3D Tooth Segmentation and Labeling Using Deep Convolutional Neural Networks

Development and validation of a graph convolutional network (GCN)-based automatic superimposition method for maxillary digital dental models (MDMs)

OBJECTIVES

To validate the accuracy and reliability of a graph convolutional network (GCN)-based superimposition method of a maxillary digital dental model (MDM) by comparing it with manual superimposition and quantifying the clinical error from this method.

MATERIALS AND METHODS

Based on a GCN, learning the features from 100 three-dimensional digital occlusal models under supervision of the palatal stable structure labels that were manually annotated by senior specialists, the palatal stable structure was automatically segmented. The average Hausdorff distance was calculated to assess the difference between automatic and manual segmentations. Tooth position and angulation, including rotation, tip, and torque, of bilateral upper first molars and central incisors were obtained to measure the clinical error of automatic superimposition. Reliability was calculated by intraclass correlation coefficient (ICC).

RESULTS

The average Hausdorff distance was 0.36 mm between automatic and manual segmentations of the palatal stable region and was larger than the intraexaminer and interexaminer deviations. The tooth position deviation was <0.32 mm, and the tooth angulation difference was <0.26° for tip and torque, and 0.46-0.61° in rotation. ICCs, used for assessment of reliability, ranged from 0.82 to 0.99 in all variables.

CONCLUSIONS

The GCN-based MDM superimposition is an efficient method for the assessment of tooth movement in adults. The clinical error in tooth position and angulation induced by the method was clinically acceptable. Reliability was as high as manual segmentation.

3D dental similarity quantification in forensic odontology identification

Forensic odontology identification largely depends on comparing dental work like fillings and crowns with the dental records of potential victims. This process can be challenging, especially regarding victims with minimal or no dental work. Alternatively, 3D tooth morphology can be used for identification by automated dental surface similarity scoring. However, high-resolution 3D intraoral photo scans contain hundreds of thousands of datapoints from each individual jaw, making database searches difficult and slow. Here, we reduce full 3D scans to keypoints, which are small points located in areas of high curvature on tooth surfaces. We use Difference of Curvature (DoC) for robust keypoint detection and evaluate different keypoint representation methods to distinguish between scans of the same individual and scans of different individuals, assigning them a similarity score.The results demonstrate that combining DoC with the Signature of Histograms of OrienTations (SHOT) representation method effectively separates matches from mismatches. This indicates the potential for automatic scoring of dental surface similarity. This can be valuable for forensic odontology identification, especially in cases where traditional methods are limited by the lack of dental work.

ChatIOS: Improving automatic 3-dimensional tooth segmentation via GPT-4V and multimodal pre-training

OBJECTIVES

This study aims to propose a framework that integrates GPT-4V, a recent advanced version of ChatGPT, and multimodal pre-training techniques to enhance deep learning algorithms for 3-dimensional (3D) tooth segmentation in scans produced by intraoral scanners (IOSs).

METHODS

The framework was developed on 1800 intraoral scans of approximately 24,000 annotated teeth (training set: 1200 scans, 16,004 teeth; testing set: 600 scans, 7995 teeth), from the Teeth3DS dataset, which was gathered from 900 patients with both maxillary and mandible regions. The first step of the proposed framework, ChatIOS, is to pre-process the 3D IOS data to extract 3D point clouds. Then, GPT-4V generates detailed descriptions of 2-dimensional (2D) IOS images taken from different view angles. In the multimodal pre-training, triplets, which comprise point clouds, 2D images, and text descriptions, serve as inputs. A series of ablation studies were systematically conducted to illustrate the superior design of the automatic 3D tooth segmentation system. Our quantitative evaluation criteria included segmentation quality, processing speed, and clinical applicability.

RESULTS

When tested on 600 scans, ChatIOS substantially outperformed the existing benchmarks such as PointNet++ across all metrics, including mean intersection-over-union (mIoU, from 90.3 % to 93.0 % for maxillary and from 89.2 % to 92.3 % for mandible scans), segmentation accuracy (from 97.0 % to 98.0 % for maxillary and from 96.8 % to 97.9 % for mandible scans) and dice similarity coefficient (DSC, from 98.1 % to 98.7 % for maxillary and from 97.9 % to 98.6 % for mandible scans). Our model took only approximately 2s to generate segmentation outputs per scan and exhibited acceptable consistency with clinical expert evaluations.

CONCLUSIONS

Our ChatIOS framework can increase the effectiveness and efficiency of 3D tooth segmentation that clinical procedures require, including orthodontic and prosthetic treatments. This study presents an early exploration of the applications of GPT-4V in digital dentistry and also pioneers the multimodal pre-training paradigm for 3D tooth segmentation.

CLINICAL SIGNIFICANCE

Accurate segmentation of teeth on 3D intraoral scans is critical for orthodontic and prosthetic treatments. ChatIOS can integrate GPT-4V with pre-trained vision-language models (VLMs) to gain an in-depth understanding of IOS data, which can contribute to more efficient and precise tooth segmentation systems.

A Novel Hierarchical Cross-Stream Aggregation Neural Network for Semantic Segmentation of 3-D Dental Surface Models

Accurate teeth delineation on 3-D dental models is essential for individualized orthodontic treatment planning. Pioneering works like PointNet suggest a promising direction to conduct efficient and accurate 3-D dental model analyses in end-to-end learnable fashions. Recent studies further imply that multistream architectures to concurrently learn geometric representations from different inputs/views (e.g., coordinates and normals) are beneficial for segmenting teeth with varying conditions. However, such multistream networks typically adopt simple late-fusion strategies to combine features captured from raw inputs that encode complementary but fundamentally different geometric information, potentially hampering their accuracy in end-to-end semantic segmentation. This article presents a hierarchical cross-stream aggregation (HiCA) network to learn more discriminative point/cell-wise representations from multiview inputs for fine-grained 3-D semantic segmentation. Specifically, based upon our multistream backbone with input-tailored feature extractors, we first design a contextual cross-steam aggregation (CA) module conditioned on interstream consistency to boost each view's contextual representation learning jointly. Then, before the late fusion of different streams' outputs for segmentation, we further deploy a discriminative cross-stream aggregation (DA) module to concurrently update all views' discriminative representation learning by leveraging a specific graph attention strategy induced by multiview prototype learning. On both public and in-house datasets of real-patient dental models, our method significantly outperformed state-of-the-art (SOTA) deep learning methods for teeth semantic segmentation. In addition, extended experimental results suggest the applicability of HiCA to other general 3-D shape segmentation tasks. The code is available at https://github.com/ladderlab-xjtu/HiCA.

Cross-center Model Adaptive Tooth segmentation

Automatic 3-dimensional tooth segmentation on intraoral scans (IOS) plays a pivotal role in computer-aided orthodontic treatments. In practice, deploying existing well-trained models to different medical centers suffers from two main problems: (1) the data distribution shifts between existing and new centers, which causes significant performance degradation. (2) The data in the existing center(s) is usually not permitted to be shared, and annotating additional data in the new center(s) is time-consuming and expensive, thus making re-training or fine-tuning unfeasible. In this paper, we propose a framework for Cross-center Model Adaptive Tooth segmentation (CMAT) to alleviate these issues. CMAT takes the trained model(s) from the source center(s) as input and adapts them to different target centers, without data transmission or additional annotations. CMAT is applicable to three cross-center scenarios: source-data-free, multi-source-data-free, and test-time. The model adaptation in CMAT is realized by a tooth-level prototype alignment module, a progressive pseudo-labeling transfer module, and a tooth-prior regularized information maximization module. Experiments under three cross-center scenarios on two datasets show that CMAT can consistently surpass existing baselines. The effectiveness is further verified with extensive ablation studies and statistical analysis, demonstrating its applicability for privacy-preserving model adaptive tooth segmentation in real-world digital dentistry.

TSegLab: Multi-stage 3D dental scan segmentation and labeling

This study introduces a novel deep learning approach for 3D teeth scan segmentation and labeling, designed to enhance accuracy in computer-aided design (CAD) systems. Our method is organized into three key stages: coarse localization, fine teeth segmentation, and labeling. In the teeth localization stage, we employ a Mask-RCNN model to detect teeth in a rendered three-channel 2D representation of the input scan. For fine teeth segmentation, each detected tooth mesh is isomorphically mapped to a 2D harmonic parameter space and segmented with a Mask-RCNN model for precise crown delineation. Finally, for labeling, we propose a graph neural network that captures both the 3D shape and spatial distribution of the teeth, along with a new data augmentation technique to simulate missing teeth and teeth position variation during training. The method is evaluated using three key metrics: Teeth Localization Accuracy (TLA), Teeth Segmentation Accuracy (TSA), and Teeth Identification Rate (TIR). We tested our approach on the Teeth3DS dataset, consisting of 1800 intraoral 3D scans, and achieved a TLA of 98.45%, TSA of 98.17%, and TIR of 97.61%, outperforming existing state-of-the-art techniques. These results suggest that our approach significantly enhances the precision and reliability of automatic teeth segmentation and labeling in dental CAD applications. Link to the project page: https://crns-smartvision.github.io/tseglab.

PITX2 expression and Neanderthal introgression in HS3ST3A1 contribute to variation in tooth dimensions in modern humans

Dental morphology varies greatly throughout evolution, including in the human lineage, but little is known about the biology of this variation. Here, we use multiomics analyses to examine the genetics of variation in tooth crown dimensions. In a human cohort with mixed continental ancestry, we detected genome-wide significant associations at 18 genome regions. One region includes EDAR, a gene known to impact dental features in East Asians. Furthermore, we find that EDAR variants increase the mesiodistal diameter of all teeth, following an anterior-posterior gradient of decreasing strength. Among the 17 novel-associated regions, we replicate 7/13 in an independent human cohort and find that 4/12 orthologous regions affect molar size in mice. Two association signals point to compelling candidate genes. One is ∼61 kb from PITX2, a major determinant of tooth development. Another overlaps HS3ST3A1, a paralogous neighbor of HS3ST3B1, a tooth enamel knot factor. We document the expression of Pitx2 and Hs3st3a1 in enamel knot and dental epithelial cells of developing mouse incisors. Furthermore, associated SNPs in PITX2 and HS3ST3A1 overlap enhancers active in these cells, suggesting a role for these SNPs in gene regulation during dental development. In addition, we document that Pitx2 and Hs3st3a1/Hs3st3b1 knockout mice show alterations in dental morphology. Finally, we find that associated SNPs in HS3ST3A1 are in a DNA tract introgressed from Neanderthals, consistent with an involvement of HS3ST3A1 in tooth size variation during human evolution.

Automated Measurements of Tooth Size and Arch Widths on Cone-Beam Computerized Tomography and Scan Images of Plaster Dental Models

Measurements of tooth size for estimating inter-arch tooth size discrepancies and inter-tooth distances, essential for orthodontic diagnosis and treatment, are primarily done using traditional methods involving plaster models and calipers. These methods are time-consuming and labor-intensive, requiring multiple steps. With advances in cone-beam computerized tomography (CBCT) and intraoral scanning technology, these processes can now be automated through computer analyses. This study proposes a multi-step computational method for measuring mesiodistal tooth widths and inter-tooth distances, applicable to both CBCT and scan images of plaster models. The first step involves 3D segmentation of the upper and lower teeth using CBCT, combining results from sagittal and panoramic views. For intraoral scans, teeth are segmented from the gums. The second step identifies the teeth based on an adaptively estimated jaw midline using maximum intensity projection. The third step uses a decentralized convolutional neural network to calculate key points representing the parameters. The proposed method was validated against manual measurements by orthodontists using plaster models, achieving an intraclass correlation coefficient of 0.967 and a mean absolute error of less than 1 mm for all tooth types. An analysis of variance test confirmed the statistical consistency between the method's measurements and those of human experts.

Mapping the Use of Artificial Intelligence-Based Image Analysis for Clinical Decision-Making in Dentistry: A Scoping Review

OBJECTIVES

Artificial intelligence (AI) is an emerging field in dentistry. AI is gradually being integrated into dentistry to improve clinical dental practice. The aims of this scoping review were to investigate the application of AI in image analysis for decision-making in clinical dentistry and identify trends and research gaps in the current literature.

MATERIAL AND METHODS

This review followed the guidelines provided by the Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews (PRISMA-ScR). An electronic literature search was performed through PubMed and Scopus. After removing duplicates, a preliminary screening based on titles and abstracts was performed. A full-text review and analysis were performed according to predefined inclusion criteria, and data were extracted from eligible articles.

RESULTS

Of the 1334 articles returned, 276 met the inclusion criteria (consisting of 601,122 images in total) and were included in the qualitative synthesis. Most of the included studies utilized convolutional neural networks (CNNs) on dental radiographs such as orthopantomograms (OPGs) and intraoral radiographs (bitewings and periapicals). AI was applied across all fields of dentistry - particularly oral medicine, oral surgery, and orthodontics - for direct clinical inference and segmentation. AI-based image analysis was use in several components of the clinical decision-making process, including diagnosis, detection or classification, prediction, and management.

CONCLUSIONS

A variety of machine learning and deep learning techniques are being used for dental image analysis to assist clinicians in making accurate diagnoses and choosing appropriate interventions in a timely manner.

Engineering with Biomedical Sciences Changing the Horizon of Healthcare-A Review

In the dynamic realm of healthcare, the convergence of engineering and biomedical sciences has emerged as a pivotal frontier. In this review we go into specific areas of innovation, including medical imaging and diagnosis, developments in biomedical sensors, and drug delivery systems. Wearable biosensors, non-wearable biosensors, and biochips, which include gene chips, protein chips, and cell chips, are all included in the scope of the topic that pertains to biomedical sensors. Extensive research is conducted on drug delivery systems, spanning topics such as the integration of computer modeling, the optimization of drug formulations, and the design of delivery devices. Furthermore, the paper investigates intelligent drug delivery methods, which encompass stimuli-responsive systems such as temperature, redox, pH, light, enzyme, and magnetic responsive systems. In addition to that, the review goes into topics such as tissue engineering, regenerative medicine, biomedical robotics, automation, biomechanics, and the utilization of green biomaterials. The purpose of this analysis is to provide insights that will enhance continuing research and development efforts in engineering-driven biomedical breakthroughs, ultimately contributing to the improvement of healthcare. These insights will be provided by addressing difficulties and highlighting future prospects.

Two-stage deep learning framework for occlusal crown depth image generation

The generation of depth images of occlusal dental crowns is complicated by the need for customization in each case. To decrease the workload of skilled dental technicians, various computer vision models have been used to generate realistic occlusal crown depth images with definite crown surface structures that can ultimately be reconstructed to three-dimensional crowns and directly used in patient treatment. However, it has remained difficult to generate images of the structure of dental crowns in a fluid position using computer vision models. In this paper, we propose a two-stage model for generating depth images of occlusal crowns in diverse positions. The model is divided into two parts: segmentation and inpainting to obtain both shape and surface structure accuracy. The segmentation network focuses on the position and size of the crowns, which allows the model to adapt to diverse targets. The inpainting network based on a GAN generates curved structures of the crown surfaces based on the target jaw image and a binary mask made by the segmentation network. The performance of the model is evaluated via quantitative metrics for the area detection and pixel-value metrics. Compared to the baseline model, the proposed method reduced the MSE score from 0.007001 to 0.002618 and increased DICE score from 0.9333 to 0.9648. It indicates that the model showed better performance in terms of the binary mask from the addition of the segmentation network and the internal structure through the use of inpainting networks. Also, the results demonstrated an improved ability of the proposed model to restore realistic details compared to other models.

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.

Geo-Net: Geometry-Guided Pretraining for Tooth Point Cloud Segmentation

Accurately delineating individual teeth in 3-dimensional tooth point clouds is an important orthodontic application. Learning-based segmentation methods rely on labeled datasets, which are typically limited in scale due to the labor-intensive process of annotating each tooth. In this article, we propose a self-supervised pretraining framework, named Geo-Net, to boost segmentation performance by leveraging large-scale unlabeled data. The framework is based on the scalable masked autoencoders, and 2 geometry-guided designs, curvature-aware patching algorithm (CPA) and scale-aware reconstruction (SCR), are proposed to enhance the masked pretraining for tooth point cloud segmentation. In particular, CPA is designed to assemble informative patches as the reconstruction unit, guided by the estimated pointwise curvatures. Aimed at equipping the pretrained encoder with scale-aware modeling capacity, we also propose SCR to perform multiple reconstructions across shallow and deep layers. In vitro experiments reveal that after pretraining with large-scale unlabeled data, the proposed Geo-Net can outperform the supervised counterparts in mean Intersection of Union (mIoU) with the same amount of annotated labeled data. The code and data are available at https://github.com/yifliu3/Geo-Net.

Robust Segmentation of Partial and Imperfect Dental Arches

Automatic and accurate dental arch segmentation is a fundamental task in computer-aided dentistry. Recent trends in digital dentistry are tackling the design of 3D crowns using artificial intelligence, which initially requires a proper semantic segmentation of teeth from intraoral scans (IOS). In practice, most IOS are partial with as few as three teeth on the scanned arch, and some of them might have preparations, missing, or incomplete teeth. Existing deep learning-based methods (e.g., MeshSegNet, DArch) were proposed for dental arch segmentation, but they are not as efficient for partial arches that include imperfections such as missing teeth and preparations. In this work, we present the ArchSeg framework that can leverage various deep learning models for semantic segmentation of perfect and imperfect dental arches. The Point Transformer V2 deep learning model is used as the backbone for the ArchSeg framework. We present experiments to demonstrate the efficiency of the proposed framework to segment arches with various types of imperfections. Using a raw dental arch scan with two labels indicating the range of present teeth in the arch (i.e., the first and the last teeth), our ArchSeg can segment a standalone dental arch or a pair of aligned master/antagonist arches with more available information (i.e., die mesh). Two generic models are trained for lower and upper arches; they achieve dice similarity coefficient scores of 0.936±0.008 and 0.948±0.007, respectively, on test sets composed of challenging imperfect arches. Our work also highlights the impact of appropriate data pre-processing and post-processing on the final segmentation performance. Our ablation study shows that the segmentation performance of the Point Transformer V2 model integrated in our framework is improved compared with the original standalone model.

Finite element models: A road to in-silico modeling in the age of personalized dentistry

OBJECTIVE

This article reviews the applications of Finite Element Models (FEMs) in personalized dentistry, focusing on treatment planning, material selection, and CAD-CAM processes. It also discusses the challenges and future directions of using finite element analysis (FEA) in dental care.

DATA

This study synthesizes current literature and case studies on FEMs in personalized dentistry, analyzing research articles, clinical reports, and technical papers on the application of FEA in dental biomechanics.

SOURCES

Sources for this review include peer-reviewed journals, academic publications, clinical case studies, and technical papers on dental biomechanics and finite element analysis. Key databases such as PubMed, Scopus, Embase, and ArXiv were used to identify relevant studies.

STUDY SELECTION

Studies were selected based on their relevance to the application of FEMs in personalized dentistry. Inclusion criteria were studies that discussed the use of FEA in treatment planning, material selection, and CAD-CAM processes in dentistry. Exclusion criteria included studies that did not focus on personalized dental treatments or did not utilize FEMs as a primary tool.

CONCLUSIONS

FEMs are essential for personalized dentistry, offering a versatile platform for in-silico dental biomechanics modeling. They can help predict biomechanical behavior, optimize treatment outcomes, and minimize clinical complications. Despite needing further advancements, FEMs could help significantly enhance treatment precision and efficacy in personalized dental care.

CLINICAL SIGNIFICANCE

FEMs in personalized dentistry hold the potential to significantly improve treatment precision and efficacy, optimizing outcomes and reducing complications. Their integration underscores the need for interdisciplinary collaboration and advancements in computational techniques to enhance personalized dental care.

Exploring the Applications of Artificial Intelligence in Dental Image Detection: A Systematic Review

BACKGROUND

Dental care has been transformed by neural networks, introducing advanced methods for improving patient outcomes. By leveraging technological innovation, dental informatics aims to enhance treatment and diagnostic processes. Early diagnosis of dental problems is crucial, as it can substantially reduce dental disease incidence by ensuring timely and appropriate treatment. The use of artificial intelligence (AI) within dental informatics is a pivotal tool that has applications across all dental specialties. This systematic literature review aims to comprehensively summarize existing research on AI implementation in dentistry. It explores various techniques used for detecting oral features such as teeth, fillings, caries, prostheses, crowns, implants, and endodontic treatments. AI plays a vital role in the diagnosis of dental diseases by enabling precise and quick identification of issues that may be difficult to detect through traditional methods. Its ability to analyze large volumes of data enhances diagnostic accuracy and efficiency, leading to better patient outcomes.

METHODS

An extensive search was conducted across a number of databases, including Science Direct, PubMed (MEDLINE), arXiv.org, MDPI, Nature, Web of Science, Google Scholar, Scopus, and Wiley Online Library.

RESULTS

The studies included in this review employed a wide range of neural networks, showcasing their versatility in detecting the dental categories mentioned above. Additionally, the use of diverse datasets underscores the adaptability of these AI models to different clinical scenarios. This study highlights the compatibility, robustness, and heterogeneity among the reviewed studies. This indicates that AI technologies can be effectively integrated into current dental practices. The review also discusses potential challenges and future directions for AI in dentistry. It emphasizes the need for further research to optimize these technologies for broader clinical applications.

CONCLUSIONS

By providing a detailed overview of AI's role in dentistry, this review aims to inform practitioners and researchers about the current capabilities and future potential of AI-driven dental care, ultimately contributing to improved patient outcomes and more efficient dental practices.

LMVSegRNN and Poseidon3D: Addressing Challenging Teeth Segmentation Cases in 3D Dental Surface Orthodontic Scans

The segmentation of teeth in 3D dental scans is difficult due to variations in teeth shapes, misalignments, occlusions, or the present dental appliances. Existing methods consistently adhere to geometric representations, omitting the perceptual aspects of the inputs. In addition, current works often lack evaluation on anatomically complex cases due to the unavailability of such datasets. We present a projection-based approach towards accurate teeth segmentation that operates in a detect-and-segment manner locally on each tooth in a multi-view fashion. Information is spatially correlated via recurrent units. We show that a projection-based framework can precisely segment teeth in cases with anatomical anomalies with negligible information loss. It outperforms point-based, edge-based, and Graph Cut-based geometric approaches, achieving an average weighted IoU score of 0.97122±0.038 and a Hausdorff distance at 95 percentile of 0.49012±0.571 mm. We also release Poseidon's Teeth 3D (Poseidon3D), a novel dataset of real orthodontic cases with various dental anomalies like teeth crowding and missing teeth.

Accuracy of Tooth Segmentation in the Digital Kesling Setup of Two Different Software Programs: A Retrospective Study

Introduction Precise virtual setup creation and orthodontic appliance fabrication depend on accurate teeth segmentation from intraoral scans. This accuracy is also fundamental for successful orthodontic treatment, as it ensures correct diagnosis and optimal treatment planning. A number of software packages that facilitate the building of virtual setups have been made available in recent years. The performance of these software packages on automatic tooth segmentation has not been widely studied. Hence, the aim of this study was to evaluate the accuracy of automated teeth segmentation in the digital Kesling setup of Ortho Studio (Maestro 3D Dental Studio, Bordeaux, France) and OrthoAnalyzer (3Shape, Copenhagen, Denmark) software systems. Materials and methods All the scans were taken from the same intraoral scanner (Runyes 3D intraoral scanner; Runyes Medical, Ningbo, China). The scans were stored and imported as stereolithography (STL) files into the Maestro Ortho Studio and 3Shape OrthoAnalyzer software systems. Subsequently, the digital photos underwent alignment in both software applications, an essential stage in each respective workflow prior to any further processing. The digitized images were automatically segmented in Maestro and 3Shape software by a single researcher. For each software interface, the accuracy of teeth segmentation was assessed. An independent t-test, with a significance level set at p < 0.05, was used to evaluate the statistical significance between the two software segmentations. Results The total number of teeth segmented by both software programs utilizing the 12 intraoral scans was 336 for both groups. Successful identification of the tooth segments was 98.21% (n = 330) for 3Shape software and 98.8% (n = 332) for Maestro software. There was no significant difference in the accuracy of determining the tooth segmentations between anterior and posterior teeth, respectively, between both groups, with a p-value of 0.523. Conclusion There were no statistically significant differences between the two software programs, and both demonstrated high success rates for auto-tooth segmentation. Although both programs had excellent success rates, Maestro 3D performed more accurately than 3Shape OrthoAnalyzer.

AI-Driven Innovations in Pediatric Dentistry: Enhancing Care and Improving Outcome

Artificial intelligence (AI) is transforming pediatric dentistry by enhancing diagnostic accuracy, streamlining treatment planning, and improving behavior management. This review explores current AI applications in detecting dental anomalies, categorizing fissure sealants, assessing chronological age, and managing patient behavior. The review also identifies emerging trends and future directions in AI technology that promise to further revolutionize pediatric dental care. By synthesizing recent research and clinical studies, this review aimed to inform dental professionals and researchers about the potential of AI to address traditional challenges and improve oral health outcomes for children.

DilatedToothSegNet: Tooth Segmentation Network on 3D Dental Meshes Through Increasing Receptive Vision

The utilization of advanced intraoral scanners to acquire 3D dental models has gained significant popularity in the fields of dentistry and orthodontics. Accurate segmentation and labeling of teeth on digitized 3D dental surface models are crucial for computer-aided treatment planning. At the same time, manual labeling of these models is a time-consuming task. Recent advances in geometric deep learning have demonstrated remarkable efficiency in surface segmentation when applied to raw 3D models. However, segmentation of the dental surface remains challenging due to the atypical and diverse appearance of the patients' teeth. Numerous deep learning methods have been proposed to automate dental surface segmentation. Nevertheless, they still show limitations, particularly in cases where teeth are missing or severely misaligned. To overcome these challenges, we introduce a network operator called dilated edge convolution, which enhances the network's ability to learn additional, more distant features by expanding its receptive field. This leads to improved segmentation results, particularly in complex and challenging cases. To validate the effectiveness of our proposed method, we performed extensive evaluations on the recently published benchmark data set for dental model segmentation Teeth3DS. We compared our approach with several other state-of-the-art methods using a quantitative and qualitative analysis. Through these evaluations, we demonstrate the superiority of our proposed method, showcasing its ability to outperform existing approaches in dental surface segmentation.

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.

Automatic removal of soft tissue from 3D dental photo scans; an important step in automating future forensic odontology identification

The potential of intraoral 3D photo scans in forensic odontology identification remains largely unexplored, even though the high degree of detail could allow automated comparison of ante mortem and post mortem dentitions. Differences in soft tissue conditions between ante- and post mortem intraoral 3D photo scans may cause ambiguous variation, burdening the potential automation of the matching process and underlining the need for limiting inclusion of soft tissue in dental comparison. The soft tissue removal must be able to handle dental arches with missing teeth, and intraoral 3D photo scans not originating from plaster models. To address these challenges, we have developed the grid-cutting method. The method is customisable, allowing fine-grained analysis using a small grid size and adaptation of how much of the soft tissues are excluded from the cropped dental scan. When tested on 66 dental scans, the grid-cutting method was able to limit the amount of soft tissue without removing any teeth in 63/66 dental scans. The remaining 3 dental scans had partly erupted third molars (wisdom teeth) which were removed by the grid-cutting method. Overall, the grid-cutting method represents an important step towards automating the matching process in forensic odontology identification using intraoral 3D photo scans.

Deep learning-based tooth segmentation methods in medical imaging: A review

Deep learning approaches for tooth segmentation employ convolutional neural networks (CNNs) or Transformers to derive tooth feature maps from extensive training datasets. Tooth segmentation serves as a critical prerequisite for clinical dental analysis and surgical procedures, enabling dentists to comprehensively assess oral conditions and subsequently diagnose pathologies. Over the past decade, deep learning has experienced significant advancements, with researchers introducing efficient models such as U-Net, Mask R-CNN, and Segmentation Transformer (SETR). Building upon these frameworks, scholars have proposed numerous enhancement and optimization modules to attain superior tooth segmentation performance. This paper discusses the deep learning methods of tooth segmentation on dental panoramic radiographs (DPRs), cone-beam computed tomography (CBCT) images, intro oral scan (IOS) models, and others. Finally, we outline performance-enhancing techniques and suggest potential avenues for ongoing research. Numerous challenges remain, including data annotation and model generalization limitations. This paper offers insights for future tooth segmentation studies, potentially facilitating broader clinical adoption.

Tooth Alignment Network Based on Landmark Constraints and Hierarchical Graph Structure

Automatic tooth alignment target prediction is vital in shortening the planning time of orthodontic treatments and aligner designs. Generally, the quality of alignment targets greatly depends on the experience and ability of dentists and has enormous subjective factors. Therefore, many knowledge-driven alignment prediction methods have been proposed to help inexperienced dentists. Unfortunately, existing methods tend to directly regress tooth motion, which lacks clinical interpretability. Tooth anatomical landmarks play a critical role in orthodontics because they are effective in aiding the assessment of whether teeth are in close arrangement and normal occlusion. Thus, we consider anatomical landmark constraints to improve tooth alignment results. In this article, we present a novel tooth alignment neural network for alignment target predictions based on tooth landmark constraints and a hierarchical graph structure. We detect the landmarks of each tooth first and then construct a hierarchical graph of jaw-tooth-landmark to characterize the relationship between teeth and landmarks. Then, we define the landmark constraints to guide the network to learn the normal occlusion and predict the rigid transformation of each tooth during alignment. Our method achieves better results with the architecture built for tooth data and landmark constraints and has better explainability than previous methods with regard to clinical tooth alignments.

Deep learning for virtual orthodontic bracket removal: tool establishment and application

OBJECTIVE

We aimed to develop a tool for virtual orthodontic bracket removal based on deep learning algorithms for feature extraction from bonded teeth and to demonstrate its application in a bracket position assessment scenario.

MATERIALS AND METHODS

Our segmentation network for virtual bracket removal was trained using dataset A, containing 978 bonded teeth, 20 original teeth, and 20 brackets generated by scanners. The accuracy and segmentation time of the network were tested by dataset B, which included an additional 118 bonded teeth without knowing the original tooth morphology. This tool was then applied for bracket position assessment. The clinical crown center, bracket center, and orientations of separated teeth and brackets were extracted for analyzing the linear distribution and angular deviation of bonded brackets.

RESULTS

This tool performed virtual bracket removal in 2.9 ms per tooth with accuracies of 98.93% and 97.42% (P < 0.01) in datasets A and B, respectively. The tooth surface and bracket characteristics were extracted and used to evaluate the results of manually bonded brackets by 49 orthodontists. Personal preferences for bracket angulation and bracket distribution were displayed graphically and tabularly.

CONCLUSIONS

The tool's efficiency and precision are satisfactory, and it can be operated without original tooth data. It can be used to display the bonding deviation in the bracket position assessment scenario.

CLINICAL SIGNIFICANCE

With the aid of this tool, unnecessary bracket removal can be avoided when evaluating bracket positions and modifying treatment plans. It has the potential to produce retainers and orthodontic devices prior to tooth debonding.

Endoscopic versus laparoscopic bariatric procedures: A computational biomechanical study through a patient-specific approach

BACKGROUND AND OBJECTIVES

Within the framework of computational biomechanics, finite element models of the gastric district could be seen as a potential clinical tool not only to study the effects apported by bariatric surgery, but also to compare different surgical techniques such as the new emerging Endoscopic Sleeve Gastroplasty (ESG) with respect to well-established ones (such as the Laparoscopic Sleeve Gastrectomy, LSG).

METHODS

This work realized a fully computational comparison between the outcomes obtained from 10 patient-specific stomach models, which were used to simulate ESG, and the complementary results obtained from models representing the post-LSG of the same subjects. Specifically, once the ESG was simulated, a mechanical stimulus was applied by increasing an intragastric pressure up to a maximum of 5 kPa, in order to replicate the process of food intake, as well as for post-LSG models.

RESULTS

Results revealed non negligible differences between the techniques also within the same subject. In particular, not only LSG could lead to a greater reduction in the stomach volume (about 77 % at baseline, which is strictly linked to weight loss), but also influence the gastric distension (12 % less than pre-operative models). On the contrary, if ESG would be performed, a more similar pre-operative mechanical stimulation of the gastric walls may be seen (difference of about 1 %), thus preserving the mechanosensation, but the detriment of the volume reduction (about 56 % at baseline, and even decreases with increasing pressure). Moreover, since results suggested ESG may be more influenced by the pre-operative gastric cavity than LSG, a predictive model was proposed to support the surgical planning and the estimation of the volume reduction after ESG.

CONCLUSIONS

ESG and LSG have substantial differences in their protocols and post-surgical effects. This work pointed out that variations between the two procedures may be observed also from a computational point of view, especially when including patient-specific geometries. These insights support gastric modelling as a valuable tool to evaluate, design and critically compare emerging bariatric surgical procedures, not only from empirical aspects and clinical outcomes, but also from a mechanical point of view.

A fine-grained orthodontics segmentation model for 3D intraoral scan data

With the widespread application of digital orthodontics in the diagnosis and treatment of oral diseases, more and more researchers focus on the accurate segmentation of teeth from intraoral scan data. The accuracy of the segmentation results will directly affect the follow-up diagnosis of dentists. Although the current research on tooth segmentation has achieved promising results, the 3D intraoral scan datasets they use are almost all indirect scans of plaster models, and only contain limited samples of abnormal teeth, so it is difficult to apply them to clinical scenarios under orthodontic treatment. The current issue is the lack of a unified and standardized dataset for analyzing and validating the effectiveness of tooth segmentation. In this work, we focus on deformed teeth segmentation and provide a fine-grained tooth segmentation dataset (3D-IOSSeg). The dataset consists of 3D intraoral scan data from more than 200 patients, with each sample labeled with a fine-grained mesh unit. Meanwhile, 3D-IOSSeg meticulously classified every tooth in the upper and lower jaws. In addition, we propose a fast graph convolutional network for 3D tooth segmentation named Fast-TGCN. In the model, the relationship between adjacent mesh cells is directly established by the naive adjacency matrix to better extract the local geometric features of the tooth. Extensive experiments show that Fast-TGCN can quickly and accurately segment teeth from the mouth with complex structures and outperforms other methods in various evaluation metrics. Moreover, we present the results of multiple classical tooth segmentation methods on this dataset, providing a comprehensive analysis of the field. All code and data will be available at https://github.com/MIVRC/Fast-TGCN.

DTR-Net: Dual-Space 3D Tooth Model Reconstruction From Panoramic X-Ray Images

In digital dentistry, cone-beam computed tomography (CBCT) can provide complete 3D tooth models, yet suffers from a long concern of requiring excessive radiation dose and higher expense. Therefore, 3D tooth model reconstruction from 2D panoramic X-ray image is more cost-effective, and has attracted great interest in clinical applications. In this paper, we propose a novel dual-space framework, namely DTR-Net, to reconstruct 3D tooth model from 2D panoramic X-ray images in both image and geometric spaces. Specifically, in the image space, we apply a 2D-to-3D generative model to recover intensities of CBCT image, guided by a task-oriented tooth segmentation network in a collaborative training manner. Meanwhile, in the geometric space, we benefit from an implicit function network in the continuous space, learning using points to capture complicated tooth shapes with geometric properties. Experimental results demonstrate that our proposed DTR-Net achieves state-of-the-art performance both quantitatively and qualitatively in 3D tooth model reconstruction, indicating its potential application in dental practice.

Connecting the dots towards precision orthodontics

Precision orthodontics entails the use of personalized clinical, biological, social and environmental knowledge of each patient for deep individualized clinical phenotyping and diagnosis combined with the delivery of care using advanced customized devices, technologies and biologics. From its historical origins as a mechanotherapy and materials driven profession, the most recent advances in orthodontics in the past three decades have been propelled by technological innovations including volumetric and surface 3D imaging and printing, advances in software that facilitate the derivation of diagnostic details, enhanced personalization of treatment plans and fabrication of custom appliances. Still, the use of these diagnostic and therapeutic technologies is largely phenotype driven, focusing mainly on facial/skeletal morphology and tooth positions. Future advances in orthodontics will involve comprehensive understanding of an individual's biology through omics, a field of biology that involves large-scale rapid analyses of DNA, mRNA, proteins and other biological regulators from a cell, tissue or organism. Such understanding will define individual biological attributes that will impact diagnosis, treatment decisions, risk assessment and prognostics of therapy. Equally important are the advances in artificial intelligence (AI) and machine learning, and its applications in orthodontics. AI is already being used to perform validation of approaches for diagnostic purposes such as landmark identification, cephalometric tracings, diagnosis of pathologies and facial phenotyping from radiographs and/or photographs. Other areas for future discoveries and utilization of AI will include clinical decision support, precision orthodontics, payer decisions and risk prediction. The synergies between deep 3D phenotyping and advances in materials, omics and AI will propel the technological and omics era towards achieving the goal of delivering optimized and predictable precision orthodontics.

Automatic Detection of Tooth-Gingiva Trim Lines on Dental Surfaces

Detecting the tooth-gingiva trim line from a dental surface plays a critical role in dental treatment planning and aligner 3D printing. Existing methods treat this task as a segmentation problem, which is resolved with geometric deep learning based mesh segmentation techniques. However, these methods can only provide indirect results (i.e., segmented teeth) and suffer from unsatisfactory accuracy due to the incapability of making full use of high-resolution dental surfaces. To this end, we propose a two-stage geometric deep learning framework for automatically detecting tooth-gingiva trim lines from dental surfaces. Our framework consists of a trim line proposal network (TLP-Net) for predicting an initial trim line from the low-resolution dental surface as well as a trim line refinement network (TLR-Net) for refining the initial trim line with the information from the high-resolution dental surface. Specifically, our TLP-Net predicts the initial trim line by fusing the multi-scale features from a U-Net with a proposed residual multi-scale attention fusion module. Moreover, we propose feature bridge modules and a trim line loss to further improve the accuracy. The resulting trim line is then fed to our TLR-Net, which is a deep-based LDDMM model with the high-resolution dental surface as input. In addition, dense connections are incorporated into TLR-Net for improved performance. Our framework provides an automatic solution to trim line detection by making full use of raw high-resolution dental surfaces. Extensive experiments on a clinical dental surface dataset demonstrate that our TLP-Net and TLR-Net are superior trim line detection methods and outperform cutting-edge methods in both qualitative and quantitative evaluations.

An artificial intelligence study: automatic description of anatomic landmarks on panoramic radiographs in the pediatric population

BACKGROUND

Panoramic radiographs, in which anatomic landmarks can be observed, are used to detect cases closely related to pediatric dentistry. The purpose of the study is to investigate the success and reliability of the detection of maxillary and mandibular anatomic structures observed on panoramic radiographs in children using artificial intelligence.

METHODS

A total of 981 mixed images of pediatric patients for 9 different pediatric anatomic landmarks including maxillary sinus, orbita, mandibular canal, mental foramen, foramen mandible, incisura mandible, articular eminence, condylar and coronoid processes were labelled, the training was carried out using 2D convolutional neural networks (CNN) architectures, by giving 500 training epochs and Pytorch-implemented YOLO-v5 models were produced. The success rate of the AI model prediction was tested on a 10% test data set.

RESULTS

A total of 14,804 labels including maxillary sinus (1922), orbita (1944), mandibular canal (1879), mental foramen (884), foramen mandible (1885), incisura mandible (1922), articular eminence (1645), condylar (1733) and coronoid (990) processes were made. The most successful F1 Scores were obtained from orbita (1), incisura mandible (0.99), maxillary sinus (0.98), and mandibular canal (0.97). The best sensitivity values were obtained from orbita, maxillary sinus, mandibular canal, incisura mandible, and condylar process. The worst sensitivity values were obtained from mental foramen (0.92) and articular eminence (0.92).

CONCLUSIONS

The regular and standardized labelling, the relatively larger areas, and the success of the YOLO-v5 algorithm contributed to obtaining these successful results. Automatic segmentation of these structures will save time for physicians in clinical diagnosis and will increase the visibility of pathologies related to structures and the awareness of physicians.

Measurement of proximal contact of single crowns to assess interproximal relief: A pilot study

Background

It is common for dental technicians to adjust the proximal surface of adjacent teeth on casts when fabricating single crowns. However, whether the accuracy of the proximal contact is affected if this step is eliminated is unclear.

Objective

To evaluate the accuracy of the proximal contact of single crowns for mandibular first molars fabricated from four different restorative materials, without adjustment of the proximal surface of the adjacent teeth by the laboratory/dental technician.

Methods

This study was in vitro; all the clinical procedures were conducted on a dentoform. The mandibular first molar tooth on the dentoform was prepared using diamond burs and a high speed handpiece. Twenty single crowns were fabricated, five for each group (monolithic zirconia, lithium disilicate, metal ceramic, and cast gold). No proximal surface adjacent to the definitive crowns was adjusted for tight contact in the dental laboratory. Both the qualitative analyses, using dental floss and shimstock, and the quantitative analyses, using a stereo microscope, were performed to evaluate the accuracy of the proximal contact of the restoration with the adjacent teeth. In the quantitative analysis, one-way analysis of variance was used to compare mean values at a significance level of 0.05.

Results

In quantitative analysis, the differences between the proximal contact tightness of the four groups was not statistically significant (P = 0.802 for mesial contacts, P = 0.354 for distal contacts). In qualitative analysis, in most crowns, dental floss passed through the contact with tight resistance and only one film of shimstock could be inserted between the adjacent teeth and the restoration. However, one specimen from the cast gold crown had open contact.

Conclusions

Even without proximal surface adjustment of the adjacent teeth during the crown fabrication process, adequate proximal contact tightness between the restoration and adjacent teeth could be achieved.

Denoised encoder-based residual U-net for precise teeth image segmentation and damage prediction on panoramic radiographs

OBJECTIVES

This research focuses on performing teeth segmentation with panoramic radiograph images using a denoised encoder-based residual U-Net model, which enhances segmentation techniques and has the capacity to adapt to predictions with different and new data in the dataset, making the proposed model more robust and assisting in the accurate identification of damages in individual teeth.

METHODS

The effective segmentation starts with pre-processing the Tufts dataset to resize images to avoid computational complexities. Subsequently, the prediction of the defect in teeth is performed with the denoised encoder block in the residual U-Net model, in which a modified identity block is provided in the encoder section for finer segmentation on specific regions in images, and features are identified optimally. The denoised block aids in handling noisy ground truth images effectively.

RESULTS

Proposed module achieved greater values of mean dice and mean IoU with 98.90075 and 98.74147 CONCLUSIONS: Proposed AI enabled model permitted a precise approach to segment the teeth on Tuffs dental dataset in spite of the existence of densed dental filling and the kind of tooth.

CLINICAL SIGNIFICANCE

The proposed model is pivotal for improved dental diagnostics, offering precise identification of dental anomalies. This could revolutionize clinical dental settings by facilitating more accurate treatments and safer examination processes with lower radiation exposure, thus enhancing overall patient care.

Deep learning-enabled 3D multimodal fusion of cone-beam CT and intraoral mesh scans for clinically applicable tooth-bone reconstruction

High-fidelity three-dimensional (3D) models of tooth-bone structures are valuable for virtual dental treatment planning; however, they require integrating data from cone-beam computed tomography (CBCT) and intraoral scans (IOS) using methods that are either error-prone or time-consuming. Hence, this study presents Deep Dental Multimodal Fusion (DDMF), an automatic multimodal framework that reconstructs 3D tooth-bone structures using CBCT and IOS. Specifically, the DDMF framework comprises CBCT and IOS segmentation modules as well as a multimodal reconstruction module with novel pixel representation learning architectures, prior knowledge-guided losses, and geometry-based 3D fusion techniques. Experiments on real-world large-scale datasets revealed that DDMF achieved superior segmentation performance on CBCT and IOS, achieving a 0.17 mm average symmetric surface distance (ASSD) for 3D fusion with a substantial processing time reduction. Additionally, clinical applicability studies have demonstrated DDMF's potential for accurately simulating tooth-bone structures throughout the orthodontic treatment process.

Hierarchical Self-Supervised Learning for 3D Tooth Segmentation in Intra-Oral Mesh Scans

Accurately delineating individual teeth and the gingiva in the three-dimension (3D) intraoral scanned (IOS) mesh data plays a pivotal role in many digital dental applications, e.g., orthodontics. Recent research shows that deep learning based methods can achieve promising results for 3D tooth segmentation, however, most of them rely on high-quality labeled dataset which is usually of small scales as annotating IOS meshes requires intensive human efforts. In this paper, we propose a novel self-supervised learning framework, named STSNet, to boost the performance of 3D tooth segmentation leveraging on large-scale unlabeled IOS data. The framework follows two-stage training, i.e., pre-training and fine-tuning. In pre-training, three hierarchical-level, i.e., point-level, region-level, cross-level, contrastive losses are proposed for unsupervised representation learning on a set of predefined matched points from different augmented views. The pretrained segmentation backbone is further fine-tuned in a supervised manner with a small number of labeled IOS meshes. With the same amount of annotated samples, our method can achieve an mIoU of 89.88%, significantly outperforming the supervised counterparts. The performance gain becomes more remarkable when only a small amount of labeled samples are available. Furthermore, STSNet can achieve better performance with only 40% of the annotated samples as compared to the fully supervised baselines. To the best of our knowledge, we present the first attempt of unsupervised pre-training for 3D tooth segmentation, demonstrating its strong potential in reducing human efforts for annotation and verification.

Machine Learning in Dentistry: A Scoping Review

Machine learning (ML) is being increasingly employed in dental research and application. We aimed to systematically compile studies using ML in dentistry and assess their methodological quality, including the risk of bias and reporting standards. We evaluated studies employing ML in dentistry published from 1 January 2015 to 31 May 2021 on MEDLINE, IEEE Xplore, and arXiv. We assessed publication trends and the distribution of ML tasks (classification, object detection, semantic segmentation, instance segmentation, and generation) in different clinical fields. We appraised the risk of bias and adherence to reporting standards, using the QUADAS-2 and TRIPOD checklists, respectively. Out of 183 identified studies, 168 were included, focusing on various ML tasks and employing a broad range of ML models, input data, data sources, strategies to generate reference tests, and performance metrics. Classification tasks were most common. Forty-two different metrics were used to evaluate model performances, with accuracy, sensitivity, precision, and intersection-over-union being the most common. We observed considerable risk of bias and moderate adherence to reporting standards which hampers replication of results. A minimum (core) set of outcome and outcome metrics is necessary to facilitate comparisons across studies.

An Explainable Deep Learning Model to Prediction Dental Caries Using Panoramic Radiograph Images

Dental caries is the most frequent dental health issue in the general population. Dental caries can result in extreme pain or infections, lowering people's quality of life. Applying machine learning models to automatically identify dental caries can lead to earlier treatment. However, physicians frequently find the model results unsatisfactory due to a lack of explainability. Our study attempts to address this issue with an explainable deep learning model for detecting dental caries. We tested three prominent pre-trained models, EfficientNet-B0, DenseNet-121, and ResNet-50, to determine which is best for the caries detection task. These models take panoramic images as the input, producing a caries-non-caries classification result and a heat map, which visualizes areas of interest on the tooth. The model performance was evaluated using whole panoramic images of 562 subjects. All three models produced remarkably similar results. However, the ResNet-50 model exhibited a slightly better performance when compared to EfficientNet-B0 and DenseNet-121. This model obtained an accuracy of 92.00%, a sensitivity of 87.33%, and an F1-score of 91.61%. Visual inspection showed us that the heat maps were also located in the areas with caries. The proposed explainable deep learning model diagnosed dental caries with high accuracy and reliability. The heat maps help to explain the classification results by indicating a region of suspected caries on the teeth. Dentists could use these heat maps to validate the classification results and reduce misclassification.

A weakly supervised learning-based segmentation network for dental diseases

With the development of deep learning, medical image segmentation has become a promising technique for computer-aided medical diagnosis. However, the supervised training of the algorithm relies on a large amount of labeled data, and the private dataset bias generally exists in previous research, which seriously affects the algorithm's performance. In order to alleviate this problem and improve the robustness and generalization of the model, this paper proposes an end-to-end weakly supervised semantic segmentation network to learn and infer mappings. Firstly, an attention compensation mechanism (ACM) aggregating the class activation map (CAM) is designed to learn complementarily. Then the conditional random field (CRF) is introduced to prune the foreground and background regions. Finally, the obtained high-confidence regions are used as pseudo labels for the segmentation branch to train and optimize using a joint loss function. Our model achieves a Mean Intersection over Union (MIoU) score of 62.84% in the segmentation task, which is an effective improvement of 11.18% compared to the previous network for segmenting dental diseases. Moreover, we further verify that our model has higher robustness to dataset bias by improved localization mechanism (CAM). The research shows that our proposed approach improves the accuracy and robustness of dental disease identification.

Artificial Intelligence in Diagnosis of Oral Diseases: A Systematic Review

AIM

To understand the role of Artificial intelligence (AI) in oral radiology and its applications.

BACKGROUND

Over the last two decades, the field of AI has undergone phenomenal progression and expansion. Artificial intelligence applications have taken up new roles in dentistry like digitized data acquisition and machine learning and diagnostic applications.

MATERIALS AND METHODS

All research papers outlining the population, intervention, control, and outcomes (PICO) questions were searched for in PubMed, ERIC, Embase, CINAHL, database from the last 10 years on first January 2023. Two authors independently reviewed the titles and abstracts of the selected studies, and any discrepancy between the two review authors was handled by a third reviewer. Two independent investigators evaluated all the included studies for the quality assessment using the modified tool for the quality assessment of diagnostic accuracy studies (QUADAS- 2).

REVIEW RESULTS

After the removal of duplicates and screening of titles and abstracts, 18 full texts were agreed upon for further evaluation, of which 14 that met the inclusion criteria were included in this review. The application of artificial intelligence models has primarily been reported on osteoporosis diagnosis, classification/segmentation of maxillofacial cysts and/or tumors, and alveolar bone resorption. Overall study quality was deemed to be high for two (14%) studies, moderate for six (43%) studies, and low for another six (43%) studies.

CONCLUSION

The use of AI for patient diagnosis and clinical decision-making can be accomplished with relative ease, and the technology should be regarded as a reliable modality for potential future applications in oral diagnosis.

Robust Mesh Segmentation Using Feature-Aware Region Fusion

This paper introduces a simple but powerful segmentation algorithm for 3D meshes. Our algorithm consists of two stages: over-segmentation and region fusion. In the first stage, adaptive space partition is applied to perform over-segmentation, which is very efficient. In the second stage, we define a new intra-region difference, inter-region difference, and fusion condition with the help of various shape features and propose an iterative region fusion method. As the region fusion process is feature aware, our algorithm can deal with complex 3D meshes robustly. Massive qualitative and quantitative experiments also validate the advantages of the proposed algorithm.

Improving performance of deep learning models using 3.5D U-Net via majority voting for tooth segmentation on cone beam computed tomography

Deep learning allows automatic segmentation of teeth on cone beam computed tomography (CBCT). However, the segmentation performance of deep learning varies among different training strategies. Our aim was to propose a 3.5D U-Net to improve the performance of the U-Net in segmenting teeth on CBCT. This study retrospectively enrolled 24 patients who received CBCT. Five U-Nets, including 2Da U-Net, 2Dc U-Net, 2Ds U-Net, 2.5Da U-Net, 3D U-Net, were trained to segment the teeth. Four additional U-Nets, including 2.5Dv U-Net, 3.5Dv5 U-Net, 3.5Dv4 U-Net, and 3.5Dv3 U-Net, were obtained using majority voting. Mathematical morphology operations including erosion and dilation (E&D) were applied to remove diminutive noise speckles. Segmentation performance was evaluated by fourfold cross validation using Dice similarity coefficient (DSC), accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV). Kruskal-Wallis test with post hoc analysis using Bonferroni correction was used for group comparison. P < 0.05 was considered statistically significant. Performance of U-Nets significantly varies among different training strategies for teeth segmentation on CBCT (P < 0.05). The 3.5Dv5 U-Net and 2.5Dv U-Net showed DSC and PPV significantly higher than any of five originally trained U-Nets (all P < 0.05). E&D significantly improved the DSC, accuracy, specificity, and PPV (all P < 0.005). The 3.5Dv5 U-Net achieved highest DSC and accuracy among all U-Nets. The segmentation performance of the U-Net can be improved by majority voting and E&D. Overall speaking, the 3.5Dv5 U-Net achieved the best segmentation performance among all U-Nets.

Advancements in Dentistry with Artificial Intelligence: Current Clinical Applications and Future Perspectives

Artificial intelligence has been widely used in the field of dentistry in recent years. The present study highlights current advances and limitations in integrating artificial intelligence, machine learning, and deep learning in subfields of dentistry including periodontology, endodontics, orthodontics, restorative dentistry, and oral pathology. This article aims to provide a systematic review of current clinical applications of artificial intelligence within different fields of dentistry. The preferred reporting items for systematic reviews (PRISMA) statement was used as a formal guideline for data collection. Data was obtained from research studies for 2009-2022. The analysis included a total of 55 papers from Google Scholar, IEEE, PubMed, and Scopus databases. Results show that artificial intelligence has the potential to improve dental care, disease diagnosis and prognosis, treatment planning, and risk assessment. Finally, this study highlights the limitations of the analyzed studies and provides future directions to improve dental care.

Application of deep learning artificial intelligence technique to the classification of clinical orthodontic photos

BACKGROUND

Taking facial and intraoral clinical photos is one of the essential parts of orthodontic diagnosis and treatment planning. Among the diagnostic procedures, classification of the shuffled clinical photos with their orientations will be the initial step while it was not easy for a machine to classify photos with a variety of facial and dental situations. This article presents a convolutional neural networks (CNNs) deep learning technique to classify orthodontic clinical photos according to their orientations.

METHODS

To build an automated classification system, CNNs models of facial and intraoral categories were constructed, and the clinical photos that are routinely taken for orthodontic diagnosis were used to train the models with data augmentation. Prediction procedures were evaluated with separate photos whose purpose was only for prediction.

RESULTS

Overall, a 98.0% valid prediction rate resulted for both facial and intraoral photo classification. The highest prediction rate was 100% for facial lateral profile, intraoral upper, and lower photos.

CONCLUSION

An artificial intelligence system that utilizes deep learning with proper training models can successfully classify orthodontic facial and intraoral photos automatically. This technique can be used for the first step of a fully automated orthodontic diagnostic system in the future.

A Tooth Segmentation Method Based on Multiple Geometric Feature Learning

Tooth segmentation is an important aspect of virtual orthodontic systems. In some existing studies using deep learning-based tooth segmentation methods, the feature learning of point coordinate information and normal vector information is not effectively distinguished. This will lead to the feature information of these two methods not producing complementary intermingling. To address this problem, a tooth segmentation method based on multiple geometric feature learning is proposed in this paper. First, the spatial transformation (T-Net) module is used to complete the alignment of dental model mesh features. Second, a multiple geometric feature learning module is designed to encode and enhance the centroid coordinates and normal vectors of each triangular mesh to highlight the differences between geometric features of different meshes. Finally, for local to global fusion features, feature downscaling and channel optimization are accomplished layer by layer using multilayer perceptron (MLP) and efficient channel attention (ECA). The experimental results show that our algorithm achieves better accuracy and efficiency of tooth segmentation and can assist dentists in their treatment work.

Transformer-Based Deep Learning Network for Tooth Segmentation on Panoramic Radiographs

Panoramic radiographs can assist dentist to quickly evaluate patients' overall oral health status. The accurate detection and localization of tooth tissue on panoramic radiographs is the first step to identify pathology, and also plays a key role in an automatic diagnosis system. However, the evaluation of panoramic radiographs depends on the clinical experience and knowledge of dentist, while the interpretation of panoramic radiographs might lead misdiagnosis. Therefore, it is of great significance to use artificial intelligence to segment teeth on panoramic radiographs. In this study, SWin-Unet, the transformer-based Ushaped encoder-decoder architecture with skip-connections, is introduced to perform panoramic radiograph segmentation. To well evaluate the tooth segmentation performance of SWin-Unet, the PLAGH-BH dataset is introduced for the research purpose. The performance is evaluated by F1 score, mean intersection and Union (IoU) and Acc, Compared with U-Net, Link-Net and FPN baselines, SWin-Unet performs much better in PLAGH-BH tooth segmentation dataset. These results indicate that SWin-Unet is more feasible on panoramic radiograph segmentation, and is valuable for the potential clinical application.

Clinical tooth segmentation based on local enhancement

The tooth arrangements of human beings are challenging to accurately observe when relying on dentists' naked eyes, especially for dental caries in children, which is difficult to detect. Cone-beam computer tomography (CBCT) is used as an auxiliary method to measure patients' teeth, including children. However, subjective and irreproducible manual measurements are required during this process, which wastes much time and energy for the dentists. Therefore, a fast and accurate tooth segmentation algorithm that can replace repeated calculations and annotations in manual segmentation has tremendous clinical significance. This study proposes a local contextual enhancement model for clinical dental CBCT images. The local enhancement model, which is more suitable for dental CBCT images, is proposed based on the analysis of the existing contextual models. Then, the local enhancement model is fused into an encoder-decoder framework for dental CBCT images. At last, extensive experiments are conducted to validate our method.

A Fully Automated Method for 3D Individual Tooth Identification and Segmentation in Dental CBCT

Accurate and automatic segmentation of three-dimensional (3D) individual teeth from cone-beam computerized tomography (CBCT) images is a challenging problem because of the difficulty in separating an individual tooth from adjacent teeth and its surrounding alveolar bone. Thus, this paper proposes a fully automated method of identifying and segmenting 3D individual teeth from dental CBCT images. The proposed method addresses the aforementioned difficulty by developing a deep learning-based hierarchical multi-step model. First, it automatically generates upper and lower jaws panoramic images to overcome the computational complexity caused by high-dimensional data and the curse of dimensionality associated with limited training dataset. The obtained 2D panoramic images are then used to identify 2D individual teeth and capture loose- and tight- regions of interest (ROIs) of 3D individual teeth. Finally, accurate 3D individual tooth segmentation is achieved using both loose and tight ROIs. Experimental results showed that the proposed method achieved an F1-score of 93.35 percent for tooth identification and a Dice similarity coefficient of 94.79 percent for individual 3D tooth segmentation. The results demonstrate that the proposed method provides an effective clinical and practical framework for digital dentistry.

Analysis of Deep Learning Techniques for Dental Informatics: A Systematic Literature Review

Within the ever-growing healthcare industry, dental informatics is a burgeoning field of study. One of the major obstacles to the health care system’s transformation is obtaining knowledge and insightful data from complex, high-dimensional, and diverse sources. Modern biomedical research, for instance, has seen an increase in the use of complex, heterogeneous, poorly documented, and generally unstructured electronic health records, imaging, sensor data, and text. There were still certain restrictions even after many current techniques were used to extract more robust and useful elements from the data for analysis. New effective paradigms for building end-to-end learning models from complex data are provided by the most recent deep learning technology breakthroughs. Therefore, the current study aims to examine the most recent research on the use of deep learning techniques for dental informatics problems and recommend creating comprehensive and meaningful interpretable structures that might benefit the healthcare industry. We also draw attention to some drawbacks and the need for better technique development and provide new perspectives about this exciting new development in the field.