Panoramic Radiographs Research Articles

Prevalence, Severity, and Correlation with Agenesis of Permanent Successors of Infraoccluded Primary Molars at Chonnam National University Hospital’s Department of Pediatric Dentistry

This study aimed to analyze the prevalence and severity of infraoccluded primary molars (IPM) and their correlation with the agenesis of permanent successors (APS). A total of 4,011 panoramic radiographs from children aged 4 to 11 years who had all 8 primary molars were examined. The prevalence of APS was analyzed based on the severity and tooth type of IPM. The prevalence of IPM was 13.0%, and there was no difference between genders. The majority of the children had two IPMs each. In all tooth types, mild infraocclusion was the most prevalent, whereas severe infraocclusion was the least frequent. Among the types of primary molars, the lower primary first molar (62.3%) was the most affected, followed by the lower primary second molar (27.7%), the upper primary second molar (5.8%), and the upper primary first molar (4.2%). Infraocclusion was 11.2 times more prevalent in the mandible than in the maxilla, with no significant difference between the left and right sides. The correlation between IPM and APS was also investigated. Among the subjects, 177 had one or more agenesis of premolars, of whom 54 (30.5%) had IPM. Additionally, among the 521 individuals with IPM, 54 individuals exhibited APS (10.4%). This study identified a noteworthy prevalence of infraocclusion, with notable variations among molar types. The LPFM was particularly affected. The majority of cases were classified as mild in severity. Furthermore, a compelling association between IPM and APS was established. Understanding this connection may enhance treatment strategies for infraoccluded teeth and tooth agenesis.

A study of tooth agenesis in a sample of Malagasy orthodontic patient

The aim of this study was to describe the specific features of dental agenesis in Malagasy people. A retrospective cross-sectional study was conducted in two private orthodontic clinics in the city of Antananarivo, Madagascar. A total of 72 panoramic radiographs of patients aged more than 7 years old and undergoing orthodontic treatment between January 2008 and September 2022 were examined. Dental agenesis was declared in the absence of crown mineralization on the radiograph. Wisdom teeth agenesis was not considered in this study. Data were collected, coded, processed, and analyzed using SPSS 20.0 software. Statistical significance was set at p < 0.05. A significant predominance of females (72.2% vs. 27.8%) was observed among subjects with tooth agenesis (p < 0.000). The mandible was the most affected arch (57%). The mandibular lateral incisor (83%) was the most frequently absent tooth, followed by the maxillary lateral incisor (69.3%) and the mandibular second premolar (12.2%). Dental position anomalies associated with agenesis included impacted tooth (41.7%) and tooth transposition (4.2%). The general characteristics of tooth agenesis in our study population did not show any major differences compared to previous researches in other countries. However, a difference linked to ethnic origin was observed regarding the type of tooth most frequently affected by agenesis.

Prevalence of Dental Anomalies in Patients with Non-syndromic Cleft Lip with or without Cleft Palate

This study aimed to assess the prevalence and distribution pattern of dental anomalies in the permanent teeth of patients with non-syndromic cleft lip with or without cleft palate. Additionally, it aimed to compare differences in dental anomalies between cleft and non-cleft areas, considering gender and cleft phenotype. Panoramic radiographs of 164 patients diagnosed with non-syndromic orofacial clefts were retrospectively analyzed by a single examiner to confirm dental anomalies. The dental anomalies investigated included tooth agenesis, supernumerary teeth, microdontia, rotation, ectopic eruption, and enamel hypoplasia. Cleft phenotypes were categorized into 7 types based on medical and dental records. A significantly higher prevalence of supernumerary teeth was observed in males than females within non-cleft areas (<i>p</i> = 0.017), with no significant differences in other dental anomalies. In non-cleft area, patients with cleft palate exhibited a high prevalence of tooth agenesis (<i>p</i> < 0.0001) and microdontia (<i>p</i> = 0.012) compared to other cleft phenotypes. Maxillary incisor rotation was closely associated with adjacent tooth agenesis in unilateral cleft lip and palate cases (<i>p</i> = 0.034). This study suggests that the additional subphenotype based on dental anomalies in patients with orofacial cleft may serve as applicable clinical markers.

Dental Implants in 18 Patients with Systemic Scleroderma: A Retrospective Radiographic Analysis Over a 5-Year Period with Focus on Marginal Bone Loss.

Patients with systemic scleroderma (SSc) often suffer from premature tooth loss. The aim of this study was to radiologically investigate bone loss at dental implants in patients with SSc and compare it with data from the literature on healthy patients. Mesial and distal bone level changes at implants were independently determined on panoramic and intraoral radiographs. They were double-checked after determination of evaluability by three different raters. Cohen's kappa was used to test for interrater reliability. Mean bone loss was estimated using linear regression analysis considering the patient as a random-effect implant and performed separately in predefined implant regions for different time points and for the mesial and distal sides of the implants. Mesial and distal bone level changes were analyzed in 61 implants using periapical and panoramic radiographs. In total, 114 radiographs from 18 patients were evaluable in both the mesial and distal regions. After a maximum observation period of 60 months, the mean peri-implant bone loss was 1.68 mm (range: 0.83 to 2.54 mm) at the distal aspect and 1.65 mm (range: 0.81 to 2.48 mm) at the mesial aspect in the right posterior mandible (region 44 to 47 [FDI numbering system]), whereas in the left posterior maxilla (regions 24 to 27), the mean peri-implant bone loss was 0.61 mm (range: 0.32 to 0.91 mm) at the distal aspect and 0.59 mm (range: 0.16 to 1.03 mm) at the mesial aspect. The mean bone loss 60 months after surgery was 1.05 mm (range: 0.85 to 1.25 mm). Marginal bone loss at implants in patients with SSc is comparable to data from the literature collected in healthy subjects.

Application of Orthopantomography in the Analysis of Bone Mineral Density in Patients with Osteogenesis Imperfecta

Osteogenesis imperfecta is a disorder characterized by osteopenia and bone fragility. Considering that orthopantomography is a routine diagnostic test in growing patients, it can be used to analyze bone density in these patients. The study sample consisted of 21 child patients diagnosed with OI, under medical treatment with antiresorptives and for whom orthopantomography was available, analyzed and compared with 20 healthy children. The panoramic radiographs were analyzed and the radiomorphometric indices and fractal dimension were measured after first selecting the areas of interest to be studied. The results showed that fractal dimension of the basal cortical bone was lower in the study group, and MCW was lower in patients with osteogenesis imperfecta. In addition, MCW and fractal dimension were lower with higher number of treatment cycles received. In light of the results obtained, we can conclude that panoramic radiography can be useful in analyzing changes in bone mineral density in these patients throughout the course of treatment.

Comparison of periapical radiography, panoramic radiography, and CBCT in the evaluation of trabecular bone structure using fractal analysis.

The aim of this study is to compare imaging techniques to evaluate trabecular bone structure using Fractal Analysis (FA). Fifteen sheep hemimandibles were used for this study. Digital images were obtained using periapical radiography, panoramic radiography, and cone-beam computed tomography (CBCT). CBCT imaging was performed in standard (STD) and high-resolution (HR) modes. FA was conducted using ImageJ 1.3 software with the box-counting method on the images. The fractal dimension (FD) values were analyzed by the statistical software Jamovi 1.6.23. Statistical significance was accepted as p < 0.05. The highest mean FD value was the FD on digital periapical radiographs (PaFD) (1.28 ± 0.04), and the lowest mean FD value was the FD on standard resolution cone-beam computed tomography images (STD-CBCTFD) (1.12 ± 0.10). Although there was no statistically significant difference between the PaFD and the FD on digital panoramic radiographs (PanFD) (p = 0.485), the PaFD was found to be significantly higher than STD-CBCTFD (p < 0.001), and the FD on high-resolution cone-beam computed tomography images (HR-CBCTFD) (p = 0.007). The PanFD was found to be significantly higher than the STD-CBCTFD (p = 0.004). According to our results, in the evaluation of trabecular bone structure using FA, periapical radiographs and panoramic radiographs have similar image quality for assessment of the FD. On the other hand, CBCT results did not correlate with results from any of the other techniques in this study.

Binary decisions of artificial intelligence to classify third molar development around the legal age thresholds of 14, 16 and 18 years

Third molar development is used for dental age estimation when all the other teeth are fully mature. In most medicolegal facilities, dental age estimation is an operator-dependent procedure. During the examination of unaccompanied and undocumented minors, this procedure may lead to binary decisions around age thresholds of legal interest, namely the ages of 14, 16 and 18 years. This study aimed to test the performance of artificial intelligence to classify individuals below and above the legal age thresholds of 14, 16 and 18 years using third molar development. The sample consisted of 11,640 panoramic radiographs (9680 used for training and 1960 used for validation) of males (n = 5400) and females (n = 6240) between 6 and 22.9 years. Computer-based image annotation was performed with V7 software (V7labs, London, UK). The region of interest was the mandibular left third molar (T38) outlined with a semi-automated contour. DenseNet121 was the Convolutional Neural Network (CNN) of choice and was used with Transfer Learning. After Receiver-operating characteristic curves, the area under the curve (AUC) was 0.87 and 0.86 to classify males and females below and above the age of 14, respectively. For the age threshold of 16, the AUC values were 0.88 (males) and 0.83 (females), while for the age of 18, AUC were 0.94 (males) and 0.83 (females). Specificity rates were always between 0.80 and 0.92. Artificial intelligence was able to classify male and females below and above the legal age thresholds of 14, 16 and 18 years with high accuracy.

Prevalence of External Root Resorption in Second Molar Associated with Impacted Mandibular Third Molars: A Radiographic Study

Background: Mandibular third molars are the most frequently encountered impacted teeth in dental surgery cases. Impactions could be caused by differences in crown size, later development of roots, reduced skeletal growth and lack of space. If untreated, an impacted tooth can lead to a number of problems, including external root resorption, which is frequently observed in mandibular second molars. The current study was designed to investigate the prevalence of root resorption of mandibular second molar caused by impacted mandibular third molar. METHODS: A cross-sectional, observational study using panoramic radiographs obtained from December 2019 to February 2022 from of patients who visited the Dental Clinic of the University of Benghazi. All radiographs were assessed about presence, location and severity of external root resorption of second molar. Positions of the impacted third molars were classified using two classification systems Pell, Gregory's and Winter classification. Data were tabulated and analyzed using Chi Square test; P value was set at 0.05. RESULTS: Panoramic radiographs of 434 patients were examined that consisted of 244 (56.2%) female and 190 (43.7%) male. The prevalence of external root resorption of second molar was 213(49%). The severity of resorption was categorized as slight (70.4%), moderate (17.8%), and severe (11.7%), most of them was located at cervical third. External root resorption was proportionally higher in the impacted teeth with class B (50.2%) and mesio-angular positions (62.9%). CONCLUSIONS: Prevalence of external root resorption of mandibular second molars caused by Impacted third molars was high in this study especially in males. Mandibular third molars with a greater potential to cause the adjacent second molar's external root resorption were those in class B position according to Pell and Gregory classification and in mesioangular position regarding Winter classification. Keywords: Panoramic, Radiograph, Root resorption, second molar, third molar, Impacted.

Role of ortho-pantho-graphic X-ray in the diagnosis of osteoporosis

Background: Osteoporosis affects people, especially old age, as postmenopausal women and remains unnoticeable until the patient presents with a fracture. Osteoporosis in human begins started with the loss of bone mass that increases with age, this is related to the decrease in bone density and an increase in porosity that will cause fractures in this osteoporotic bone. Objective was to assess the usefulness of orthopanthographic (OPG) in the early detection of osteoporosis. Methods: This is an analytic across-sectional test validation study, was done in Hawari Hospital-Benghazi, Libya which considered a referral General Hospital affiliated with University of Benghazi. This study was done during a period from March 2022 to July 2023. Sixty women were selected, divided into osteoporotic and non osteoporotic groups depending on the clinical and laboratory investigations under the supervision of an orthopedic consultant in the outpatient clinic. Panoramic radiographic X-rays were taken for evaluation and estimation of the mandibular cortex on the basis of (Mental index, Klemetti index, and Panoramic mandibular index) as a diagnostic tool to differentiate normal from osteoporotic patient, all three indices correlated significantly with bone mineral density and used as useful indicators for detected the osteopenia and osteoporosis. Results: We calculated values of the three indices (Mental index, Klemetti index, and Panoramic mandibular index) values were low especially in the osteoporotic group, as well the values of mental index and panoramic mandibular index were low compared with low bone mineral density of the patient and klemetti index with: C2, C3 categories (moderate and severe erosion) most common observed in the osteoporotic patient. Conclusions: Orthopanthographic X-rays provide a valuable tool for early detection and assessment of osteoporosis (preclinical stage) especially when characterized by a decrease in bone mineral density.

STSN-Net: Simultaneous Tooth Segmentation and Numbering Method in Crowded Environments with Deep Learning.

Accurate tooth segmentation and numbering are the cornerstones of efficient automatic dental diagnosis and treatment. In this paper, a multitask learning architecture has been proposed for accurate tooth segmentation and numbering in panoramic X-ray images. A graph convolution network was applied for the automatic annotation of the target region, a modified convolutional neural network-based detection subnetwork (DSN) was used for tooth recognition and boundary regression, and an effective region segmentation subnetwork (RSSN) was used for region segmentation. The features extracted using RSSN and DSN were fused to optimize the quality of boundary regression, which provided impressive results for multiple evaluation metrics. Specifically, the proposed framework achieved a top F1 score of 0.9849, a top Dice metric score of 0.9629, and an mAP (IOU = 0.5) score of 0.9810. This framework holds great promise for enhancing the clinical efficiency of dentists in tooth segmentation and numbering tasks.

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.

The Prevalence of Congenitally Missing Permanent Teeth in a Sample of Orthodontic and Non-Orthodontic Caucasian Patients.

Hypodontia represents a notable clinical and public health concern. To assess the prevalence of congenitally missing permanent teeth in a sample of orthodontic/dental patients of Caucasian origin originating from the Greek island of Lesvos. Panoramic X-rays from 621 children and adolescents, aged 9 to 16 years (average age 12.5 years), 521 seeking orthodontic care (orthodontic group) and 100 seeking dental care (non-orthodontic group) were examined to identify congenitally missing permanent teeth. The orthodontic group exhibited a 5.5% prevalence of congenitally missing permanent teeth (2.8% females; 2.7% males), while the non-orthodontic group showed a prevalence of 4% (3% females; 1% males). The descending order of prevalence for missing tooth types was as follows: lower second premolars, upper laterals, lower central incisors, lower canines, upper second premolars, and lower second molars. Among orthodontic patients with missing teeth, 62% presented with an Angle's Class II malocclusion. Hypodontia was most frequently observed in the mandible. No statistically significant differences were observed between the orthodontic and non-orthodontic groups in terms of the percentage of children and types of congenitally missing teeth. Congenitally missing teeth were observed in about 4-5% of the studied population with a female predilection. The lower second premolar was the most commonly absent tooth, followed by the maxillary lateral incisors. An Angle's Class II malocclusion was present in the majority of orthodontic patients with hypodontia, mostly in the mandible.

Performance evaluation of a deep learning model for automatic detection and localization of idiopathic osteosclerosis on dental panoramic radiographs

Idiopathic osteosclerosis (IO) are focal radiopacities of unknown etiology observed in the jaws. These radiopacities are incidentally detected on dental panoramic radiographs taken for other reasons. In this study, we investigated the performance of a deep learning model in detecting IO using a small dataset of dental panoramic radiographs with varying contrasts and features. Two radiologists collected 175 IO-diagnosed dental panoramic radiographs from the dental school database. The dataset size is limited due to the rarity of IO, with its incidence in the Turkish population reported as 2.7% in studies. To overcome this limitation, data augmentation was performed by horizontally flipping the images, resulting in an augmented dataset of 350 panoramic radiographs. The images were annotated by two radiologists and divided into approximately 70% for training (245 radiographs), 15% for validation (53 radiographs), and 15% for testing (52 radiographs). The study employing the YOLOv5 deep learning model evaluated the results using precision, recall, F1-score, mAP (mean Average Precision), and average inference time score metrics. The training and testing processes were conducted on the Google Colab Pro virtual machine. The test process's performance criteria were obtained with a precision value of 0.981, a recall value of 0.929, an F1-score value of 0.954, and an average inference time of 25.4 ms. Although radiographs diagnosed with IO have a small dataset and exhibit different contrasts and features, it has been observed that the deep learning model provides high detection speed, accuracy, and localization results. The automatic identification of IO lesions using artificial intelligence algorithms, with high success rates, can contribute to the clinical workflow of dentists by preventing unnecessary biopsy procedure.

Prevalence of panoramic radiographs findings of cementum‐osseous dysplasia with calcification in the department of oral surgery at hospital: A retrospective study

AbstractAimCemento‐osseous dysplasia (COD) is a benign, non‐neoplastic, fibro‐osseous lesion that is often asymptomatic and discovered incidentally on dental radiographs. Radiological examination, rather than biopsy, is recommended for diagnosis because of the risk of infection. The dentist working at a hospital sometimes requests a family dentist to follow up on the progress of COD discovered accidentally during panoramic radiography at a hospital. However, there are few reports on the prevalence of COD on panoramic radiographs obtained at the oral surgery department of a hospital; therefore, we investigated this in this study.Materials and methodsWe examined the prevalence of COD with calcification (classification, presence of infection, and complications with simple bone cysts) in 1194 patients for whom panoramic radiographs were obtained.ResultsTwelve patients (1.0%) had findings of COD with calcification: four cases of periapical COD (three females and one male), five cases of focal COD (four females and one male), and three cases of florid COD (three females and zero males). Infection was seen in one case of Florid COD and one case of Focal COD. A simple bone cyst was observed in one patient with Florid COD.ConclusionCOD with calcification was observed in a certain percentage of patients, and many were asymptomatic. Dental healthcare workers need to understand that COD carries a risk of infection and that there are diseases that need to be differentiated. Patients should also be advised about the need for long‐term follow‐up.

Accelerating computer vision-based human identification through the integration of deep learning-based age estimation from 2 to 89 years

Computer Vision (CV)-based human identification using orthopantomograms (OPGs) has the potential to identify unknown deceased individuals by comparing postmortem OPGs with a comprehensive antemortem CV database. However, the growing size of the CV database leads to longer processing times. This study aims to develop a standardized and reliable Convolutional Neural Network (CNN) for age estimation using OPGs and integrate it into the CV-based human identification process. The CNN was trained on 50,000 OPGs, each labeled with ages ranging from 2 to 89 years. Testing included three postmortem OPGs, 10,779 antemortem OPGs, and an additional set of 70 OPGs within the context of CV-based human identification. Integrating the CNN for age estimation into CV-based human identification process resulted in a substantial reduction of up to 96% in processing time for a CV database containing 105,251 entries. Age estimation accuracy varied between postmortem and antemortem OPGs, with a mean absolute error (MAE) of 2.76 ± 2.67 years and 3.26 ± 3.06 years across all ages, as well as 3.69 ± 3.14 years for an additional 70 OPGs. In conclusion, the incorporation of a CNN for age estimation in the CV-based human identification process significantly reduces processing time while delivering reliable results.

Third molar angulation and retromolar space after functional orthodontic treatment : Evaluation of panoramic radiographs after monoblock or Herbst appliance.

The aim of this respectively cohort study was to evaluate the lower second and third molars and canine angulations, retromolar space and occlusal relationships after functional orthodontic treatments with the monoblock or Herbst appliance using panoramic radiographs. Pre- and posttreatment cephalometric and panoramic radiographs of 133 patients (mean age 13.89 ± 1.14years) treated non-extraction with monoblock (n: 44), Herbst (n: 45) and fixed orthodontic appliances (control group; n: 44) were included to the study. Dental and skeletal measurements were performed on cephalometric radiographs. The angle between the third and second molars, and canines with the lower border of the mandible and the occlusal plane, gonial angle, the angle between the third and second molars and the retromolar space width were assessed on pre- and posttreatment panoramic radiographs. Paired and independent ttests were used for the statistical analysis of the data for intragroup and intergroup comparisons. Functional treatment with both the monoblock and the Herbst appliances resulted in improvement of skeletal classII relationships. Retromolar space significantly increased in the functional appliance groups compared to the control group (p ≤ 0.001), but improvement of the angulations of posterior teeth was significant only in the monoblock group (p ≤ 0.001). While both the Herbst and monoblock appliances led to an increase in retromolar space, monoblock treatment resulted in more favorable angulation of the third molars compared to the Herbst treatment.

Relationship between Skeletal Malocclusion and Radiomorphometric Indices of the Mandible in Long Face Patients.

This study aimed to assess the relationship between skeletal malocclusion and radiomorphometric indices of the mandible in long face patients. This cross-sectional study evaluated 174 lateral cephalograms and panoramic radiographs of long face patients between the ages of 17 and 30 presenting at the Orthodontics Department of Qazvin Dental School. The gonial angle, antegonial angle, type of antegonial notch, and depth of antegonial notch were measured bilaterally on panoramic radiographs. The correlation between the radiomorphometric parameters and the type of occlusion was analyzed using one-way ANOVA, independent t-test, Chi-square test, and Fisher's exact test (alpha = 0.05). The mean size of gonial angle was significantly different among the three classes of occlusion (p = 0.046), while the difference was not significant regarding the antegonial angle size and antegonial notch depth (p > 0.05). An independent t-test showed that the mean sizes of gonial angle (p = 0.026) and antegonial angle (p = 0.036), and the antegonial notch depth (p = 0.046) in males, were significantly greater than the values in females. According to the Chi-square and Fisher's exact test, the right antegonial notch type was significantly different among the three classes of malocclusion (p = 0.006), while this difference was not significant in the left side (p = 0.318). The right antegonial notch type II was more common in males, while the right antegonial notch type I was more common in females (p = 0.014). According to the results, the indices of gonial angle and type of antegonial notch can be clinically useful for predicting the growth rate of the mandible and designing the appropriate treatment in long face patients.

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

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. 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. 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%. AI algorithms can be automated to preprocess PRs and improve the identification of impacted canines.

Performance of a deep learning system for simultaneously diagnosing radiolucent and radiopaque lesions in the anterior maxilla on panoramic radiographs

AbstractAimTo validate the performance of a deep learning system with detection and classification functions for a mix of radiolucent and radiopaque lesions in the anterior maxilla on panoramic radiographs.MethodsPatients with radiolucent or radiopaque lesions in the anterior maxilla on panoramic radiographs were selected retroactively from May 2022 until Feb 2002 to obtain 100 preoperative radiographs each for nasopalatine duct cysts (NDCs), radicular cysts (RCs), and impacted supernumerary teeth (ISTs). An additional 100 patients with no lesions in the anterior maxilla were selected. Two deep learning systems (Systems 1 and 2) were created and tested. For System 1, the models were created and tested using datasets of radiolucent lesions (NDCs and RCs) and No lesions. For developing System 2, the data of radiopaque lesions (ISTs) were added to those used in System 1. The neural network used was You Only Look Once ver. 7 (YOLOv7). The recall, precision, F1 score, and accuracy calculated from the confusion matrix were used to evaluate diagnostic performance.ResultsThe performance of System 2, which included the IST data, was worse than that of System 1. Even when NDCs and RCs were addressed as a joint category of radiolucent lesions, the addition of IST data resulted in a worse performance than that of System 1.ConclusionOur results indicate that combined use of radiopaque lesions (ISTs) with radiolucent lesions (NDCs and RCs) reduces the deep learning performance for radiolucent lesions with the volume of data used in the present study.

Caries Experience before and after COVID-19 Restrictions: An Observational Study.

Background: The declaration of COVID-19 as a pandemic by the World Health Organization in 2020 led to the suspension of several clinical practices globally, including dentistry. This study investigates the impact of these restrictions on dental caries experience. Methods: A retrospective cross-sectional study was conducted at Egas Moniz University's dental hospital in the Lisbon Metropolitan Area from June 2019 to June 2021. The study involved 3380 participants who were divided into two cohorts: after and before COVID-19 restrictions. Data collection included a questionnaire, full-mouth clinical examinations, and radiographs (panoramic X-rays, bitewings). Results: Before the COVID-19 restrictions, the prevalence of dental caries was 91.8%, with an average DMFT (decayed, missing, and filled teeth) index of 12.13. Post-restrictions, the prevalence decreased to 84.5%, with a DMFT index of 10.99. There was an increase in missing teeth and a decrease in decayed and filled teeth. Additionally, the frequency of toothbrushing declined among participants. Conclusions: The COVID-19 pandemic restrictions have significantly impacted dental caries experiences and oral health, highlighting a decrease in dental caries, but also a concerning reduction in oral hygiene practices. These results emphasize the importance of customized dental healthcare during public health emergencies to reduce impacts and maintain oral health.