Fully automated deep learning approach to dental development assessment in panoramic radiographs.

BACKGROUND: Dental development assessment is an important factor in dental age estimation and dental maturity evaluation. This study aimed to develop and evaluate the performance of an automated dental development staging system based on Demirjian's method using deep learning. METHODS: The study included 5133 anonymous panoramic radiographs obtained from the Department of Pediatric Dentistry database at Seoul National University Dental Hospital between 2020 and 2021. The proposed methodology involves a three-step procedure for dental staging: detection, segmentation, and classification. The panoramic data were randomly divided into training and validating sets (8:2), and YOLOv5, U-Net, and EfficientNet were trained and employed for each stage. The models' performance, along with the Grad-CAM analysis of EfficientNet, was evaluated. RESULTS: The mean average precision (mAP) was 0.995 for detection, and the segmentation achieved an accuracy of 0.978. The classification performance showed F1 scores of 69.23, 80.67, 84.97, and 90.81 for the Incisor, Canine, Premolar, and Molar models, respectively. In the Grad-CAM analysis, the classification model focused on the apical portion of the developing tooth, a crucial feature for staging according to Demirjian's method. CONCLUSIONS: These results indicate that the proposed deep learning approach for automated dental staging can serve as a supportive tool for dentists, facilitating rapid and objective dental age estimation and dental maturity evaluation.

Association of mandibular canine impaction and anatomical factors: A multicentre retrospective panoramic study in Latin America.

INTRODUCTION: Mandibular canine impaction is infrequent in dental eruption anomalies and treatment is very challenging. The aim of this multicenter retrospective panoramic study in Latin America was to evaluate panoramic radiographic imaging characteristics of mandibular canine impaction (impaction area, mandibular base contact, transmigration, impaction height and sex) and their associations. MATERIAL AND METHODS: This cross-sectional study evaluated 212 digital panoramic radiographs from three radiological centres in Tingo Maria (Peru), Bogota and Tunja (Colombia). The study included children of both sexes with impacted mandibular canines. Mandibular alpha angle, contact with mandibular basal bone (MBB), impacted sector according to 10 sectors with an adaptation of the Ericson and Kurol method, presence of transmigration and the impacted height were measured and the relationship among these measures was analyzed. Fisher's exact test, Chi-square and binary logistic regression were used. (P<0.05). RESULTS: The mandibular canine impaction showed contact with the MBB (32.08%), dental transmigration (36.79%), mainly located at an apical (40.09%) and sub-apical (36.79%) level. Transmigration mainly occurred in sectors 6 (33.30%) and 10 (25.60%) (P<0.001). It was found that for each year of increase in age, the possibility of contact with the MBB decreased (ß=0.89, P=0.010), and as the alpha angle increased by one degree the probability of contact with the MBB decreased (ß=0.97, P=0.001) and the probability of transmigration increased (ß=1.05, P<0.001). CONCLUSIONS: One third of the impacted canines were in contact with the MBB, while another third presented dental transmigration and were mainly located apically and subapically of the incisor roots. These imaging features should be taken into account when planning orthodontic treatment.

Clinical analysis of nonsyndromic oligodontia phenotypes.

OBJECTIVES: To provide references, this study investigated the clinical characteristics of patients with nonsyndromic oligodontia. METHODS: The information of 178 patients with oligodontia was collected, including histories, oral examinations, and panoramic radiographs. Tooth agenesis characteristics were calculated and evaluated. All the data were statistically analyzed with SPSS 24.0 software. RESULTS: No significant difference in the number of missing teeth was found between sexes nor between the right and left sides, and congenitally missing teeth affected the maxillary arch (P<0.05). The highest prevalence of tooth agenesis was observed in the mandibular second premolars. In the maxillary arch, the most common pattern of tooth agenesis was agenesis of the bilateral first and second premolars. The agenesis of the bilateral second premolars was observed in the mandibular arch. The prevalence of a symmetric pattern between the right and left quadrants was significantly higher than that of matched patterns between the maxillary and mandibular antagonistic quadrants. Approximately 16.85% of patients with nonsyndromic oligodontia were affected by other tooth-related anomalies. CONCLUSIONS: The common patterns of tooth agenesis were successfully identified in patients with nonsyndromic oligodontia. Dentists need to provide multidisciplinary treatments for patients with nonsyndromic oligodontia because of variations in occluding and full-mouth tooth agenesis patterns.

Automatic and robust estimation of sex and chronological age from panoramic radiographs using a multi-task deep learning network: a study on a South Korean population.

Sex and chronological age estimation are crucial in forensic investigations and research on individual identification. Although manual methods for sex and age estimation have been proposed, these processes are labor-intensive, time-consuming, and error-prone. The purpose of this study was to estimate sex and chronological age from panoramic radiographs automatically and robustly using a multi-task deep learning network (ForensicNet). ForensicNet consists of a backbone and both sex and age attention branches to learn anatomical context features of sex and chronological age from panoramic radiographs and enables the multi-task estimation of sex and chronological age in an end-to-end manner. To mitigate bias in the data distribution, our dataset was built using 13,200 images with 100 images for each sex and age range of 15-80 years. The ForensicNet with EfficientNet-B3 exhibited superior estimation performance with mean absolute errors of 2.93 ± 2.61 years and a coefficient of determination of 0.957 for chronological age, and achieved accuracy, specificity, and sensitivity values of 0.992, 0.993, and 0.990, respectively, for sex prediction. The network demonstrated that the proposed sex and age attention branches with a convolutional block attention module significantly improved the estimation performance for both sex and chronological age from panoramic radiographs of elderly patients. Consequently, we expect that ForensicNet will contribute to the automatic and accurate estimation of both sex and chronological age from panoramic radiographs.

Efficacy of the methods of age determination using artificial intelligence in panoramic radiographs - a systematic review.

The aim of this systematic review is to analyze the literature to determine whether the methods of artificial intelligence are effective in determining age in panoramic radiographs. Searches without language and year limits were conducted in PubMed/Medline, Embase, Web of Science, and Scopus databases. Hand searches were also performed, and unpublished manuscripts were searched in specialized journals. Thirty-six articles were included in the analysis. Significant differences in terms of root mean square error and mean absolute error were found between manual methods and artificial intelligence techniques, favoring the use of artificial intelligence (p < 0.00001). Few articles compared deep learning methods with machine learning models or manual models. Although there are advantages of machine learning in data processing and deep learning in data collection and analysis, non-comparable data was a limitation of this study. More information is needed on the comparison of these techniques, with particular emphasis on time as a variable.

Artificial intelligence-based automated preprocessing and classification of impacted maxillary canines in panoramic radiographs.

OBJECTIVES: Automating the digital workflow for diagnosing impacted canines using panoramic radiographs (PRs) is challenging. This study explored feature extraction, automated cropping, and classification of impacted and nonimpacted canines as a first step. METHODS: A convolutional neural network with SqueezeNet architecture was first trained to classify two groups of PRs (91with and 91without impacted canines) on the MATLAB programming platform. Based on results, the need to crop the PRs was realized. Next, artificial intelligence (AI) detectors were trained to identify specific landmarks (maxillary central incisors, lateral incisors, canines, bicuspids, nasal area, and the mandibular ramus) on the PRs. Landmarks were then explored to guide cropping of the PRs. Finally, improvements in classification of automatically cropped PRs were studied. RESULTS: Without cropping, the area under the curve (AUC) of the receiver operating characteristic (ROC) curve for classifying impacted and nonimpacted canine was 84%. Landmark training showed that detectors could correctly identify upper central incisors and the ramus in ∼98% of PRs. The combined use of the mandibular ramus and maxillary central incisors as guides for cropping yielded the best results (∼10% incorrect cropping). When automatically cropped PRs were used, the AUC-ROC improved to 96%. CONCLUSIONS: AI algorithms can be automated to preprocess PRs and improve the identification of impacted canines.

The Utility of Cone Beam Computed Tomography Scans in Diagnosing and Treating Anterior Lesions of the Maxilla and Mandible.

BACKGROUND: The standard screening protocol for radiographic examination in dentistry as per the American Dental Association recommendations is a panoramic radiograph (PAN) and four horizontal bitewings. PAN inherently suffers from several shortcomings like the superimposition of anatomic structures, especially of the cervical spine that obscures a significant portion of the anterior maxilla and mandible. This region has a significant amount of pathology that is not adequately imaged. Three-dimensional (3D) imaging provides circumferential information on the area of interest and adds value to the diagnosis and treatment planning of pathology, especially in the anterior maxilla and mandible. However, there is not an adequate number of well-designed studies that articulate the true value addition of 3D imaging for the evaluation of this region. OBJECTIVES: The objective of this study is to evaluate the value addition of 3D imaging in diagnosing pathologies in the anterior maxilla and mandible when compared to two-dimensional PAN. MATERIALS AND METHODS: A total of 25 cases that had a diagnosis of anterior pathology and had both a PAN and a cone beam computed tomography (CBCT) scan were collected for this study. An institutional review board approval to retrospectively evaluate these data was obtained. The PAN and CBCT scans were randomly evaluated by a second-year dental student, an oral and maxillofacial radiology resident in training, and a board-certified oral radiologist. The scans were evaluated using a three-point modified Likert scale, where 1 represents "not visible or clear," 2 represents "visible but not clear," and 3 represents "visible and clear." The lesions were evaluated for characteristics like lesion location, size & shape, internal contents, borders of the lesion, cortical integrity, locularity, and effect on adjacent structures like root resorption. After the evaluation was completed, a comparison of the lesion diagnosis was done with histopathology to confirm the diagnosis. The evaluators were also asked to comment on the specific feature that 3D imaging provided that added value to the case. Kappa analysis was done to evaluate inter-operator reliability. RESULTS: PAN demonstrated significantly lower efficacy in identifying and diagnosing lesions. Only 56% of cases were analyzed using PAN, with 44% deemed undetectable or poorly visualized. These challenging cases necessitated CBCT scans for accurate diagnosis, which successfully diagnosed all 25 cases. The p-value of 0.0002 for PAN implies a highly significant difference from histopathology, suggesting the distinctions are not due to chance. Conversely, the p-value of 0.3273 for CBCT implies that observed differences may be random, lacking sufficient evidence to reject the null hypothesis. CBCT scans consistently outperformed PAN in visualizing various lesion characteristics, underscoring their superior diagnostic capabilities. CONCLUSIONS: In this study, with a small sample size, 3D imaging provided a significant value addition to the diagnosis and treatment planning by providing additional information regarding the location, extent, internal content, and effect on adjacent structures. The practical implications for clinical settings, along with comparisons to current literature, underscore the study's distinctiveness.

Mask refinement network for tooth segmentation on panoramic radiographs.

OBJECTIVES: Instance-level tooth segmentation extracts abundant localization and shape information from panoramic radiographs (PRs). The aim of this study was to evaluate the performance of a mask refinement network that extracts precise tooth edges. METHODS: A public dataset which consists of 543 PRs and 16211 labelled teeth was utilized. The structure of a typical Mask Region-based Convolutional Neural Network (Mask RCNN) was used as the baseline. A novel loss function was designed focus on producing accurate mask edges. In addition to our proposed method, 3 existing tooth segmentation methods were also implemented on the dataset for comparative analysis. The average precisions (APs), mean intersection over union (mIoU), and mean Hausdorff distance (mHAU) were exploited to evaluate the performance of the network. RESULTS: A novel mask refinement region-based convolutional neural network was designed based on Mask RCNN architecture to extract refined masks for individual tooth on PRs. A total of 3311 teeth were correctly detected from 3382 tested teeth in 111 PRs. The AP, precision, and recall were 0.686, 0.979, and 0.952, respectively. Moreover, the mIoU and mHAU achieved 0.941 and 9.7, respectively, which are significantly better than the other existing segmentation methods. CONCLUSIONS: This study proposed an efficient deep learning algorithm for accurately extracting the mask of any individual tooth from PRs. Precise tooth masks can provide valuable reference for clinical diagnosis and treatment. This algorithm is a fundamental basis for further automated processing applications.

Correlation between the presence of tonsilloliths and the bone defects by periodontitis on imaging analysis: a pilot study.

BACKGROUND: Very recently, a significant relationship between tonsilloliths and dental plaque-related pathologies was reported using digital panoramic radiographs. Their dynamics over time suggest that tonsilloliths may be in a permanently active phase that functions to remove foreign matter. The aim of the study was to evaluate the relationship between the occurrence of tonsilloliths and the extent of periodontitis. METHODS: A total of 608 patients who underwent both CT and panoramic radiographs were included in the study. Both of two imaging were retrospectively and independently assessed with respect to the presence of tonsilloliths detected on CT and panoramic radiographs, and bone defects caused by periodontitis detected on panoramic radiographs. The type of retrospective study is case-control. Then, the differences between age groups were evaluated with respect to the degree of bone resorption and its correlation with the presence of tonsilloliths. The relationships between categorical variables were assessed using Pearson's correlation coefficient or Spearman's correlation coefficient. RESULTS: There was a significant relationship between tonsilloliths on CT and the extent of the bone defect on panoramic radiographs (Spearman's correlation coefficient, r = 0.648, p = 0.043). In addition, there was a significant difference in the extent of the bone defect caused by periodontitis between subjects with and without tonsilloliths in the 60 to 69-year-old group (Mann-Whitney U test, p = 0.025), 70 to 79-year-old group (Mann-Whitney U test, p = 0.002), and 80 to 89-year-old group (Mann-Whitney U test, p = 0.022), but not in other age groups (Mann-Whitney U test: under 9-year-old group, p = 1.000; 10 to 19-year-old group, p = 1.000; 20 to 29-year-old group, p = 0.854; 30 to 39-year-old group, p = 0.191, 40 to 49-year-old group, p = 0.749; 50 to 59-year-old group, p = 0.627; ≥90-year-old group, p = 1.000). CONCLUSIONS: The presence of tonsilloliths was related to the extent of periodontitis because the structures were responding dynamically.

Is it possible to predict neurosensory alterations in impacted lower third molar removal based on preoperative imaging procedures? A prospective cohort study / ¿Es posible predecir alteraciones neurosensoriales en la extracción del tercer molar inferior impactado basándose en procedimientos de imagen preoperatorios? Un estudio de cohorte prospectivo

Background: Surgical extraction of the lower third molar (LTM) may trigger neurosensory injury of the inferioralveolar nerve, making extraction a real challenge. This study set out to assess whether is it possible to predictneurosensory alterations from preoperative imaging.Material and Methods: A total of 99 patients underwent 124 impacted lower third molar (ILTM) surgeries. Priorto surgery, panoramic and CBCT images were evaluated in an attempt to predict a neurosensory disturbance.Preoperative data (ILTM position, panoramic radiograph signs, inferior alveolar nerve (IAN) location and its con-tact with the ILTM roots) and intra/postoperative findings (extraction difficulty and sensitivity alterations) wererecorded. Descriptive and bivariate data analysis was performed. Statistical comparison applied the chi-squaretest, Fisher test, and one-way ANOVA test. Statistical significance was established with a confidence interval (CI)of 95%.Results: In 4.03% of cases, patients experienced neurosensory alterations. Of 124 ILTM positions in panoramicradiographs, 76 cases were considered to exhibit a potential neurosensory risk as they presented two or more typesof superimposed relationships between ILTM and mandibular canal. Of these, alterations were reported in onlythree cases (3.95%). Of the 48 remaining ILTM images presenting only one sign, neurosensory alterations wereobserved in two cases (4.17%). No permanent alterations were recorded in any of the five cases observed.Conclusions: Within the limitations of the present study, prediction of neurosensory alterations prior to ILTMextraction by means of preoperative imaging did not show a significant statistical correlation with post-surgicalincidence. Nevertheless, interruption of the canal´s white line (ICWL) or a diversion of the canal (DC) may predictan increased risk of IAN injury.(AU)

Prescription of panoramic radiographs in children using age-based prevalence of dental anomalies and pathologies.

BACKGROUND: Panoramic radiographs (PRs) are used in the detection and diagnosis of developmental dental anomalies and pathologies (DDAPs) in children. AIM: The primary objective of this observational cohort study was to evaluate the age-based prevalence of DDAP on PRs, whereas the secondary objective was to determine a threshold age for the detection of DDAP to provide supportive evidence for the prescription of PR in paediatric dental practice. DESIGN: The study examined diagnostic PRs from 581 subjects aged 6 to 19 years. All PRs were reviewed by experienced, calibrated, masked examiners for the identification or presence of anomalies in size, shape, position, structure, and other developmental anomalies and pathologies (ODAP) of the face-neck region in a standardized condition. The data were statistically analyzed for interpretation. RESULTS: Overall, 74% (n = 411) of the cohort had at least one anomaly (shape anomaly: 12%, number anomaly: 17%, positional anomaly: 28%, structural anomaly: 0%, and ODAP: 63%). The optimal Youden index cutoff for any anomaly was 9 years. Twelve and 15 years also showed predictive ability. CONCLUSION: The results suggest that PRs should be prescribed at ages 9, 12, and 15 years for the diagnosis of DDAP.

Applying artificial intelligence to determination of legal age of majority from radiographic data.

Forensic odontologists use biological patterns to estimate chronological age for the judicial system. The age of majority is a legally significant period with a limited set of reliable oral landmarks. Currently, experts rely on the questionable development of third molars to assess whether litigants can be prosecuted as legal adults. Identification of new and novel patterns may illuminate features more dependably indicative of chronological age, which have, until now, remained unseen. Unfortunately, biased perceptions and limited cognitive capacity compromise the ability of researchers to notice new patterns. The present study demonstrates how artificial intelligence can break through identification barriers and generate new estimation modalities. A convolutional neural network was trained with 4003 panoramic-radiographs to sort subjects into 'under-18' and 'over-18' age categories. The resultant architecture identified legal adults with a high predictive accuracy equally balanced between precision, specificity and recall. Moving forward, AI-based methods could improve courtroom efficiency, stand as automated assessment methods and contribute to our understanding of biological ageing.

Comparing the prevalence of impacted teeth through radiographic evidence among orthodontic and general populations: A secondary data analysis.

Introduction: There is noticeable variability in reporting the prevalence of impacted teeth, which can be attributed to the variability in the age, gender, and type of populations investigated. Materials and Methods: Panoramic radiographs were examined retrospectively for patients who attended dental clinics at King Abdulaziz Medical City and the College of Dentistry at King Saud bin Abdulaziz University for Health Sciences (KSAU-HS) Riyadh, Saudi Arabia. The sampling frame for the orthodontic population included digital records of 2998 patients randomly selected from an original 8000 patients treated from 2016 to 2022 in the orthodontic clinic. For the general population, 3002 patients were randomly selected from an original 15000 patients treated at the dental college from 2016 to 2022. A tooth was considered impacted if it failed to erupt after two years of the expected complete root formation. Results: The prevalence of at least a single impacted tooth was higher in the orthodontic population (13.2 %) than in the general population (11.2 %). However, this difference was not statistically significant, p = 0.103. The orthodontic population had a significantly higher prevalence of impacted #13, #11,#23,#25. In contrast, the general population had a significantly higher prevalence of all third molars impaction (p < 0.005). Conclusion: Although the prevalence of at least a single tooth impaction between the orthodontic and general populations was not significantly different, the type of teeth differs. Hence, understanding the type of population investigated while reporting the prevalence of impacted teeth is critical in understanding the variability between different reports.

Mandibular Cortical Bone Evaluation in a Healthy Paediatric Population.

BACKGROUND: Changes in mandibular cortical bone have been documented in children with chronic diseases but not in healthy populations. AIM: We aimed to qualitatively and quantitatively evaluate the mandibular cortical bone of a healthy paediatric population using dental panoramic radiographs (DPTs). The secondary objective was to assess the effect of dental status on cortical bone. DESIGN: The DPTs of 660 individuals, aged 6-18 years, were evaluated by two blinded examiners. Bone was qualitatively categorized according to the Mandibular Cortical Index (MCI), and its width was calculated using the Mandibular Cortical Width Index (MCW). Differences between gender and age were tested using Fisher's exact and correlation with dental status with the chi-square test. RESULTS: A significant correlation was observed between bone morphology and gender, with girls having more frequent even and sharp endosteal margins than boys, who showed semilunar defects. The degree of erosion increased with age, as did bone thickness. A positive correlation between thickness and type of dentition was recorded, with normal bone predominating in children in the mixed dentition stage. Νο correlation was found between bone morphology or thickness and the factors associated with dental status. CONCLUSIONS: Bone quality and quantity vary significantly between different genders and age groups. Dental needs and treatment characteristics did not seem to affect the above parameters.

Coarse-to-fine prior-guided attention network for multi-structure segmentation on dental panoramic radiographs.

Objective. Accurate segmentation of various anatomical structures from dental panoramic radiographs is essential for the diagnosis and treatment planning of various diseases in digital dentistry. In this paper, we propose a novel deep learning-based method for accurate and fully automatic segmentation of the maxillary sinus, mandibular condyle, mandibular nerve, alveolar bone and teeth on panoramic radiographs.Approach. A two-stage coarse-to-fine prior-guided segmentation framework is proposed to segment multiple structures on dental panoramic radiographs. In the coarse stage, a multi-label segmentation network is used to generate the coarse segmentation mask, and in the fine-tuning stage, a prior-guided attention network with an encoder-decoder architecture is proposed to precisely predict the mask of each anatomical structure. First, a prior-guided edge fusion module is incorporated into the network at the input of each convolution level of the encode path to generate edge-enhanced image feature maps. Second, a prior-guided spatial attention module is proposed to guide the network to extract relevant spatial features from foreground regions based on the combination of the prior information and the spatial attention mechanism. Finally, a prior-guided hybrid attention module is integrated at the bottleneck of the network to explore global context from both spatial and category perspectives.Main results. We evaluated the segmentation performance of our method on a testing dataset that contains 150 panoramic radiographs collected from real-world clinical scenarios. The segmentation results indicate that our proposed method achieves more accurate segmentation performance compared with state-of-the-art methods. The average Jaccard scores are 87.91%, 85.25%, 63.94%, 93.46% and 88.96% for the maxillary sinus, mandibular condyle, mandibular nerve, alveolar bone and teeth, respectively.Significance. The proposed method was able to accurately segment multiple structures on panoramic radiographs. This method has the potential to be part of the process of automatic pathology diagnosis from dental panoramic radiographs.

Applications of artificial intelligence in the analysis of dental panoramic radiographs: an overview of systematic reviews.

OBJECTIVES: This overview of systematic reviews aimed to establish the current state of knowledge on the suitability of artificial intelligence (AI) in dental panoramic radiograph analysis and illustrate its changes over time. METHODS: Medical databases covered by the Association for Computing Machinery, Bielefeld Academic Search Engine, Google Scholar, and PubMed engines were searched. The risk of bias was assessed using ROBIS tool. Ultimately, 12 articles were qualified for the qualitative synthesis. The results were visualized with timelines, tables, and charts. RESULTS: In the years 1988-2023, a significant development of information technologies for the analysis of DPRs was observed. The latest analyzed AI models achieve high accuracy in detecting caries (91.5%), osteoporosis (89.29%), maxillary sinusitis (87.5%), periodontal bone loss (93.09%), and teeth identification and numbering (93.67%). The detection of periapical lesions is also characterized by high sensitivity (99.95%) and specificity (92%). However, due to the small number of heterogeneous source studies synthesized in systematic reviews, the results of this overview should be interpreted with caution. CONCLUSION: Currently, AI applications can significantly support dentists in dental panoramic radiograph analysis. As systematic reviews on AI become outdated quickly, their regular updating is recommended. PROSPERO registration number: CRD42023416048.

Prevalence of Impacted Teeth and Pattern of Third Molar Impaction among Kerala Population a Cross Sectional Study.

Background: When a tooth does not erupt to the normal functional position, the tooth is said to be impacted. Impaction can be partial or complete which has many problems associated with it and adjacent tooth. Aim: To assess the prevalence of impaction and pattern of mandibular impaction among adults in Ernakulum district, Kerala. Methodology: Retrospective data were analyzed using panoramic radiographs of 1,500 subjects were correlated with demographic details age and gender. Two independent investigators carried out the research independently. Data were analyzed using SPSS. Results: The prevalence of teeth impaction was 22.0%. A total of 330 subjects presented with at least one impacted tooth. Mandibular third molars were the most commonly impacted tooth (17.46%). The mesioangular orientation was the most common pattern. There was no gender difference in prevalence of impaction (P >.05). Conclusion: Twenty two percent among Kerala population. The mandibular wisdom teeth were the most commonly impacted teeth. Mesioangular orientation was the most common pattern. No association was found between impacted teeth as per gender.

General and local predictors of mandibular cortical bone morphology in adult females and males: the seventh survey of the Tromsø Study.

OBJECTIVES: To analyze factors predicting mandibular cortical width (MCW) and mandibular cortical index (MCI) in adult females and males. MATERIAL AND METHODS: Data on 427 females and 335 males aged 40-84 from The Tromsø study: Tromsø7 were used. T-score, age, menopausal status (for females), remaining teeth, and periodontal status were analyzed in linear and logistic regression analyses as predictors of MCW and MCI, respectively. RESULTS: T-score, age, and the number of remaining teeth significantly predicted MCW in females but not males. Standardized ß coefficients were 0.286, -0.231, and 0.131, respectively. The linear regression model explained 24% of MCW variation in females. MCI in females was significantly predicted by T-score, age, and remaining teeth with the Wald values of 9.65, 6.17, and 5.83, respectively. The logistic regression model explained 16.3-23% of the variation in MCI in females. In males, T-score was the only significant predictor of the eroded cortex, and the logistic model explained only 4.3-5.8% of the variation in MCI. CONCLUSIONS: The T-score demonstrated a stronger relationship with MCW and MCI than other factors in females, which supports the usefulness of those indices for osteoporosis screening. Conversely, the T-score exhibited no association with MCW and remained the only significant predictor of MCI in males, yet to a lesser extent than in females. CLINICAL RELEVANCE: Understanding factors affecting mandibular cortical morphology is essential for further investigations of MCW and MCI usefulness for osteoporosis screening in females and males.

Dental radiographic changes in individuals with COVID-19: a controlled retrospective study.

OBJECTIVE: The aim of this study is to compare the pre-COVID-19 and post-COVID-19 dental radiological findings of individuals with positive rRT-PCR test results and with healthy controls using the apical periodontitis grade scale (APGS), radiographic-based periodontal bone loss (R-PBL), and radiographic DMFT indices, and to investigate the relatively long-term dental effects of COVID-19. METHODS: This study included people who had two panoramic radiographs taken between 2018 and 2022. There are 52 patients with positive rRT-PCR tests in the study group. The control group included 50 individuals. Study and control groups were compared using the apical periodontitis grade scale (APGS), radiographic-based periodontal bone loss (R-PBL), and radiographic DMFT indices. RESULTS: Although results showed a significant difference in percentage R-PBL value and R-PBL types in the study group, there was no significant difference in percentage R-PBL value and R-PBL types in the control group. Also, both groups showed a significant difference in the DMFT index. CONCLUSIONS: According to the results of this study, it can be said that COVID-19 increases the incidence of periodontitis, and it can be interpreted that the pandemic may adversely affect the general oral health of all people.

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.