Panoramic Radiographs Research Articles

Clinical Image Quality Evaluation For Panoramic Radiography: Clinical Audit

Clinical Image Quality Evaluation For Panoramic Radiography: Clinical Audit

Patterns of mandibular third molar impaction and its relationship with distal caries in the adjacent mandibular second molars: A retrospective study

BackgroundImpacted third molars can cause significant challenges for dental health. While many of these impacted teeth remain asymptomatic, they can lead to dental caries. ObjectiveTo investigate the patterns of mandibular third molar impaction and its relationship with the occurrence of caries in the adjacent mandibular second molars. Materials and MethodsThis study assessed the dental panoramic radiographs of 1591 participants who visited the Department of Oral and Maxillofacial Surgery at the Dental Teaching Hospital at Umm Al-Qura University between 2022 and 2024. The presence of distal caries in the adjacent mandibular second molars was assessed and compared across the different impaction patterns, considering both age and gender. ResultsThe results showed that 29.22 % of the patients had impacted mandibular third molars. The most common patterns of impacted mandibular third molar angulation were mesioangular in the females and horizontal in the males. The majority of these impacted third molars were level A and class I (as per the Pell and Gregory classification).One hundred and eighty-three (39.35 %) of the impacted mandibular third molars had associated carious lesions, with 89 showing distal caries in the adjacent mandibular second molar and 18 showing caries in the third molar itself. The carious lesions were most commonly found in cases of mesioangular, level A, and class I impaction patterns (p < 0.05). ConclusionThe findings of this study shed light to the high prevalence of carious lesions associated with impacted mandibular third molar, especially in cases of mesioangular, level A, and class I impaction patterns. These findings highlight the importance of careful monitoring of impacted third molars to prevent the development of caries in the adjacent teeth.

Fractal Analysis of Mandible in Panoramic Radiographs of Patients Received Radiotherapy for Nasopharyngeal Carcinoma

PurposeThis study aimed to assess the impact of radiotherapy on the internal structure complexity of mandibular cortical and trabecular bone and to determine the duration required for a return to healthy values post-radiotherapy. Materials and MethodsPanoramic radiographs from patients undergoing radiotherapy for nasopharyngeal carcinoma were analyzed before and after treatment. Four groups were formed based on post-radiotherapy radiography timing (0-6 months, 6-12 months, 12-24 months, and 24-36 months), comprising a total of 59 cases and 118 radiographs. Fractal analysis was conducted on four bilateral regions (ROI) in both trabecular and cortical bone on each radiograph. Additionally, measurements of inferior alveolar canal width and mandibular cortical width were performed. Mean and maximum radiation dose values to the mandible were measured, and their correlation with changes in fractal dimension, inferior alveolar canal width, and mandibular cortical width values was assessed. ResultsFractal dimension values in regions over trabecular bone showed a statistically significant decrease in all groups, although no significant difference was observed among the four groups. In ROI-4 from cortical bone, a significant fractal dimension decrease was noted in all groups except the 0-6 month group. The magnitude of fractal dimension decrease was higher in the 12-24 and 24-36 month groups compared to the 0-6 month group. inferior alveolar canal width and mandibular cortical width values significantly decreased post-radiotherapy in all groups, with a consistent decrease across the groups. ConclusionsRadiotherapy induces a reduction in the internal complexity of trabecular and cortical bone structures in the mandible. Osteoradionecrosis risk persists even three years post-radiotherapy, suggesting a cautious approach to interventional procedures on the bone.

Clinical knowledge-guided hybrid classification network for automatic periodontal disease diagnosis in X-ray image

Accurate classification of periodontal disease through panoramic X-ray images carries immense clinical importance for effective diagnosis and treatment. Recent methodologies attempt to classify periodontal diseases from X-ray images by estimating bone loss within these images, supervised by manual radiographic annotations for segmentation or keypoint detection. However, these annotations often lack consistency with the clinical gold standard of probing measurements, potentially causing measurement inaccuracy and leading to unstable classifications. Additionally, the diagnosis of periodontal disease necessitates exceptional sensitivity. To address these challenges, we introduce HC-Net, an innovative hybrid classification framework devised for accurately classifying periodontal disease from X-ray images. This framework comprises three main components: tooth-level classification, patient-level classification, and a learnable adaptive noisy-OR gate. In the tooth-level classification, we initially employ instance segmentation to individually identify each tooth, followed by tooth-level periodontal disease classification. For patient-level classification, we utilize a multi-task strategy to concurrently learn patient-level classification and a Classification Activation Map (CAM) that signifies the confidence of local lesion areas within the panoramic X-ray image. Eventually, our adaptive noisy-OR gate acquires a hybrid classification by amalgamating predictions from both levels. In particular, we incorporate clinical knowledge into the workflows used by professional dentists, targeting the enhanced handling of sensitivity of periodontal disease diagnosis. Extensive empirical testing on a dataset amassed from real-world clinics demonstrates that our proposed HC-Net achieves unparalleled performance in periodontal disease classification, exhibiting substantial potential for practical application.

Comparative Evaluation of Condylar Guidance Obtained by Digital Panoramic Radiographic Images Using Two Different Interocclusal Recording Material During Jaw Relation in Completely Edentulous Patients: An In Vivo Study.

Objective To compare the condylar guidance value obtained during jaw relation by two different interocclusal recording materials to that obtained from OPG (Orthopantomogram). Materials and methods Two different interocclusal recording materials were used, namely bite registration wax (reinforced wax, by MAARC Dental Company) and bite registration paste (jet bite, coltene) for interocclusal records during jaw relations. An OPG is shot prior to the treatment, and horizontal condylar guidance (HCG) is traced joining the bony landmarks in a completely edentulous patient seeking complete denture treatment. All the conventional steps for complete denture fabrication up to jaw relation are performed. A facebow transfer is done on a Hanau H2 articulator, and height tracers (extra oral tracing devices) are attached. After satisfactory training, the tracing is performed by the patient, and the interocclusal records are obtained. The articulator is programmed to obtain the value of HCG using protrusive records, which are then compared to the value obtained from OPG. Statistics were carried out to determine angles. Followed by statistical analysis with Pearson correlation to analyze the results (α = 0.01). Results A substantial relationship was discovered between the horizontal condylar inclination between two interocclusal recording materials and the corresponding OPG for both the right (p = 0.0015) and left (p = 0.0007) sides. Conclusion The condylar guidance obtained with jet bite was closer than the condylar guidance value obtained with reinforced wax when compared with the horizontal condylar inclination obtained in OPG by tracing with a mean difference of 10° for polyvinyl siloxane and 20° for reinforced wax in seven subjects evaluated.

Determination of Mandibular Morphology in a Turkish Population With Bipolar I Disorder Using Panoramic Radiography.

The presence of specific craniofacial deviations may be evidence of abnormal early brain development in bipolar disorder (BD). This study aimed to compare mandibular morphology in patients with BD versus nonpsychiatric controls using panoramic radiography. A total of 215 recorded images, 70 patients with BD and 145 controls, were evaluated. Seven mandibular parameters of the ramus height (RH), condylar height (CH), gonial angle (GA), antegonial angle (AGA), antegonial notch depth (AND), ramal notch depth (RND), and bigonial width (BGW) were measured in a blinded manner. Group analysis was conducted separately for males and females. The univariate comparisons showed increased values in RH, CH, AND, RND, and BGW and decreased values in GA in males with BD compared with male controls. In addition, females with BD had higher RH, CH, RND, and BGW values in comparison to female controls. The differences were statistically significant. Data from multivariate analyses revealed that increases in RH and BGW values in both sexes were significant predictive variables that distinguished patients with BD from controls. Moreover, deeper AND was the most prominent predictor that distinguished male patients with BD from male controls. The identification of subtle changes in mandibular measurements is consistent with the notion of impaired neurodevelopment in BD.

Evaluación tomográfica del mixoma odontogénico en maxilar superior. Reporte de caso y revisión de la literatura

Odontogenic myxoma (OM) is a slow-growing, painless, aggressive and non-metastatic central jaw tumor of mesenchymal origin. Radiographically, it can vary from a unilocular radiolucent lesion to a multilocular lesion with well-defined or diffuse margins. The aim of this paper is to recognize the radiographic and tomographic characteristics of OM in a patient who attended the Dental Clinic of the Faculty of Dentistry of the Universidad Nacional Mayor de San Marcos in Lima-Peru. Case presentation: 86 year old male patient, who in the panoramic radiography indicated for his oral rehabilitation, a unilocular radiolucent image was found in the anterosuperior area with partially defined limits, corticalized edges and oval shape. In the volumetric tomography there was evidence of thinning and erosion of both bone tables, thinning of the floor of the nasal cavity. The radiolucent image seems to havean extension close to the alveolar ridge. In adition, there was an effacement of the cortices of the nasopalatine duct. The lesion was enucleated and an anatomopathological examination was performed. Diagnosis was odontogenic myxoma. The patient was evaluated at one year and six months with satisfactory results. The wide variety of radiographic characteristics of odontogenic myxoma leads us to think of a large number of differential diagnoses, being the histological evaluation together with the imaging analysis the ones that provide a definitive diagnosis. Although the anterosuperior area is the least common for its presentation, radiolucent images in this area should be considered as possible odontogenic myxomas, since this condition is more frequent in latín race.

Prevalence and pattern of third molars impaction in a large Yemeni sample: a retrospective study.

The prevalence of teeth impaction varies substantially between different populations, and the impaction of third molars is the most commonly recorded. This study aimed to explore the prevalence and pattern of the third molars impactions among Yemeni population. This was a retrospective radiographic study conducted in Yemen between 2022 and 2023. The digital panoramic radiographs were collected from two major X-ray centers in Yemen. The angular position and depth of the impacted third molars were assessed according to the classifications of Winter and of Pell and Gregory, respectively. All radiographs were evaluated twice by one investigator in a two-week interval, and Kappa test was used for intra-rater reliability. Gender-wise differences, differences between both sides, and differences between maxilla and mandible were analyzed using Chi-squared tes with odds ratio (OR) for the risk of impaction. A P-value < 0.05 was considered significant. Panoramic radiographs of 6338 individuals were included. Their mean age was 35.1 ± 13.3 years andand 63.9% were females. A total of 25,352 sites (quadrants) were screened for the presence of thirds molars. Among which, 14,003 third molars (55.3%) were present in one or more sites. There were 1440 individuals (23%) with a total of 2828 impacted third molars (20% of the existing third molars). Females were less likely to have third molar impaction (OR = 0.46, CI95% = 0.4-0.52). Impaction of the mandibular third molars was significantly more frequent than the maxillary ones (OR = 1.15, CI95% = 1.04-1.26; P = 0.005). Horizontal and mesioangular impactions were statistically more frequent in the lower molars compared to the upper ones (P < 0.001 each). Contrastingly, vertical (P = 0.015), distoangular, and other impactions (P < 0.001 each)were statistically more frequent in the maxilla. Levels A and B were more frequent in the lower third molars, while level C was predominating in the upper molars (P < 0.001 each). The prevalence of third molars impaction is more frequent in males and mandibular arch. The angulation and level of impaction seem to be more complicated in the maxillary arch.

Radiographic identification of symptomless mandibular third molars without clinical pericoronitis

ObjectivesThe aim was to identify radiographic characteristics of mandibular third molars in young adults without symptoms or clinical signs of pericoronal infection.Materials and methodsAn existing cross-sectional material, including records from clinical oral examination and panoramic radiographs (PANs) of university students, was submitted to retrospective analysis. The outcome variable was a symptomless and clinically pericoronitis-free mandibular third molar. Predictor variables for the third molar were clinical eruption level, pathological signs in the follicle, marginal bone level, radiographic depth in bone, inclination, stage of root development, and available space for eruption. Statistics included χ2 and Mann-Whitney U tests.ResultsAnalysis included 345 mandibular third molars in 189 participants (20% men, 80% women; mean age 20.7 years; SD ± 0.6). Symptomless and clinically pericoronitis-free mandibular third molars were characterized as follows: clinically unerupted in 78% of teeth, associated with reduced marginal bone level in 70%, located deeper in the bone in 87%, mesially inclined in 73%, and stage of root development incomplete in 68% (p ≤ 0.001 for all).ConclusionsRadiographic characteristics of symptomless mandibular third molars without clinical pericoronitis in young adults can be assessed from a PAN with 68–87% certainty.Clinical relevanceThese findings may prove useful when trying to exclude non-pathological mandibular third molars from diseased teeth.

Accuracy of Mandibular Foramen Localization Using Digital Orthopantomogram (OPG) in Middle Eastern Population.

Locating the mandibular foramen (MF) through imaging is clinically important for inferior alveolar nerve (IAN) anesthesia and mandibular ramus osteotomies. Although cone-beam computed tomography (CBCT) is superior in imaging the mandible, an orthopantomogram (OPG) is preferred for its ease of use and availability. Therefore, the present study aimed to evaluate the accuracy of digital OPG in localizing the MF, in a subset of the Middle Eastern population. Radiographic images (OPG and CBCT) of selected patients (adults, dentulous and no mandibular abnormalities) were used to locate the MF through digital measurements (mm) of the anteroposterior distance from the anterior border of the ramus (MF-AP) and the superoinferior position from the mandibular occlusal plane (MF-SI). Measurements were statistically compared between OPG and CBCT for accuracy. Differences in measurements between OPG and CBCT were compared against the anatomic location (right/left), age and biological sex, assuming a p-value < 0.05 as significant. A total of 204 radiographic records (males: 100/females: 104/mean age: 34.65 ± 11.55 years) were evaluated. The measurements for the MF were MF-AP-OPG (right: 13.53 ± 2.44/left: 13.19 ± 2.25), MF-AP-CBCT (right: 13.61 ± 2.39/left: 13.36 ± 2.19), MF-SI-OPG (right: 5.25 ± 1.71/left: 5.41 ± 1.65) and MF-SI-CBCT (right: 5.59 ± 1.66/left: 5.52 ± 1.61). Measurements between OPG and CBCT were not significantly different, except for MF-SI (right) (p = 0.042). While the overall difference between OPG and CBCT (MF-AP/MF-SI) measurements showed a significant association (p < 0.01) with the anatomic location (right/left), a significant association (p < 0.05) with biological sex was observed only for MF-AP. Based on this study's outcomes, digital OPG is an accurate modality to locate the MF based on anteroposterior (MF-AP) and superoinferior (MF-SI) measurements. This would be clinically beneficial for dental and oral surgeons to achieve the optimum IAN block anesthesia based on preoperative panoramic radiographs. Similarly, it would assist maxillofacial surgeons in planning mandibular orthognathic surgeries and ramus osteotomies without complications.

Jaw bone changes in panoramic radiography in patients with hyperparathyroidism

Background and aims: The current investigation aimed to evaluate jaw bone changes, and compare the presence of gonial cortex bone thickness, mental index (MI), lamina dura (LD), lower dental canal, and bone density in panoramic radiography, in patients with hyperparathyroidism. Methods: The present cross-sectional descriptive-analytical study was performed on 17 healthy individuals and 17 patients who suffered from resorptive hypercalciuria in the dialysis center of Shahid Beheshti hospital in Babol in 2018. If patients had two or more decayed teeth, they were referred to a specialized maxillofacial clinic by the dentist for free panoramic imaging. Mandibular cortical index, LD, bone change, mandibular resorption (MR), and general cortical indices underwent examination. Results: The mean age of the control and case groups was 36.58±11.81 years and 40.23±14.32 years, respectively (P=0.424). In addition, the mean MI was 4.27±0.87 and 2.98±0.75 in the control and case groups, respectively (P&lt;0.001). Based on the results, the mean gonion region’s cortical bone thickness was 0.93±0.23 and 1.09±0.24 in the case and control groups, respectively (P&lt;0.001). Further, bone changes (P=0.036) and MR (P=0.017) were significantly different in the case and control groups. However, LD vision showed no significant difference in the hyperparathyroidism and the control groups (P=0.141). Conclusion: The results demonstrated a decrease in the thickness of the cortical bone in the guinea pig, mental region, and lack of dental canal in resorptive hypercalciuria compared to healthy individuals.

Linear measurements of the mandible on panoramic radiograph for sex estimation in populations in Yogyakarta, Indonesia

BackgroundIdentification is one of the main aspects of forensics. Sex estimation is an essential part of identification because it can simplify the whole process. Mandible is the largest, strongest, and sexually dimorphic bone and is part of the orofacial structure, which has the second highest level of dimorphism after the pelvic bone. Sex estimation using the mandible can be performed by conducting various linear measurements on a panoramic radiograph, including right minimum ramus width (RMiRW), left minimum ramus width (LMiRW), right projective height of ramus (RPHR), left projective height of ramus (LPHR), right maximum ramus width (RMxRW), left maximum ramus width (LMxRW), right coronoid height (RCH), left coronoid height (LCH), symphysis height (SH), right mandibular corpus height (RMCH), and left mandibular corpus height (LMCH). This study aimed to analyze how linear measurements in panoramic radiographs differ between men and women and to estimate sex by utilizing these parameters.ResultsIn this study, 195 panoramic radiographs from 95 men and 100 women aged 20–40 years obtained from our dental hospital were used as a training data. Meanwhile, 61 panoramic radiographs from 29 men and 32 women outside the training data with same characteristics were used as the testing data. The linear measurements of the mandible using panoramic radiographs were taken with EzDent-i Vatech software. Independent t-test showed significant difference (p < 0.05) in some linear measurements of the mandible between adult men and women. These significantly different linear measurements were then subjected to discriminant function analysis to produce sex estimation equations. The equation accuracy percentage ranged between 63.6 and 94.4% for the training sample and 59.5% and 85% for the testing sample.ConclusionThe linear measurements of the mandible using diagnostically acceptable panoramic radiographs taken from a patient with standardized head positioning can serve as an alternative method for sex estimation. The accuracy of discriminant analysis for sex estimation varies depending on the parameter used in the estimation.

Comparative Analysis of Impacted Mandibular Third Molar Root Proximity to the Mandibular Canal using Orthopantomography and Cone-beam Computed Tomography Imaging Modalities: A Pilot Study

Abstract Introduction: Fully detect risks of nerve damage, which can lead to temporary or permanent issues. Cone-beam computed tomography (CBCT) offers a three-dimensional (3D) view, providing more detailed visualisation of anatomical structures and their spatial relationships, which improves the accuracy of predicting nerve exposure. The study aims to evaluate and compare these imaging techniques’ effectiveness in categorising the relationship between third molars and the inferior alveolar canal, emphasising the importance of precise imaging for safer surgical outcomes. Materials and Methods: A pilot study involving 20 patients, representing 10% of the total sample size of 200, was conducted at Ahmedabad Dental College’s Department of Oral Medicine and Radiology. Investigators, trained to interpret radiological images from orthopantomography (OPG) and CBCT, compared their interpretations with those of two experts. A high inter-rater reliability was confirmed with a kappa statistic of 0.98. Following ethical approval, data were retrospectively collected from 20 cases, with digital OPG and CBCT images analysed and classified according to established criteria. Results: The results revealed a significant association between the results diagnosed through OPG and CBCT indicating similarity in their diagnosis. It was also seen that there was no bias towards the gender and the distribution was similar in case of diagnosis through OPG or CBCT. Conclusion: CBCT demands an in-depth understanding of anatomy and pathology, coupled with proficiency in operating imaging software and the ability to identify abnormalities in cross-sectional images. When executed and interpreted accurately, CBCT proves to be an exceptionally valuable tool in clinical dental practice. Its detailed 3D imaging capabilities enhance the assessment of complex cases, such as those involving intricate anatomical structures and pathologies. By providing comprehensive views that surpass traditional two-dimensional imaging, CBCT aids in precise diagnosis and treatment planning, making it an indispensable resource for addressing various dental conditions effectively.

The radiographic diversity of dental patterns among 7219 young individuals-a contribution to disaster victim identification.

The diversity of dental patterns is a fundamental topic in disaster victim identification. The current scientific literature, however, is scarce of data regarding young individuals. This study aimed to assess the radiographic diversity of dental patterns, considering missing, unrestored, and filled teeth in young individuals. The sample consisted of 7219 panoramic radiographs of individuals between 12 and 22.9 years. The permanent teeth, except third molars, were coded as missing, unrestored, or filled and odds ratios (OR) were calculated based on sex, dental arch, and age. The sex-combined sample had 1.116 distinctive dental patterns. "All unrestored" teeth was the most common pattern (OR: 0.437) followed by the sequence of unrestored teeth except restored mandibular first molars (OR: 0.021). Females had more distinctive dental patterns than males (p < .001), while males had more unrestored teeth (p < .001). In the age category of 12-12.9 years, the OR for finding a distinctive dental pattern was 11%, while in the age category of 22-22.9 years it increased to 58%. On the other hand, the OR for "all unrestored" gradually decreased according to age (74% in the younger category, and 23% in the older age category). The distinctiveness of dental patterns among young individuals is affected by the predominance of unrestored teeth. However, registering a single filled tooth in a remaining unrestored dentition can reduce exponentially the probability of finding an identical pattern of missing, unrestored and filled teeth.

Panoramic evaluation of external root resorption in mandibular molars during orthodontic treatment: a comparison between root-filled and vital teeth treated with fixed appliances or clear aligners

BackgroundThis investigation compared the extent of external apical root resorption (EARR) in root-filled teeth (RFT) and their contralateral vital pulp teeth (VPT) counterparts during orthodontic treatment (OT) with clear aligner (CA) treatment or fixed appliance (FA) treatment.MethodsSixty-six patients with similar baseline American Board of Orthodontics (ABO) discrepancy index scores were divided into two groups: 37 patients (21 females, 16 males; mean age 17.45 ± 2.67 years) in the FA group, and 29 patients (18 females, 11 males; mean age 18.33 ± 1.96 years) in the CA group. Digital panoramic radiographs captured pre- and post-OT were used to measure tooth lengths and root surface measurements in mandibular molars. EARR in both RFT and contralateral VPT was evaluated pre- and post-OT. Statistical analysis employed paired t-tests, independent t-tests, and analysis of covariance (ANCOVA) (p < .05).ResultsAll teeth exhibited varying degrees of EARR following OT. FA treatment resulted in significantly longer treatment duration (p < .05) and greater EARR compared to CA treatment (p < .05). Moreover, statistically significant differences in EARR were observed within both groups between RFT and VPT (p < .05).ConclusionsComparison of pre- and post-OT radiographs revealed different degrees of EARR in all teeth. CA treatment resulted in less frequent and less severe EARR compared to FA treatment. RFT demonstrated greater resistance to EARR than VPT in both treatment groups.

Evaluation of age estimation using alveolar bone images

ObjectiveThe purpose of this study is to examine the time-related changes of alveolar bone in 2D images quantitatively and to estimate age groups based on the change index. Materials and methodsThe 238 panoramic X-ray images and 140 CT panoramic reconstructed images of the permanent dentition period were used to examine age-related changes. Comparisons between the younger age group and each of the other age groups were calculated using the landmark method of Procrustes analysis. As aging changes were observed in each age group, age estimation was performed using antemortem panoramic X-ray images and postmortem CT images so that they could be used in practice. The CT images used in the age estimation were performed using forty-two postmortem CT panoramic reconstructed images of known age submitted to the judicial autopsy. ResultsBoth panoramic and CT images showed changes in the alveolar bone over time. Age estimation using postmortem CT images provided a certain assessment. ConclusionIn this study, clinically observed changes in alveolar bone over time were quantified on the images. Furthermore, the possibility of age estimation by alveolar bone was also suggested. The use of an updatable clinical database that can be stored in coordinate values offers the potential for age estimation in line with the times.

X-ray Image Analysis for Dental Disease: A Deep Learning Approach Using EfficientNets

Dental cavities are a highly common persistent dental problem that impacts populations across different age groups on a global scale. It is crucial to get a dental issue diagnosed as early as possible and with as much accuracy as possible to treat it efficiently and prevent any related issues. If a dental infection is not treated, it will eventually grow and cause tooth loss. Dental X-ray images are crucial and beneficial in the diagnostic process of dental diseases for dentists. By applying Deep Learning (DL) techniques to dental X-ray images, dental experts can efficiently and precisely detect dental conditions, including dental cavities, fillings and implants. The objective of this research is to assess the performance of DL-based methods for dental disease detection via panoramic radiographs. In this study, we evaluated the performance of all of the EfficientNet variants (e.g., EfficientNets B0-B7) to determine which one is the most effective model for detecting dental disease. Moreover, we utilized the Borderline Synthetic Minority Oversampling Technique (SMOTE) to cope with the issue related to the minority classes contained in the dataset. To assess the efficacy of the model, various metrics are employed, including recall, accuracy, precision, loss, and F1-score. As a result, the performance of the EfficientNet-B5 model was superior to that of the other EfficientNet models. The EfficientNet-B5 model achieved the following values for its metrics: F1-score, accuracy, recall, AUC, and precision: 98.37%, 98.32%, 98.32%, 99.21%, and 98.32%, respectively. The accuracy rates for the EfficientNet-B0, EfficientNet-B1, EfficientNet-B2, EfficientNet-B3, EfficientNet-B4, EfficientNet-B6, and EfficientNet-B7, are 91.59%, 94.12%, 93.28%, 85.71%, 94.96%, 96.64% and 90.76%, respectively. The results indicated that the EfficientNet-B5 model performs better than other EfficientNet classifiers, which supports dental professionals significantly in the recognition of dental diseases.

Enhanced Osteoporosis Detection Using Artificial Intelligence: A Deep Learning Approach to Panoramic Radiographs with an Emphasis on the Mental Foramen.

Osteoporosis, a skeletal disorder, is expected to affect 60% of women aged over 50 years. Dual-energy X-ray absorptiometry (DXA) scans, the current gold standard, are typically used post-fracture, highlighting the need for early detection tools. Panoramic radiographs (PRs), common in annual dental evaluations, have been explored for osteoporosis detection using deep learning, but methodological flaws have cast doubt on otherwise optimistic results. This study aims to develop a robust artificial intelligence (AI) application for accurate osteoporosis identification in PRs, contributing to early and reliable diagnostics. A total of 250 PRs from three groups (A: osteoporosis group, B: non-osteoporosis group matching A in age and gender, C: non-osteoporosis group differing from A in age and gender) were cropped to the mental foramen region. A pretrained convolutional neural network (CNN) classifier was used for training, testing, and validation with a random split of the dataset into subsets (A vs. B, A vs. C). Detection accuracy and area under the curve (AUC) were calculated. The method achieved an F1 score of 0.74 and an AUC of 0.8401 (A vs. B). For young patients (A vs. C), it performed with 98% accuracy and an AUC of 0.9812. This study presents a proof-of-concept algorithm, demonstrating the potential of deep learning to identify osteoporosis in dental radiographs. It also highlights the importance of methodological rigor, as not all optimistic results are credible.

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.

DentAge: Deep learning for automated age prediction using panoramic dental X-ray images.

Age estimation plays a crucial role in various fields, including forensic science and anthropology. This study aims to develop and validate DentAge, a deep-learning model for automated age prediction using panoramic dental X-ray images. DentAge was trained on a dataset comprising 21,007 panoramic dental X-ray images sourced from a private dental center in Slovenia. The dataset included subjects aged 4 to 97 years with various dental conditions. Transfer learning was employed, initializing the model with ImageNet weights and fine-tuning on the dental image dataset. The model was trained using stochastic gradient descent with momentum, and mean absolute error (MAE) served as the objective function. Across the test dataset, DentAge achieved an MAE of 3.12 years, demonstrating its efficacy in age prediction. Notably, the model performed well across different age groups, with MAEs ranging from 1.94 (age group [10-20]) to 13.40 years (age group [90-100]). Visual evaluation revealed factors contributing to prediction errors, including prosthetic restorations, tooth loss, and bone resorption. DentAge represents a significant advancement in automated age prediction within dentistry. The model's robust performance across diverse age groups and dental conditions underscores its potential utility in real-world scenarios. Our model will be accessible to the public for further adjustments and validation, ensuring DentAge's effectiveness and trustworthiness in practical scenarios.