain tumors with a high degree of deterioration (Grade III and Grade IV), the highest diagnostic accuracies achieved by ASI-DBNet are 97.93% and 96.28%, respectively, which is of great clinical significance. Meanwhile, the gradient-weighted class activation map (Grad_cam) and attention rollout visualization mechanisms are utilized to visualize the working logic behind the model, and the resulting feature maps highlight the important distinguishing features related to the diagnosis. Therefore, the interpretability and confidence of the model are improved, which is of great value for the clinical diagnosis of brain cancer.

A ViT-AMC Network With Adaptive Model Fusion and Multiobjective Optimization for Interpretable Laryngeal Tumor Grading From Histopathological Images.

The tumor grading of laryngeal cancer pathological images needs to be accurate and interpretable. The deep learning model based on the attention mechanism-integrated convolution (AMC) block has good inductive bias capability but poor interpretability, whereas the deep learning model based on the vision transformer (ViT) block has good interpretability but weak inductive bias ability. Therefore, we propose an end-to-end ViT-AMC network (ViT-AMCNet) with adaptive model fusion and multiobjective optimization that integrates and fuses the ViT and AMC blocks. However, existing model fusion methods often have negative fusion: 1). There is no guarantee that the ViT and AMC blocks will simultaneously have good feature representation capability. 2). The difference in feature representations learning between the ViT and AMC blocks is not obvious, so there is much redundant information in the two feature representations. Accordingly, we first prove the feasibility of fusing the ViT and AMC blocks based on Hoeffding's inequality. Then, we propose a multiobjective optimization method to solve the problem that ViT and AMC blocks cannot simultaneously have good feature representation. Finally, an adaptive model fusion method integrating the metrics block and the fusion block is proposed to increase the differences between feature representations and improve the deredundancy capability. Our methods improve the fusion ability of ViT-AMCNet, and experimental results demonstrate that ViT-AMCNet significantly outperforms state-of-the-art methods. Importantly, the visualized interpretive maps are closer to the region of interest of concern by pathologists, and the generalization ability is also excellent. Our code is publicly available at https://github.com/Baron-Huang/ViT-AMCNet.

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.

DCPR-GAN: Dental Crown Prosthesis Restoration Using Two-Stage Generative Adversarial Networks.

Restoring the correct masticatory function of broken teeth is the basis of dental crown prosthesis rehabilitation. However, it is a challenging task primarily due to the complex and personalized morphology of the occlusal surface. In this article, we address this problem by designing a new two-stage generative adversarial network (GAN) to reconstruct a dental crown surface in the data-driven perspective. Specifically, in the first stage, a conditional GAN (CGAN) is designed to learn the inherent relationship between the defective tooth and the target crown, which can solve the problem of the occlusal relationship restoration. In the second stage, an improved CGAN is further devised by considering an occlusal groove parsing network (GroNet) and an occlusal fingerprint constraint to enforce the generator to enrich the functional characteristics of the occlusal surface. Experimental results demonstrate that the proposed framework significantly outperforms the state-of-the-art deep learning methods in functional occlusal surface reconstruction using a real-world patient database. Moreover, the standard deviation (SD) and root mean square (RMS) between the generated occlusal surface and the target crown calculated by our method are both less than 0.161 mm. Importantly, the designed dental crown have enough anatomical morphology and higher clinical applicability.

Principal stress lines based design method of lightweight and low vibration amplitude gear web.

A lightweight and low vibration amplitude web design method was investigated to reduce gear weight and noise. It was based upon the relationship between length and orthogonality that the principal stress lines were designed at the gear web. By constructing a vibration control model with gear design parameters, the optimal distance was calculated. By offsetting the principal stress lines at the optimal distance, the lightweight gear web with the low vibration amplitude was then generated. A vibration experimental platform was built to verify the novel gear vibration performances, and it was compared with other gears with the same web's porosity to verify loading performance. The experimental results indicated that compared with the solid gear, the novel gear is 20.50% lighter and with a 29.46% vibration amplitude reduction.

Efficient Computer-Aided Design of Dental Inlay Restoration: A Deep Adversarial Framework.

Restoring the normal masticatory function of broken teeth is a challenging task primarily due to the defect location and size of a patient's teeth. In recent years, although some representative image-to-image transformation methods (e.g. Pix2Pix) can be potentially applicable to restore the missing crown surface, most of them fail to generate dental inlay surface with realistic crown details (e.g. occlusal groove) that are critical to the restoration of defective teeth with varying shapes. In this article, we design a computer-aided Deep Adversarial-driven dental Inlay reStoration (DAIS) framework to automatically reconstruct a realistic surface for a defective tooth. Specifically, DAIS consists of a Wasserstein generative adversarial network (WGAN) with a specially designed loss measurement, and a new local-global discriminator mechanism. The local discriminator focuses on missing regions to ensure the local consistency of a generated occlusal surface, while the global discriminator aims at defective teeth and adjacent teeth to assess if it is coherent as a whole. Experimental results demonstrate that DAIS is highly efficient to deal with a large area of missing teeth in arbitrary shapes and generate realistic occlusal surface completion. Moreover, the designed watertight inlay prostheses have enough anatomical morphology, thus providing higher clinical applicability compared with more state-of-the-art methods.

Accuracy of a Novel Virtual Articulator for Recording Three-Dimensional Dentition.

PURPOSE: To research and develop a novel virtual articulator system (the PN-300) based on computer binocular vision, raster scanning, and simulation technology and to conduct a preliminary evaluation of its accuracy. MATERIALS AND METHODS: Two digital cameras were used to build the trajectory-tracking part of the virtual articulator system, and cameras combined with a projection module were used to form the scanning part of the system. The most prominent feature of the PN-300 is its ability to simultaneously obtain the 3D data of the subject's teeth and the movement trajectory of the mandible relative to the maxilla. The PN-300 recorded the linear, circular, and rectangular quadrilateral movements of a high-accuracy 3D electronic translation stage. The accuracy of measurement of the inclination of incisal guidance derived from the PN-300 based on the PROTAR evo7 articulator was also estimated. RESULTS: The measurement error was below 100 µm for the linear and circular movements, and the angle error was within 0.2 degrees for the rectangular quadrilateral movements. The error of inclination of protrusive incisal guidance was 1.51 ± 0.68 degrees, and for incisal guidance was 0.82 ± 0.55 degrees. Trajectories and incisal 3D data obtained by the PN-300 were combined with data from plaster models and CBCT to simulate mandibular movement and to calculate the trajectories of the condyle. CONCLUSION: The PN-300 achieved a good accuracy for recording mandibular movement and can be expected to calculate the movement of the condyle.

Personalized design technique for the dental occlusal surface based on conditional generative adversarial networks.

The tooth defect is a frequently occurring disease within the field of dental clinic. However, the traditional manual restoration for the defective tooth needs an especially long treatment time, and dental computer aided design and manufacture (CAD/CAM) systems fail to restore the personalized anatomical features of natural teeth. Aiming to address the shortcomings of existed methods, this article proposes an intelligent network model for designing tooth crown surface based on conditional generative adversarial networks. Then, the data set for training the network model is constructed via generating depth maps of 3D tooth models scanned by the intraoral. Through adversarial training, the network model is able to generate tooth occlusal surface under the constraint of the space occlusal relationship, the perceptual loss, and occlusal groove filter loss. Finally, we carry out the assessment experiments for the quality of the occlusal surface and the occlusal relationship with the opposing tooth. The experimental results demonstrate that our method can automatically reconstruct the personalized anatomical features on occlusal surface and shorten the treatment time while restoring the full functionality of the defective tooth.

The extraction method of tooth preparation margin line based on S-Octree CNN.

The tooth preparation margin line has a significant impact on the marginal fitness for dental restoration. Among the previous methods, the extraction of margin line mainly relies on manual interaction, which is complicated and inefficient. Therefore, we propose a method to extract the margin line with the convolutional neural network based on sparse octree (S-Octree) structure. First, the dental preparations are rotated to augment the dataset. Second, the preparation models are treated as the sparse point cloud with labels through the spatial partition method of the S-Octree. Then, based on the feature line, the dental preparation point cloud is automatically divided into two regions by the convolutional neural network (CNN). Third, in order to obtain the margin line, we adopt some methods such as the dense condition random field (dense CRF), point cloud reconstruction, and back projection to the original dental preparation model. Finally, based on the measurement indicators of accuracy, sensitivity, and specificity, the average accuracy of the label predicted by the network model can reach 97.43%. The experimental results show that our method can automatically accomplish the extraction of the tooth preparation margin line.

Relative trajectory-driven virtual dynamic occlusal adjustment for dental restorations.

The abnormal occlusal contact can disrupt the coordination and health of the oral jaw system. Therefore, the dynamic adjustment of the occlusal surface is of great significance for assessing the status of occlusal contact and clarifying jaw factors of stomatognathic system diseases. To solve this problem, a trajectory subtraction algorithm based on screw theory to improve the accuracy of the occlusal movement trajectory is proposed in our paper. Driving by the relative trajectory, a virtual dynamic occlusal adjustment system is developed to realize 3D occlusal movement simulating, automatic occluding relation detection, and automatic occlusal adjustment. Furthermore, we adapt an active occlusal adjustment method based on Laplacian deformation to increase the contact areas of the occlusal surface, which can aid dentists to realize the automatic adjustment of the non-interference regions. As a consequence, the proposed subtraction algorithm is feasible and the root-mean-square is 0.097 mm, and the adjusted occlusal surface is more consistent with the natural occlusal morphology. Graphical abstract ᅟ.