Fine structural human phantom in dentistry and instance tooth segmentation.

In this study, we present the development of a fine structural human phantom designed specifically for applications in dentistry. This research focused on assessing the viability of applying medical computer vision techniques to the task of segmenting individual teeth within a phantom. Using a virtual cone-beam computed tomography (CBCT) system, we generated over 170,000 training datasets. These datasets were produced by varying the elemental densities and tooth sizes within the human phantom, as well as varying the X-ray spectrum, noise intensity, and projection cutoff intensity in the virtual CBCT system. The deep-learning (DL) based tooth segmentation model was trained using the generated datasets. The results demonstrate an agreement with manual contouring when applied to clinical CBCT data. Specifically, the Dice similarity coefficient exceeded 0.87, indicating the robust performance of the developed segmentation model even when virtual imaging was used. The present results show the practical utility of virtual imaging techniques in dentistry and highlight the potential of medical computer vision for enhancing precision and efficiency in dental imaging processes.

Research Progress on Dental Age Estimation Based on MRI Technology.

Dental age estimation is a crucial aspect and one of the ways to accomplish forensic age estimation, and imaging technology is an important technique for dental age estimation. In recent years, some studies have preliminarily confirmed the feasibility of magnetic resonance imaging (MRI) in evaluating dental development, providing a new perspective and possibility for the evaluation of dental development, suggesting that MRI is expected to be a safer and more accurate tool for dental age estimation. However, further research is essential to verify its accuracy and feasibility. This article reviews the current state, challenges and limitations of MRI in dental development and age estimation, offering reference for the research of dental age assessment based on MRI technology.

Dental Age Estimation in Northern Chinese Han Children and Adolescents Using Demirjian's Method Combined with Machine Learning Algorithms.

OBJECTIVES: To investigate the application value of combining the Demirjian's method with machine learning algorithms for dental age estimation in northern Chinese Han children and adolescents. METHODS: Oral panoramic images of 10 256 Han individuals aged 5 to 24 years in northern China were collected. The development of eight permanent teeth in the left mandibular was classified into different stages using the Demirjian's method. Various machine learning algorithms, including support vector regression (SVR), gradient boosting regression (GBR), linear regression (LR), random forest regression (RFR), and decision tree regression (DTR) were employed. Age estimation models were constructed based on total, female, and male samples respectively using these algorithms. The fitting performance of different machine learning algorithms in these three groups was evaluated. RESULTS: SVR demonstrated superior estimation efficiency among all machine learning models in both total and female samples, while GBR showed the best performance in male samples. The mean absolute error (MAE) of the optimal age estimation model was 1.246 3, 1.281 8 and 1.153 8 years in the total, female and male samples, respectively. The optimal age estimation model exhibited varying levels of accuracy across different age ranges, which provided relatively accurate age estimations in individuals under 18 years old. CONCLUSIONS: The machine learning model developed in this study exhibits good age estimation efficiency in northern Chinese Han children and adolescents. However, its performance is not ideal when applied to adult population. To improve the accuracy in age estimation, the other variables can be considered.

Adolescents and Children Age Estimation Using Machine Learning Based on Pulp and Tooth Volumes on CBCT Images.

OBJECTIVES: To estimate adolescents and children age using stepwise regression and machine learning methods based on the pulp and tooth volumes of the left maxillary central incisor and cuspid on cone beam computed tomography (CBCT) images, and to compare and analyze the estimation results. METHODS: A total of 498 Shanghai Han adolescents and children CBCT images of the oral and maxillofacial regions were collected. The pulp and tooth volumes of the left maxillary central incisor and cuspid were measured and calculated. Three machine learning algorithms (K-nearest neighbor, ridge regression, and decision tree) and stepwise regression were used to establish four age estimation models. The coefficient of determination, mean error, root mean square error, mean square error and mean absolute error were computed and compared. A correlation heatmap was drawn to visualize and the monotonic relationship between parameters was visually analyzed. RESULTS: The K-nearest neighbor model (R2=0.779) and the ridge regression model (R2=0.729) outperformed stepwise regression (R2=0.617), while the decision tree model (R2=0.494) showed poor fitting. The correlation heatmap demonstrated a monotonically negative correlation between age and the parameters including pulp volume, the ratio of pulp volume to hard tissue volume, and the ratio of pulp volume to tooth volume. CONCLUSIONS: Pulp volume and pulp volume proportion are closely related to age. The application of CBCT-based machine learning methods can provide more accurate age estimation results, which lays a foundation for further CBCT-based deep learning dental age estimation research.

Fully automatic AI segmentation of oral surgery-related tissues based on cone beam computed tomography images.

Accurate segmentation of oral surgery-related tissues from cone beam computed tomography (CBCT) images can significantly accelerate treatment planning and improve surgical accuracy. In this paper, we propose a fully automated tissue segmentation system for dental implant surgery. Specifically, we propose an image preprocessing method based on data distribution histograms, which can adaptively process CBCT images with different parameters. Based on this, we use the bone segmentation network to obtain the segmentation results of alveolar bone, teeth, and maxillary sinus. We use the tooth and mandibular regions as the ROI regions of tooth segmentation and mandibular nerve tube segmentation to achieve the corresponding tasks. The tooth segmentation results can obtain the order information of the dentition. The corresponding experimental results show that our method can achieve higher segmentation accuracy and efficiency compared to existing methods. Its average Dice scores on the tooth, alveolar bone, maxillary sinus, and mandibular canal segmentation tasks were 96.5%, 95.4%, 93.6%, and 94.8%, respectively. These results demonstrate that it can accelerate the development of digital dentistry.

Application of deep learning in isolated tooth identification.

BACKGROUND: Teeth identification has a pivotal role in the dental curriculum and provides one of the important foundations of clinical practice. Accurately identifying teeth is a vital aspect of dental education and clinical practice, but can be challenging due to the anatomical similarities between categories. In this study, we aim to explore the possibility of using a deep learning model to classify isolated tooth by a set of photographs. METHODS: A collection of 5,100 photographs from 850 isolated human tooth specimens were assembled to serve as the dataset for this study. Each tooth was carefully labeled during the data collection phase through direct observation. We developed a deep learning model that incorporates the state-of-the-art feature extractor and attention mechanism to classify each tooth based on a set of 6 photographs captured from multiple angles. To increase the validity of model evaluation, a voting-based strategy was applied to refine the test set to generate a more reliable label, and the model was evaluated under different types of classification granularities. RESULTS: This deep learning model achieved top-3 accuracies of over 90% in all classification types, with an average AUC of 0.95. The Cohen's Kappa demonstrated good agreement between model prediction and the test set. CONCLUSIONS: This deep learning model can achieve performance comparable to that of human experts and has the potential to become a valuable tool for dental education and various applications in accurately identifying isolated tooth.

Microhardness Measurements on Tooth and Alveolar Bone in Rodent Oral Disease Models.

The mechanical property, microhardness, is evaluated in dental enamel, dentin, and bone in oral disease models, including dental fluorosis and periodontitis. Micro-CT (µCT) provides 3D imaging information (volume and mineral density) and scanning electron microscopy (SEM) produces microstructure images (enamel prism and bone lacuna-canalicular). Complementarily to structural analysis by µCT and SEM, microhardness is one of the informative parameters to evaluate how structural changes alter mechanical properties. Despite being a useful parameter, studies on microhardness of alveolar bone in oral diseases are limited. To date, divergent microhardness measurement methods have been reported. Since microhardness values vary depending on the sample preparation (polishing and flat surface) and indentation sites, diverse protocols can cause discrepancies among studies. Standardization of the microhardness protocol is essential for consistent and accurate evaluation in oral disease models. In the present study, we demonstrate a standardized protocol for microhardness analysis in tooth and alveolar bone. Specimens used are as follows: for the dental fluorosis model, incisors were collected from mice treated with/without fluoride-containing water for 6 weeks; for ligature-induced periodontal bone resorption (L-PBR) model, alveolar bones with periodontal bone resorption were collected from mice ligated on the maxillary 2nd molar. At 2 weeks after the ligation, the maxilla was collected. Vickers hardness was analyzed in these specimens according to the standardized protocol. The protocol provides detailed materials and methods for resin embedding, serial polishing, and indentation sites for incisors and alveolar. To the best of our knowledge, this is the first standardized microhardness protocol to evaluate the mechanical properties of tooth and alveolar bone in rodent oral disease models.

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.

Determination of Mouth Width for Facial Reconstruction Based on Statistical Regression Model.

INTRODUCTION: It is important to generate predictable statistical models by increasing the number of variables on the human skeletal and soft tissue structures on the face to increase the accuracy of human facial reconstructions. The purpose of this study was to determine mouth width 3-dimensionally based on statistical regression model. MATERIAL AND METHODS: Cone-beam computed tomography scan data from 130 individuals were used to measure the horizontal and vertical dimensions of orbital and nasal structures and intercanine width. The correlation between these hard tissue variables and the mouth width was evaluated using the statistical regression model. RESULTS: Orbital width, nasal width, and intercanine width were found to be strong predictors of the mouth width determination and were used to generate the regression formulae to find the most approximate position of the mouth. CONCLUSION: These specific variables may contribute to improving the accuracy of mouth width determination for oral and maxillofacial reconstructions.

Tooth replacement in the early-diverging neornithischian Jeholosaurus shangyuanensis and implications for dental evolution and herbivorous adaptation in Ornithischia.

BACKGROUND: Tooth replacement patterns of early-diverging ornithischians, which are important for understanding the evolution of the highly specialized dental systems in hadrosaurid and ceratopsid dinosaurs, are poorly known. The early-diverging neornithischian Jeholosaurus, a small, bipedal herbivorous dinosaur from the Early Cretaceous Jehol Biota, is an important taxon for understanding ornithischian dental evolution, but its dental morphology was only briefly described previously and its tooth replacement is poorly known. RESULTS: CT scanning of six specimens representing different ontogenetic stages of Jeholosaurus reveals significant new information regarding the dental system of Jeholosaurus, including one or two replacement teeth in nearly all alveoli, relatively complete tooth resorption, and an increase in the numbers of alveoli and replacement teeth during ontogeny. Reconstructions of Zahnreihen indicate that the replacement pattern of the maxillary dentition is similar to that of the dentary dentition but with a cyclical difference. The maxillary tooth replacement rate in Jeholosaurus is probably 46 days, which is faster than that of most other early-diverging ornithischians. During the ontogeny of Jeholosaurus, the premaxillary tooth replacement rate slows from 25 days to 33 days with similar daily dentine formation. CONCLUSIONS: The tooth replacement rate exhibits a decreasing trend with ontogeny, as in Alligator. In a phylogenetic context, fast tooth replacement and multi-generation replacement teeth have evolved at least twice independently in Ornithopoda, and our analyses suggest that the early-diverging members of the major ornithischian clades exhibit different tooth replacement patterns as an adaption to herbivory.

Performance comparison of multifarious deep networks on caries detection with tooth X-ray images.

OBJECTIVES: Deep networks have been preliminarily studied in caries diagnosis based on clinical X-ray images. However, the performance of different deep networks on caries detection is still unclear. This study aims to comprehensively compare the caries detection performances of recent multifarious deep networks with clinical dentist level as a bridge. METHODS: Based on the self-collected periapical radiograph dataset in clinic, four most popular deep networks in two types, namely YOLOv5 and DETR object detection networks, and UNet and Trans-UNet segmentation networks, were included in the comparison study. Five dentists carried out the caries detection on the same testing dataset for reference. Key tooth-level metrics, including precision, sensitivity, specificity, F1-score and Youden index, were obtained, based on which statistical analysis was conducted. RESULTS: The F1-score order of deep networks is YOLOv5 (0.87), Trans-UNet (0.86), DETR (0.82) and UNet (0.80) in caries detection. A same ranking order is found using the Youden index combining sensitivity and specificity, which are 0.76, 0.73, 0.69 and 0.64 respectively. A moderate level of concordance was observed between all networks and the gold standard. No significant difference (p > 0.05) was found between deep networks and between the well-trained network and dentists in caries detection. CONCLUSIONS: Among investigated deep networks, YOLOv5 is recommended to be priority for caries detection in terms of its high metrics. The well-trained deep network could be used as a good assistance for dentists to detect and diagnose caries. CLINICAL SIGNIFICANCE: The well-trained deep network shows a promising potential clinical application prospect. It can provide valuable support to healthcare professionals in facilitating detection and diagnosis of dental caries.

Impact of the superimposition methods and the designated comparison area on accuracy analyses in dentate models.

OBJECTIVES: To measure the impact of superimposition methods and the designated comparison area on accuracy analyses of dentate models using an ISO-recommended 3-dimensional (3D) metrology-grade inspection software (Geomagic Control X; 3D Systems; Rock Hill, South Carolina; USA). MATERIALS AND METHODS: A dentate maxillary typodont scanned with a desktop scanner (E4; 3 Shape; Copenhagen; Denmark) and an intraoral scanner (Trios 4; 3 Shape; Copenhagen; Denmark) was used as reference. Eight groups were created based on the core features of each superimposition method: landmark-based alignment (G1); partial area-based alignment (G2); entire tooth area-based alignment (G3); double alignment combining landmark-based alignment with entire tooth area-based alignment (G4); double alignment combining partial area-based alignment with entire tooth area-based alignment (G5); initial automated quick pre-alignment (G6); initial automated precise pre-alignment (G7); and entire model area-based alignment (G8). Diverse variations of each alignment and two regions for accuracy analyses (teeth surface or full model surface) were tested, resulting in a total of thirty-two subgroups (n = 18). The alignment accuracy between experimental and reference meshes was quantified using root mean square (RMS) error as trueness and its repeatability as precision. The descriptive statistics, a factorial repeated measures analysis of variance (ANOVA) and a post hoc Tuckey multiple comparison tests were used to analyze the trueness, and precision (α = 0.05). RESULTS: A total of 576 superimpositions were performed. The unique partial area-based superimposition method demonstrated the least precise alignment and was the sole group to exhibit a significant difference (p<.001). Automated initial pre-alignments demonstrated similar accuracy to other superimposition methods (p>.05). Double alignments did not result in accuracy improvement (p>.05). The designated comparison area displayed differences in both trueness (p<.001) and precision (p<.001), leading to an overall discrepancy of 8 ± 4 µm between selecting the teeth surface or full model surface. CONCLUSIONS: The superimposition method choice within the tested software did not impact accuracy analyses, except when the alignment relies on a unique and reduced area, such as the palatal rugae, a single tooth, or three adjacent teeth on one side. CLINICAL SIGNIFICANCE: The superimposition method choice within the tested ISO-recommended 3D inspection software did not impact accuracy analyses.

Occlusal characteristics in modern humans with tooth agenesis.

Non-syndromic permanent tooth agenesis affects a significant proportion of the population, especially if third molars are considered. Although tooth agenesis has been linked to a smaller craniofacial size, reduced facial convexity and a shorter skeletal face, the occlusal characteristics of individuals with tooth agenesis remain largely unexplored. Therefore, this study investigated potential associations between tooth agenesis and metric occlusal traits in 806 individuals (491 with 4.1 missing teeth per subject, including third molars, and 315 without any tooth agenesis). Dentoskeletal morphology was defined through anatomical landmarks on pre-treatment cephalometric radiographs. Multivariate regression models, adjusted for sex and age, showed that tooth agenesis was significantly associated with a reduced overjet, an increased interincisal angle, and shorter upper and lower dental arch lengths, but not with overbite. Moreover, apart from reduced tooth length and dentoalveolar effects, as the number of missing teeth increased the upper front teeth were progressively retruded according to the craniofacial complex and to the face. Thus, tooth agenesis has a substantial influence on dental and occlusal characteristics, as well as on the sagittal position and inclination of anterior teeth. These findings emphasize the necessity for personalized, multidisciplinary approaches in individuals with multiple agenesis to successfully meet treatment goals.

Sex and ancestry patterning of residual correlations in human dental development: Cooperative genetic interaction and phenotypic plasticity.

OBJECTIVES: Most research in human dental age estimation has focused on point estimates of age, and most research on dental development theories has focused on morphology or eruption. Correlations between developing teeth using ordinal staging have received less attention. The effect of demographic variables on these correlations is unknown. I tested the effect of reference sample demographic variables on the residual correlation matrix using the lens of cooperative genetic interaction (CGI). MATERIALS AND METHODS: The sample consisted of Moorrees et al., Journal of Dental Research, 1963, 42, 1490-1502, scores of left mandibular permanent teeth from panoramic radiographs of 880 London children 3-22.99 years of age stratified by year of age, sex, and Bangladeshi or European ancestry. A multivariate cumulative probit model was fit to each sex/ancestry group (n = 220), each sex or ancestry (n = 440), and all individuals (n = 880). Residual correlation matrices from nine reference sample configurations were compared using Bartlett's tests of between-sample difference matrices against the identity matrix, hierarchical cluster analysis, and dendrogram cophenetic correlations. RESULTS: Bartlett's test results were inconclusive. Cluster analysis showed clustering by tooth class, position within class, and developmental timing. Clustering patterns and dendrogram correlations showed similarity by sex but not ancestry. DISCUSSION: Expectations of CGI were supported for developmental staging. This supports using CGI as a model for explaining patterns of variation within the dentition. Sex was found to produce consistent patterns of dental correlations, whereas ancestry did not. Clustering by timing of development supports phenotypic plasticity in the dentition and suggests shared environment over genetic ancestry to explain population differences.

Performance evaluation of three versions of a convolutional neural network for object detection and segmentation using a multiclass and reduced panoramic radiograph dataset.

OBJECTIVES: To evaluate the diagnostic performance of three versions of a deep-learning convolutional neural network in terms of object detection and segmentation using a multiclass panoramic radiograph dataset. METHODS: A total of 600 orthopantomographies were randomly selected for this study and manually annotated by a single operator using an image annotation tool (COCO Annotator v.11.0.1) to establish ground truth. The annotation classes included teeth, maxilla, mandible, inferior alveolar nerve, dento- and implant-supported crowns/pontics, endodontic treatment, resin-based restorations, metallic restorations, and implants. The dataset was then divided into training, validation, and testing subsets, which were used to train versions 5, 7, and 8 of You Only Look Once (YOLO) Neural Network. Results were stored, and a posterior performance analysis was carried out by calculating the precision (P), recall (R), F1 Score, Intersection over Union (IoU), and mean average precision (mAP) at 0.5 and 0.5-0.95 thresholds. The confusion matrix and recall precision graphs were also sketched. RESULTS: YOLOv5s showed an improvement in object detection results with an average R = 0.634, P = 0.781, mAP0.5 = 0.631, and mAP0.5-0.95 = 0.392. YOLOv7m achieved the best object detection results with average R = 0.793, P = 0.779, mAP0.5 = 0.740, and mAP0.5-0.95 = 0,481. For object segmentation, YOLOv8m obtained the best average results (R = 0.589, P = 0.755, mAP0.5 = 0.591, and mAP0.5-0.95 = 0.272). CONCLUSIONS: YOLOv7m was better suited for object detection, while YOLOv8m demonstrated superior performance in object segmentation. The most frequent error in object detection was related to background classification. Conversely, in object segmentation, there is a tendency to misclassify True Positives across different dental treatment categories. CLINICAL SIGNIFICANCE: General diagnostic and treatment decisions based on panoramic radiographs can be enhanced using new artificial intelligence-based tools. Nevertheless, the reliability of these neural networks should be subjected to training and validation to ensure their generalizability.

Windows into the past: recent scientific techniques in dental analysis.

Teeth are the hardest and most chemically stable tissues in the body, are well-preserved in archaeological remains and, being resistant to decomposition in the soil, survive long after their supporting structures have deteriorated. It has long been recognised that visual and radiographic examination of teeth can provide considerable information relating to the lifestyle of an individual. This paper examines the latest scientific approaches that have become available to investigate recent and ancient teeth. These techniques include DNA analysis, which can be used to determine the sex of an individual, indicate familial relationships, study population movements, provide phylogenetic information and identify the presence of disease pathogens. A stable isotopic approach can shed light on aspects of diet and mobility and even research climate change. Proteomic analysis of ancient dental calculus can reveal specific information about individual diets. Synchrotron microcomputed tomography is a non-invasive technique which can be used to visualise physiological impactful events, such as parturition, menopause and diseases in cementum microstructure - these being displayed as aberrant growth lines.

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.

The repeatability of periodontal imaging with intraoral ultrasound scanning.

OBJECTIVE: Ultrasound is a non-invasive and low-cost diagnostic tool widely used in medicine. Recent studies have demonstrated that ultrasound imaging might have the potential to be used intraorally to assess the periodontium by comparing it to current imaging methods. This study aims to characterize the repeatability of intraoral periodontal ultrasound imaging. MATERIALS AND METHODS: Two hundred and twenty-three teeth were scanned from fourteen volunteers participating in this study. One operator conducted all the scans in each tooth thrice with a 20 MHz intraoral ultrasound. The repeatability of three measurements, alveolar bone crest to the cementoenamel junction (ABC-CEJ), gingival thickness (GT), and alveolar bone thickness (ABT), was calculated with intercorrelation coefficient (ICC). Measurements were also compared with mean absolute deviation (MAD), repeatability coefficient (RC), and descriptive statistics. RESULTS: ICC scores for intra-rater repeatability were 0.917(0.897,0.933), 0.849(0.816,0.878), and 0.790(0.746,0.898), MAD results were 0.610 mm (± 0.508), 0.224 (± 0.200), and 0.067 (± 0.060), and RC results were 0.648, 0.327, and 0.121 for ABC-CEJ, GT, and ABT measurements, respectively. CONCLUSION: Results of the present study pointed towards good or excellent repeatability of ultrasound as a measurement tool for periodontal structures. CLINICAL RELEVANCE: Clinicians could benefit from the introduction of a novel chairside diagnostic tool. Ultrasound is a non-invasive imaging assessment tool for the periodontium with promising results in the literature. Further validation, establishment of scanning protocols, and commercialization are still needed before ultrasound imaging is available for clinicians.

Deep learning for tooth identification and numbering on dental radiography: a systematic review and meta-analysis.

OBJECTIVES: Improved tools based on deep learning can be used to accurately number and identify teeth. This study aims to review the use of deep learning in tooth numbering and identification. METHODS: An electronic search was performed through October 2023 on PubMed, Scopus, Cochrane, Google Scholar, IEEE, arXiv, and medRxiv. Studies that used deep learning models with segmentation, object detection, or classification tasks for teeth identification and numbering of human dental radiographs were included. For risk of bias assessment, included studies were critically analysed using quality assessment of diagnostic accuracy studies (QUADAS-2). To generate plots for meta-analysis, MetaDiSc and STATA 17 (StataCorp LP, College Station, TX, USA) were used. Pooled outcome diagnostic odds ratios (DORs) were determined through calculation. RESULTS: The initial search yielded 1618 studies, of which 29 were eligible based on the inclusion criteria. Five studies were found to have low bias across all domains of the QUADAS-2 tool. Deep learning has been reported to have an accuracy range of 81.8%-99% in tooth identification and numbering and a precision range of 84.5%-99.94%. Furthermore, sensitivity was reported as 82.7%-98% and F1-scores ranged from 87% to 98%. Sensitivity was 75.5%-98% and specificity was 79.9%-99%. Only 6 studies found the deep learning model to be less than 90% accurate. The average DOR of the pooled data set was 1612, the sensitivity was 89%, the specificity was 99%, and the area under the curve was 96%. CONCLUSION: Deep learning models successfully can detect, identify, and number teeth on dental radiographs. Deep learning-powered tooth numbering systems can enhance complex automated processes, such as accurately reporting which teeth have caries, thus aiding clinicians in making informed decisions during clinical practice.

Quantitative photothermal analysis and multispectral imaging of dental structures: insights into optical and thermal properties of carious and healthy teeth.

Significance: In the analysis of two-layered turbid dental tissues, the outer finite-thickness layer is modeled by an optical transport coefficient distinct from its underlying semi-infinite substrate layer. The optical and thermophysical parameters of healthy and carious teeth across the various wavelengths were measured leading to the determination of the degree of reliability of each of the fitted parameters, with most reliable being thermal diffusivity and conductivity, enamel thickness, and optical transport coefficient of the enamel layer. Quantitative pixel-by-pixel images of the key reliable optical and thermophysical parameters were constructed. Aim: We introduced a theoretical model of pulsed photothermal radiometry based on conduction-radiation theory and applied to quantitative photothermal detection and imaging of biomaterials. The theoretical model integrates a combination of inverse Fourier transformation techniques, avoiding the conventional cumbersome analytical Laplace transform method. Approach: Two dental samples were selected for analysis: the first sample featured controlled, artificially induced early caries on a healthy tooth surface, while the second sample exhibited natural defects along with an internal filling. Using an Nd:YAG laser and specific optical parametric oscillator (OPO) wavelengths (675, 700, 750, and 808 nm), photothermal transient signals were captured from different points on these teeth and analyzed as a function of OPO wavelength. Measurements were also performed with an 808-nm laser diode for comparison with the same OPO wavelength excitation, particularly for the second sample with natural defects. Results: The findings demonstrated that the photothermal transient signals exhibit a fast-decaying pattern at shorter wavelengths due to their higher scattering nature, while increased scattering and absorption in the carious regions masked conductive and radiative contributions from the underlayer. These observations were cross-validated using micro-computed tomography, which also enabled the examination of signal patterns at different tooth locations. Conclusions: The results of our study showed the impact of optical and thermal characteristics of two-layered turbid dental tissues via an inverse Fourier technique, as well as the interactions between these layers, on the patterns observed in depth profiles.