A YOLO-V5 approach for the evaluation of normal fillings and overhanging fillings: an artificial intelligence study.

Dental fillings, frequently used in dentistry to address various dental tissue issues, may pose problems when not aligned with the anatomical contours and physiology of dental and periodontal tissues. Our study aims to detect the prevalence and distribution of normal and overhanging filling restorations using a deep CNN architecture trained through supervised learning, on panoramic radiography images. A total of 10480 fillings and 2491 overhanging fillings were labeled using CranioCatch software from 2473 and 1850 images, respectively. After the data obtaining phase, validation (80%), training 10%), and test-groups (10%) were formed from images for both labelling. The YOLOv5x architecture was used to develop the AI model. The model's performance was assessed through a confusion matrix and sensitivity, precision, and F1 score values of the model were calculated. For filling, sensitivity is 0.95, precision is 0.97, and F1 score is 0.96; for overhanging were determined to be 0.86, 0.89, and 0.87, respectively. The results demonstrate the capacity of the YOLOv5 algorithm to segment dental radiographs efficiently and accurately and demonstrate proficiency in detecting and distinguishing between normal and overhanging filling restorations.

Tomographic diagnosis of alveolar bone coverage impact in orthodontic planning: cross-sectional study.

INTRODUCTION: Alveolar bone coverage can be diagnosed through cone beam computed tomography (CBCT) and this information can prevent orthodontic tooth movement beyond the biological limit. OBJECTIVE: This study evaluated the impact of the bone coverage (BC) diagnosis by CBCT in the orthodontists' planning. METHODS: One hundred fifty-nine Brazilian orthodontists suggested treatment plans for six patients at two different times, using two sequential questionnaires. The first questionnaire consisted of extra and intra-oral photographs, one panoramic radiograph; one lateral cephalometric radiograph with Steiner and Tweed analysis, and the patient chief complaint. The second questionnaire included the same presentations of cases with tomographic images and the radiologist's report. The McNemar test assessed the difference between the first and the second treatment plans. RESULTS: In all six cases, most participants changed the treatment plan after evaluating the CBCT images and the radiologist's report (93.7% in case 5, 78.6% in case 4, 74.2% in case 3, 69.8% in case 6, 66% in case 2 and 61% in case 1; p≤0.01). CONCLUSION: The evaluation of bone coverage through CBCT images has a substantial impact on the orthodontic diagnosis and planning of the Brazilian orthodontists.

Descriptive analysis of the cases published in the Align® Global Gallery.

INTRODUCTION: Social media enhanced access to information, making it easier to share dental treatments. OBJECTIVE: This study aimed to conduct a descriptive analysis of the clinical cases published on the Align® Global Gallery platform. MATERIAL AND METHODS: A retrospective cross-sectional study of 1,582 cases was conducted, data extracted referred to the following basic information: case number; patient's age; reported gender; Invisalign® package modality; treatment time; aligner exchange protocol; total number of aligners per arch; type of retainers, and inclusion of initial and final panoramic and cephalometric radiographs. RESULTS: The majority were young (mean age 24.6 years, SD = 11.6), female patients (69.1%) with Class I malocclusion (39.4%) and crowding (77.9%). Comprehensive treatment was common (66.5%), with an average treatment time of 18 months (SD = 8.56; 95% CI = 17.6-18.5), with the most frequently reported aligner exchange protocol being 7 days (49.5%), with an average of 50.6 aligners in the upper arch (SD = 26.9; 95% CI = 49.2-51.9), and 48.7 in the lower arch (SD = 26.1; 95% CI = 47.4-50.0). Arch expansion (66.9%) and interproximal reduction (59.7%) were common approaches, while extractions were rare (4.3%). In most cases, initial lateral cephalometric (80.4%) and panoramic (93.3%) radiographs were presented. However, the final radiograph count dropped, with lateral cephalometric at 69.2%, and panoramic at 82.2% of cases. CONCLUSION: Cases in the Align®Global Gallery mostly feature Class I patients with crowded teeth, treated with expansion and interproximal reduction. The absence of standardized information and post-treatment data restricts the applicability of these findings to broader Invisalign® treatment trends.

Imaging diagnosis of compound - complex odontoma and impacted dental elements: a case report

O odontoma é o mais comum tumor odontogênico, definido como malformação benigna, geralmente descoberto na segunda década de vida, durante a investigação de erupção tardia de dentes adjacentes ou retenção prolongada de dentes decíduos. O odontoma é subdividido em composto e complexo. O Odontoma classificado como Composto é constituído por um conjunto de estruturas similares a dentes, de formas e tamanhos diversos, cercados por uma área delgada radiolúcida. Já o Odontoma Complexo se assemelha a uma massa calcificada que apresenta a mesma radiopacidade do tecido dentário, também cercado por uma área delgada radiolúcida. Ocasionalmente, esses dois aspectos podem ser vistos em uma mesma lesão. Frequentemente os odontomas podem provocar um aumento de volume ósseo local devido ao seu desenvolvimento. O diagnóstico é feito através de exames radiográficos de rotina e quando necessário pode-se também lançar mão de Radiografias Panorâmicas e Tomografia Computadorizada Cone Beam com o intuito de verificar sua extensão, as malformações e alterações de erupção causadas aos dentes adjacentes, assim como a classificação do tumor. Este relato de caso apresenta um Odontoma Composto-Complexo em um paciente de 13 anos, do sexo masculino, atendido em 2016 na Clínica de Diagnóstico Bucal II da Universidade Federal Fluminense, que apresentou elementos dentários 22 e 23 impactados, retenção prolongada do elemento 63 e aumento de volume na região anterior do lado esquerdo da maxila. Para obtenção do diagnóstico foram realizadas: Radiografias Periapicais, Radiografia Panorâmica e Tomografia Computadorizada Cone Beam. O objetivo deste trabalho foi elucidar as formas de diagnóstico por imagem que foram utilizadas neste caso clínico e quais as vantagens de cada exame.

Odontomas are the most common type of odontogenic tumors, defined as a benign malformation, usually diagnosed in the second decade of life, during the investigation of late adjacent teeth eruption or a delay in exfoliation of deciduous teeth. They are divided into two types: compound and complex. The odontoma classified as compound is composed of multiple small tooth-like structures, in several shapes and sizes, surrounded by a thin radiolucent rim. On the other hand, complex odontomas resemble a mass of calcified tissue that presents the same dental tissue radiopacity, also surrounded by a thin radiolucent rim. Occasionally, both aspects can be seen in the same lesion. Often, odontomas can cause a local increase in bone volume due to their development. The diagnosis is made through routine radiographic examination and, when it is necessary, it is possible to make use of panoramic radiographies and cone beam computed tomography with the purpose of verifying its extension, malformations and erupted alterations caused to the adjacent teeth, as well as the tumor classification. This case report presents a Compound-Complex Odontoma in a 13-year-old male patient, treated in 2016 at the Oral Diagnosis Clinic II of the Federal Fluminense University. He presented impacted teeth 22 and 23, delayed eruption of tooth 63 and volume increase in the left anterior maxilla site. Aiming the patient's diagnosis, the following exams were necessary: periapical radiographies, panoramic radiography, cone beam computed tomography. The aim of this paper is to explain the different image diagnostic tools which were used in this clinical study and what are the advantages of each exam.

Comparison of Faster R-CNN, YOLO, and SSD for Third Molar Angle Detection in Dental Panoramic X-rays.

The use of artificial intelligence algorithms (AI) has gained importance for dental applications in recent years. Analyzing AI information from different sensor data such as images or panoramic radiographs (panoramic X-rays) can help to improve medical decisions and achieve early diagnosis of different dental pathologies. In particular, the use of deep learning (DL) techniques based on convolutional neural networks (CNNs) has obtained promising results in dental applications based on images, in which approaches based on classification, detection, and segmentation are being studied with growing interest. However, there are still several challenges to be tackled, such as the data quality and quantity, the variability among categories, and the analysis of the possible bias and variance associated with each dataset distribution. This study aims to compare the performance of three deep learning object detection models-Faster R-CNN, YOLO V2, and SSD-using different ResNet architectures (ResNet-18, ResNet-50, and ResNet-101) as feature extractors for detecting and classifying third molar angles in panoramic X-rays according to Winter's classification criterion. Each object detection architecture was trained, calibrated, validated, and tested with three different feature extraction CNNs which are ResNet-18, ResNet-50, and ResNet-101, which were the networks that best fit our dataset distribution. Based on such detection networks, we detect four different categories of angles in third molars using panoramic X-rays by using Winter's classification criterion. This criterion characterizes the third molar's position relative to the second molar's longitudinal axis. The detected categories for the third molars are distoangular, vertical, mesioangular, and horizontal. For training, we used a total of 644 panoramic X-rays. The results obtained in the testing dataset reached up to 99% mean average accuracy performance, demonstrating the YOLOV2 obtained higher effectiveness in solving the third molar angle detection problem. These results demonstrate that the use of CNNs for object detection in panoramic radiographs represents a promising solution in dental applications.

The Brazilian (FRANCO) method for dental age estimation: Willems' model revisited.

OBJECTIVES: This study aimed (I) to test the Willems' dental age estimation method in different geographic samples of the Brazilian population, and (II) to propose a new model combining the geographic samples in a single reference table of Brazilian maturity scores. MATERIALS AND METHODS: The sample consisted of 5017 panoramic radiographs of Brazilian males (n = 2443) and females (n = 2574) between 6 and 15.99 years (mean age = 10.99 ± 2.76 years). The radiographs were collected from the Southeastern (SE) (n = 2920), Central-Western (CW) (n = 1176), and Southern (SO) (n = 921) geographic regions. Demirjian's technique was applied followed by Willems' method and the proposed Brazilian model. RESULTS: Willems' method led to mean absolute errors (MAE) of 0.79 and 0.81 years for males and females, respectively. Root mean squared errors (RMSE) were 1.01 and 1.03 years, respectively. The Brazilian model led to MAE of 0.72 and 0.74 years for males and females, respectively, and RMSE of 0.93 years for both sexes. The MAE was reduced in 70% of the age categories. Differences between regions were statistically (p < 0.05) but not clinically significant. CONCLUSION: The new model based on a combined population had an enhanced performance compared to Willems' model and led to reference outcomes for Brazilians. CLINICAL RELEVANCE: Assessing patients' biological development by means of dental analysis is relevant to plan orthopedic treatments and follow up. Having a combined-region statistic model for dental age estimation of Brazilian children contributes to optimal age estimation practices.

Estimation of human age using machine learning on panoramic radiographs for Brazilian patients.

This paper addresses a relevant problem in Forensic Sciences by integrating radiological techniques with advanced machine learning methodologies to create a non-invasive, efficient, and less examiner-dependent approach to age estimation. Our study includes a new dataset of 12,827 dental panoramic X-ray images representing the Brazilian population, covering an age range from 2.25 to 96.50 years. To analyze these exams, we employed a model adapted from InceptionV4, enhanced with data augmentation techniques. The proposed approach achieved robust and reliable results, with a Test Mean Absolute Error of 3.1 years and an R-squared value of 95.5%. Professional radiologists have validated that our model focuses on critical features for age assessment used in odontology, such as pulp chamber dimensions and stages of permanent teeth calcification. Importantly, the model also relies on anatomical information from the mandible, maxillary sinus, and vertebrae, which enables it to perform well even in edentulous cases. This study demonstrates the significant potential of machine learning to revolutionize age estimation in Forensic Science, offering a more accurate, efficient, and universally applicable solution.

Factores etiopatogénicos de maloclusión: el factor dentario en la organización de la oclusión. Parte III / Etiopathogenic factors of malocclusion: the dental effect in occlusal organization. Part III

Esta publicación es la última de una serie de tres, dirigida a la organización de la oclusión, en el marco de un enfoque sistémico. En las anteriores fueron desarrollados los temas referidos al espacio en los arcos dentarios restando analizar, entonces, aspectos de la erupción dentaria. Al respecto, se sintetizarán conceptos de la evolución deseable desde el origen de los folículos dentarios hasta su inclusión en el arco y contacto con el antagonista y se presentarán ejemplos de alteraciones ordenadas según el avance biológico de la dentición (AU)

This publication is the last in a series of three, aimed at the organization of occlusion, within the framework of a systemic approach. In the previous ones, the topics related to the space in the dental arches were developed, leaving to analyze, then, aspects of the dental eruption. In this regard, concepts of the desirable evolution from the origin of the dental follicles to their inclusion in the arch and contact with the antagonist will be synthesized, and examples of alterations ordered according to the biological progress of the dentition will be presented (AU)

Are Radiographic Changes in the Mandibular Canal Associated With Bone Mineral Density?

BACKGROUND: Osteoporosis, highly prevalent among postmenopausal women, significantly reduces bone density and increases the risk of fractures. Cortical bone, which constitutes the largest calcium deposit in the human skeleton, is primarily affected in various conditions, including osteoporosis. Due to its visibility in panoramic radiography, the cortical area of the mandibular canal could be valuable in assessing decreases in bone mineral density (BMD). PURPOSE: The study aimed to characterize and compare changes in the cortices of the mandibular canal between normal, osteopenic, and osteoporotic postmenopausal women. STUDY DESIGN, SETTING, SAMPLE: Our cross-sectional study analyzed postmenopausal patients. We included only patients with panoramic radiographs with good quality and who underwent osteoporosis risk assessment by dual-energy x-ray absorptiometry (DXA). INDEPENDENT VARIABLE: BMD was measured by DXA at 3 sites (spine, femur, and forearm) and used to classify the patients into normal, osteopenic, or osteoporotic. This classification remained consistent across all measurement sites. MAIN OUTCOME VARIABLE: The main outcome variable was BMD of the mandibular canal cortices measured using black pixel intensity. COVARIATES: Demographic covariates, including age, weight, height, and BMD, were assessed. ANALYSES: One-way analysis of variance between groups considering a P < .05. The relationship between covariates and dependent variables was assessed using the Pearson correlation test. RESULTS: The sample comprised 52 postmenopausal women aged more than 40 years (mean age 61 ± 10 years), 26 (50%) normal, 18 (35%) osteopenic, and 8 (15%) osteoporotic. Significant differences were observed in the percentage of black pixels in the mandibular ramus between the groups. In this region, the average percentage of black pixels was 3.19% (± 0.65) for the normal group, 2.78% (± 0.65) for the osteopenia group, and 2.35% (± 0.65) for the osteoporosis group (P = .015). No significant differences were found in other mandibular regions. CONCLUSION AND RELEVANCE: Our findings demonstrate an association between BMD assessed in the mandibular canal cortex and the presence of osteoporosis as determined by DXA. While the observed differences in black pixel percentages in the mandibular ramus are minor, they are statistically significant, suggesting that panoramic radiography may serve as an adjunctive tool for osteoporosis screening.

Prevalence and Pattern of Tooth Impaction: A Radiographic Study in a Trinidadian Population.

OBJECTIVE: The aim of this retrospective study was to determine the prevalence and patterns of impacted third molars in a Trinidadian population. METHODS: A total of 1500 orthopantomograms (OPG) taken at the School of Dentistry, University of the West Indies, from 2008 to 2019 in patients between 15 and 67 years old were evaluated. From the data collected, the prevalence of third molar impaction, the parameters of gender, angulation, level of impaction, and associated pathologies were evaluated. Other types of impacted teeth were also recorded. RESULTS: Of the 1500 OPG viewed, 408 (27.2%) of the study sample presented with at least one impacted third molar. 161 (39.5%) were males and 247 (60.5%) were females, with a male-to-female ratio of 1:1.5. There was a greater incidence of mandibular third molars versus maxillary third molars, which had a frequency of 77.9% and 22.1%, respectively. The most common type of impaction (Winter's classification) was horizontal in the mandible and distoangular in the maxilla. The most common level of impaction in the mandible (Pell and Gregory classification) was level 1A. The total number of impacted teeth was 775, and of these, 75 (9.7%) showed other impacted teeth besides the third molars. Canines and second premolars were the most prevalent with 7.6% and 1.5%, respectively. Caries on the second molar (49.3%) and third molars (40%) were the most frequently associated pathologies identified. CONCLUSION: The prevalence of impacted wisdom teeth in this study was 27%. These results raise awareness and provide insight among dental professionals in Trinidad as to the prevalence of impacted third molars, their patterns, as well as commonly associated pathologies, and the need for screening within the population.

Diagnostic capability of artificial intelligence tools for detecting and classifying odontogenic cysts and tumors: a systematic review and meta-analysis.

OBJECTIVE: To evaluate the diagnostic capability of artificial intelligence (AI) for detecting and classifying odontogenic cysts and tumors, with special emphasis on odontogenic keratocyst (OKC) and ameloblastoma. STUDY DESIGN: Nine electronic databases and the gray literature were examined. Human-based studies using AI algorithms to detect or classify odontogenic cysts and tumors by using panoramic radiographs or CBCT were included. Diagnostic tests were evaluated, and a meta-analysis was performed for classifying OKCs and ameloblastomas. Heterogeneity, risk of bias, and certainty of evidence were evaluated. RESULTS: Twelve studies concluded that AI is a promising tool for the detection and/or classification of lesions, producing high diagnostic test values. Three articles assessed the sensitivity of convolutional neural networks in classifying similar lesions using panoramic radiographs, specifically OKC and ameloblastoma. The accuracy was 0.893 (95% CI 0.832-0.954). AI applied to cone beam computed tomography produced superior accuracy based on only 4 studies. The results revealed heterogeneity in the models used, variations in imaging examinations, and discrepancies in the presentation of metrics. CONCLUSION: AI tools exhibited a relatively high level of accuracy in detecting and classifying OKC and ameloblastoma. Panoramic radiography appears to be an accurate method for AI-based classification of these lesions, albeit with a low level of certainty. The accuracy of CBCT model data appears to be high and promising, although with limited available data.

Unusually Pronounced and Expansive Mandibular Foramen. A Incidental Radiological Finding / Foramen Mandibular Inusualmente Pronunciado y Expansivo: Un Hallazgo Radiológico Incidental

SUMMARY: The mandibular foramen and its canal are one of the most important structures in the skull, as they solely supply the mandible through their associated nerves and vessels. Many anatomical variations have been reported in the literature until now, and this case report represents a clear-cut appearance of its shape in a panoramic radiograph, which is not mostly seen in normal panoramic radiographs. These factors are of utmost importance when it comes to performing various surgeries and preventing complications due to their varied anatomy, which will allow dentists to create a better treatment plan and provide better treatments without any complications.

El foramen mandibular y su canal son algunas de las estructuras más importantes del cráneo y cara, ya que a través de ellos la mandíbula es inervada por nervios e irrigada por vasos. Hasta ahora, en la literatura consultada, se han informado de numerosas variaciones anatómicas. En este trabajo reportamos la forma y trayecto del foramen y canal mandibular, obtenidos en una radiografía panorámica, que no es observada normalmente en este tipo de radiografía. Los factores anatómicos son de importancia a la hora de realizar las cirugías para prevenir complicaciones debido a su variada anatomía, permitiendo a los odontólogos crear un mejor plan de tratamiento sin ningún tipo de complicaciones.

Identification and classification of pulp calcifications in posterior teeth according to dental condition using digital panoramic radiography and cone beam CT.

OBJECTIVE: To compare digital panoramic radiography (DPR) and cone beam CT (CBCT) in the detection and classification of pulp calcifications in posterior teeth in relation to tooth condition and its location. METHODS: Two hundred and fifty patients with simultaneous DPR and CBCT scans were selected from a dental image bank. For each posterior tooth, its condition was registered (healthy, restored, or decayed). The presence of calcifications was assessed and classified according to location (coronal or radicular) and type (total obliteration, partial obliteration, narrowing, and no calcification). Chi-square and McNemar tests were used to compare DPR and CBCT results, with a significance level of 5%. DPR diagnostic values were calculated using CBCT as reference. RESULTS: Decayed and restored teeth showed a significantly (P < .001) higher prevalence of pulp calcifications than healthy teeth in both imaging exams. There was a significant discrepancy between the imaging modalities in the identification of calcifications (P < .001), especially for radicular calcifications of maxillary teeth (DPR = 55.2%; CBCT = 30.9%). In the case of coronal calcifications, there was a greater discrepancy between CBCT and DPR in the mandibular teeth (10.7%) than in the maxillary teeth (7.7%). Overall, DPR presents higher sensitivity (0.855) than specificity (0.483) for pulp calcifications detection. CONCLUSION: DPR considerably overestimates pulp calcifications in posterior teeth, as compared to CBCT. A higher prevalence of pulp calcifications is related to decayed and restored teeth.

Performance of a commercially available Generative Pre-trained Transformer (GPT) in describing radiolucent lesions in panoramic radiographs and establishing differential diagnoses.

OBJECTIVES: To evaluate the performance of a commercially available Generative Pre-trained Transformer (GPT) in describing and establishing differential diagnoses for radiolucent lesions in panoramic radiographs. MATERIALS AND METHODS: Twenty-eight panoramic radiographs, each containing a single radiolucent lesion, were evaluated in consensus by three examiners and a commercially available ChatGPT-3.5 model. They provided descriptions regarding internal structure (radiodensity, loculation), periphery (margin type, cortication), shape, location (bone, side, region, teeth/structures), and effects on adjacent structures (effect, adjacent structure). Diagnostic impressions related to origin, behavior, and nature were also provided. The GPT program was additionally prompted to provide differential diagnoses. Keywords used by the GPT program were compared to those used by the examiners and scored as 0 (incorrect), 0.5 (partially correct), or 1 (correct). Mean score values and standard deviation were calculated for each description. Performance in establishing differential diagnoses was assessed using Rank-1, -2, and - 3. RESULTS: Descriptions of margination, affected bone, and origin received the highest scores: 0.93, 0.93, and 0.87, respectively. Shape, region, teeth/structures, effect, affected region, and nature received considerably lower scores ranging from 0.22 to 0.50. Rank-1, -2, and - 3 demonstrated accuracy in 25%, 57.14%, and 67.85% of cases, respectively. CONCLUSION: The performance of the GPT program in describing and providing differential diagnoses for radiolucent lesions in panoramic radiographs is variable and at this stage limited in its use for clinical application. CLINICAL RELEVANCE: Understanding the potential role of GPT systems as an auxiliary tool in image interpretation is imperative to validate their clinical applicability.

Bone pattern changes in post liver transplant patients using bisphosphonates.

OBJECTIVE: To identify radiographic findings suggestive of drug-induced osteonecrosis and evaluate radiomorphometric patterns indicative of changes in bone mineral density in individuals transplanted for liver disorders using bisphosphonates. STUDY DESIGN: The study group included panoramic x-rays of liver transplant patients who are being monitored and who present a clinical status of osteoporosis and use bisphosphonates. The control group was made up of liver transplant patients who did not have osteoporosis. On panoramic radiographs, mental index (MI) and mandibular cortical index (MCI) and the presence of radiographic anomalies suggestive of osteonecrosis were evaluated. RESULTS: There were significant statistical results when comparing the groups in relation to the decrease in bone mineral density (BMD) with MCI-C3 (p = 0.036), however, there were none in relation to MI (p = 0.14). There were no valid statistical results when relating MCI (p = 0.94) and MI (p = 0.66) with reduced BMD and use of bisphosphonates. CONCLUSION: Liver transplant individuals using bisphosphonates present greater radiographic signs of bone sclerosis suggestive of a greater propensity to develop osteonecrosis of the jaw and an increased risk of presenting changes suggestive of reduced bone mineral density on panoramic radiographs when compared to liver transplant individuals not using bisphosphonates.

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.

Orthopantomography Versus Cone Beam Computed Tomography for the Assessment of the Proximity of Posterior Maxillary Apexes with the Maxillary Sinus: A Cross-sectional Study.

BACKGROUND: The lack of knowledge of the relation of the maxillary sinus with the apexes of maxillary posterior teeth can lead to important complications during common dental procedures. This can be avoided using different imaging techniques, such as orthopantomography (OPG) and cone beam computed tomography (CBCT). The present study aims to compare the performance of OPG with CBCT in measuring the vertical distance of the apexes of posterior-superior teeth to the maxillary sinus. METHODS: This study corresponded to a cross-sectional study. OPGs and CBCT scans were obtained from the same individuals, and the qualitative and quantitative vertical distance of the apexes in relation to the maxillary sinus was categorized and measured in mm. RESULTS: A total of 28 pairs of OPGs and CBCT scans from the same patients were obtained. About 381 roots were analysed, which included 89 upper first premolars, 51 upper second premolars, 115 upper first molars, and 126 upper second molars. Projection/protrusion was observed with more frequency in molars, specially 1º molars in both OPG (n= 75, 65.2%) and CBCT (n= 31, 27%); however, 106 more cases (27.9%) were classified as projected in the OPG compared to CBCT (p < 0.05). When comparing the performance of the OPG and CBTC for analysing all roots qualitatively, there was a 57.8% agreement between both techniques. This difference was statistically significant (p <0.0001). Statistically significant differences were also observed when comparing the millimetric differences. CONCLUSION: This study showed that OPG is not an accurate technique to observe the relationship between the maxillary sinus and the apexes of the upper posterior teeth. In those cases where precision is required when performing dental procedures in this area, CBCT should be used. When not available, the clinicians should be aware of the limitations of the OPG and add other complementary techniques.

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.

"Determining the efficacy of a machine learning model for measuring periodontal bone loss".

BACKGROUND: Considering the prevalence of Periodontitis, new tools to help improve its diagnostic workflow could be beneficial. Machine Learning (ML) models have already been used in dentistry to automate radiographic analysis. AIMS: To determine the efficacy of an ML model for automatically measuring Periodontal Bone Loss (PBL) in panoramic radiographs by comparing it to dentists. METHODS: A dataset of 2010 images with and without PBL was segmented using Label Studio. The dataset was split into n = 1970 images for building a training dataset and n = 40 images for building a testing dataset. We propose a model composed of three components. Firstly, statistical inference techniques find probability functions that best describe the segmented dataset. Secondly, Convolutional Neural Networks extract visual information from the training dataset. Thirdly, an algorithm calculates PBL as a percentage and classifies it in stages. Afterwards, a standardized test compared the model to two radiologists, two periodontists and one general dentist. The test was built using the testing dataset, 40 questions long, done in controlled conditions, with radiologists considered as ground truth. Presence or absence, percentage, and stage of PBL were asked, and time to answer the test was measured in seconds. Diagnostic indices, performance metrics and performance averages were calculated for each participant. RESULTS: The model had an acceptable performance for diagnosing light to moderate PBL (weighted sensitivity 0.23, weighted F1-score 0.29) and was able to achieve real-time diagnosis. However, it proved incapable of diagnosing severe PBL (sensitivity, precision, and F1-score = 0). CONCLUSIONS: We propose a Machine Learning model that automates the diagnosis of Periodontal Bone Loss in panoramic radiographs with acceptable performance.