Radiographic assessment of the peri-implant site.

While peri-implant mucositis relies solely on clinical parameters, radiological assessment becomes indispensable for diagnosing peri-implantitis. Intraoral radiography, with its simplicity of application, low radiation exposure, and adequate representation of peri-implant structures, stands out as the standard of care for both immediate and follow-up assessments. Standardization by custom-made radiologic splints allows for excellent comparability with previous images and allows for the determination of even small changes in contour and density of the peri-implant bone. Furthermore, other radiographic modalities like panoramic radiography and cone beam computed tomography (CBCT) may provide useful features for specific patients and clinical cases while also showing innate limitations. Beyond the assessment of the marginal peri-implant bone level as the crucial parameter of clinical relevance, radiologic assessment may reveal various other findings related to the prosthetic restoration itself, the precision of its fit to the implant, and the peri-implant soft and hard tissues. Since such findings can be crucial for the assessment of peri-implant health and the implants' prognosis, a systematic diagnostic evaluation pathway for a thorough assessment is recommended to extract all relevant information from radiologic imaging. This article also provides an overview of the clinical and chronological indications for different imaging modalities in peri-implant issues.

Radiographic diagnosis of periodontal diseases - Current evidence versus innovations.

Accurate diagnosis of periodontal and peri-implant diseases relies significantly on radiographic examination, especially for assessing alveolar bone levels, bone defect morphology, and bone quality. This narrative review aimed to comprehensively outline the current state-of-the-art in radiographic diagnosis of alveolar bone diseases, covering both two-dimensional (2D) and three-dimensional (3D) modalities. Additionally, this review explores recent technological advances in periodontal imaging diagnosis, focusing on their potential integration into clinical practice. Clinical probing and intraoral radiography, while crucial, encounter limitations in effectively assessing complex periodontal bone defects. Recognizing these challenges, 3D imaging modalities, such as cone beam computed tomography (CBCT), have been explored for a more comprehensive understanding of periodontal structures. The significance of the radiographic assessment approach is evidenced by its ability to offer an objective and standardized means of evaluating hard tissues, reducing variability associated with manual clinical measurements and contributing to a more precise diagnosis of periodontal health. However, clinicians should be aware of challenges related to CBCT imaging assessment, including beam-hardening artifacts generated by the high-density materials present in the field of view, which might affect image quality. Integration of digital technologies, such as artificial intelligence-based tools in intraoral radiography software, the enhances the diagnostic process. The overarching recommendation is a judicious combination of CBCT and digital intraoral radiography for enhanced periodontal bone assessment. Therefore, it is crucial for clinicians to weigh the benefits against the risks associated with higher radiation exposure on a case-by-case basis, prioritizing patient safety and treatment outcomes.

Is cone-beam computed tomography more accurate than periapical radiography for detection of vertical root fractures? A systematic review and meta-analysis.

BACKGROUND: This study aimed to conduct a systematic review and meta-analysis to summarize the available evidence comparing the diagnostic accuracy of periapical radiography (PA) and cone-beam computed tomography (CBCT) for detection of vertical root fractures (VRFs). METHODS: A search was conducted in PubMed, Scopus, and Web of Science for articles published regarding all types of human teeth. Data were analyzed by Comprehensive Meta-Analysis statistical software V3 software program. The I2 statistic was applied to analyze heterogeneity among the studies. RESULTS: Twenty-three articles met the criteria for inclusion in the systematic review and 16 for the meta-analysis. The sensitivity and specificity for detection of VRFs were calculated to be 0.51 and 0.87, respectively for PA radiography, and 0.70 and 0.84, respectively for CBCT. CONCLUSIONS: The sensitivity of CBCT was higher than PA radiography; however, difference between the specificity of the two modalities was not statistically significant.

Exploring the Methodological Approaches of Studies on Radiographic Databases Used in Cariology to Feed Artificial Intelligence: A Systematic Review.

INTRODUCTION: A growing number of studies on diagnostic imaging show superior efficiency and accuracy of computer-aided diagnostic systems compared to those of certified dentists. This methodological systematic review aimed to evaluate the different methodological approaches used by studies focusing on machine learning and deep learning that have used radiographic databases to classify, detect, and segment dental caries. METHODS: The protocol was registered in PROSPERO before data collection (CRD42022348097). Literature research was performed in MEDLINE, Embase, IEEE Xplore, and Web of Science until December 2022, without language restrictions. Studies and surveys using a dental radiographic database for the classification, detection, or segmentation of carious lesions were sought. Records deemed eligible were retrieved and further assessed for inclusion by two reviewers who resolved any discrepancies through consensus. A third reviewer was consulted when any disagreements or discrepancies persisted between the two reviewers. After data extraction, the same reviewers assessed the methodological quality using the CLAIM and QUADAS-AI checklists. RESULTS: After screening 325 articles, 35 studies were eligible and included. The bitewing was the most commonly used radiograph (n = 17) at the time when detection (n = 15) was the most explored computer vision task. The sample sizes used ranged from 95 to 38,437, while the augmented training set ranged from 300 to 315,786. Convolutional neural network was the most commonly used model. The mean completeness of CLAIM items was 49% (SD ± 34%). The applicability of the CLAIM checklist items revealed several weaknesses in the methodology of the selected studies: most of the studies were monocentric, and only 9% of them used an external test set when evaluating the model's performance. The QUADAS-AI tool revealed that only 43% of the studies included in this systematic review were at low risk of bias concerning the standard reference domain. CONCLUSION: This review demonstrates that the overall scientific quality of studies conducted to feed artificial intelligence algorithms is low. Some improvement in the design and validation of studies can be made with the development of a standardized guideline for the reproducibility and generalizability of results and, thus, their clinical applications.

Tooth numbering with polygonal segmentation on periapical radiographs: an artificial intelligence study.

OBJECTIVES: Accurately identification and tooth numbering on radiographs is essential for any clinicians. The aim of the present study was to validate the hypothesis that Yolov5, a type of artificial intelligence model, can be trained to detect and number teeth in periapical radiographs. MATERIALS AND METHODS: Six thousand four hundred forty six anonymized periapical radiographs without motion-related artifacts were randomly selected from the database. All periapical radiographs in which all boundaries of any tooth could be distinguished were included in the study. The radiographic images used were randomly divided into three groups: 80% training, 10% validation, and 10% testing. The confusion matrix was used to examine model success. RESULTS: During the test phase, 2578 labelings were performed on 644 periapical radiographs. The number of true positive was 2434 (94.4%), false positive was 115 (4.4%), and false negative was 29 (1.2%). The recall, precision, and F1 scores were 0.9882, 0.9548, and 0.9712, respectively. Moreover, the model yielded an area under curve (AUC) of 0.603 on the receiver operating characteristic curve (ROC). CONCLUSIONS: This study showed us that YOLOv5 is nearly perfect for numbering teeth on periapical radiography. Although high success rates were achieved as a result of the study, it should not be forgotten that artificial intelligence currently only can be guides dentists for accurate and rapid diagnosis. CLINICAL RELEVANCE: It is thought that dentists can accelerate the radiographic examination time and inexperienced dentists can reduce the error rate by using YOLOv5. Additionally, YOLOv5 can also be used in the education of dentistry students.

Machine learning and deep learning models for the diagnosis of apical periodontitis: a scoping review.

OBJECTIVES: To assess the existing literature on the use of machine learning (ML) and deep learning (DL) models for diagnosing apical periodontitis (AP) in humans. MATERIALS AND METHODS: A scoping review was conducted following the Arksey and O'Malley framework. The PubMed, SCOPUS, and Web of Science databases were searched, focusing on articles using ML/DL approaches for AP diagnosis. No restrictions were applied. Two independent reviewers screened publications and charted data in predefined Excel tables for analysis. RESULTS: Nineteen publications focused on diagnosing AP by identifying periapical radiolucent lesions (PRLs) in dental radiographs were included. The average sensitivity and specificity for reviewed models were 83% and 90%, respectively. Only three studies explored the direct impact of artificial intelligence (AI) assistance on clinicians' diagnostic performance. Both consistently showed improved sensitivity without compromising specificity. Significant variability in dataset sizes, labeling techniques, and algorithm configurations was noticed. CONCLUSIONS: Findings affirm AI models' effectiveness and transformative potential in diagnosing AP by improving the accurate detection of periapical radiolucencies using dental radiographs. However, the lack of standardized reporting on crucial aspects of methodology and performance metrics prevents establishing a definitive diagnostic approach using AI. Further studies are needed to expand AI applications in AP diagnosis beyond radiographic analysis. CLINICAL RELEVANCE: AI can potentially improve diagnostic accuracy in AP diagnosis by enhancing the sensitivity of PRL detection in dental radiographs without compromising specificity.

Development of a correction coefficient for radiographic evaluation of the alveolar bone crest: a pilot study.

OBJECTIVES: To analyze the differences in cusp height on radiographs, establishing proportional relationships between cusp and alveolar bone crest (ABC) measurements. The goal of this study was to develop a correction coefficient by considering this proportion. MATERIALS AND METHODS: Twenty-one artificial teeth, molars and premolars, and bovine ribs were used. Interproximal radiographs were taken with the aid of a positioner. The vertical angles used were: 0°, + 5°, and + 10°, and processed using three spatial resolutions measured in line pairs per mm (lp/mm): 20, 25 and 40. The Perio filter was applied to each image, in addition to the original one. Combinations of angle, resolution, and filter were made. Eighteen images were analyzed by three specialists, resulting in 252 measurements for each evaluator, totaling 756 measurements. RESULTS: The overall variability of the measurements can be explained mainly by the variation in tooth anatomy. The 0° 25 lp/mm Perio filter method was the closest one to the actual clinical scenario for both cusps and ABC. The correction factor managed to explain 71.45% of the errors. CONCLUSIONS: The variation in vertical angulation interferes with cusp and ABC measurements, and the angulation at 0º and spatial resolution of 25 lp/mm showed better results. The use of correction coefficients allowed approaching actual measurement values. CLINICAL RELEVANCE: More accurate ABC height measurements are essential even in radiographic exams that do not meet the standard of excellence because the need to repeat radiographic exams is then eliminated.

Radiation exposure during orthodontic treatment: risk to children and adolescents.

OBJECTIVES: To estimate radiation risk to children and adolescents during orthodontic treatment by retrieving number and type of radiographs from the patient records. MATERIAL AND METHODS: Radiographs, along with justifications for radiation exposure, were obtained retrospectively from the patient records of 1,790 children and adolescents referred to two Swedish orthodontic clinics. Data were grouped according to treatment stage: treatment planning, treatment, and follow-up. Estimated risk was calculated using the concept of effective dose. RESULTS: Each patient had received around seven radiographs for orthodontic purposes. The most common exposures during treatment planning were one panoramic, one lateral, and three intraoral periapical radiographs. A small number of patients received a tomographic examination (8.2%). Few justifications for treatment planning and follow-up, but more in the actual treatment stage, had been recorded. The most common examinations were to assess root resorption and the positions of unerupted teeth, or simply carry out an unspecified control. The estimated risk of developing fatal cancer was considered low. The radiation risk from orthodontic treatment was equivalent to about 5-10 days of natural background radiation. CONCLUSIONS: Children and adolescents sometimes undergo multiple radiographic examinations, but despite the low radiation burden, accumulated radiation exposure should be considered and justified in young patients.

Efficacy of a radiographic film holder adapter in generating radiographs of dental implants with improved geometric accuracy and sharpness.

STATEMENT OF PROBLEM: Some radiographic film holders produce radiographs with geometric distortion that may interfere with diagnosis. However, whether the distortion can be corrected by adjusting the design of the radiographic film holder is unclear. PURPOSE: The purpose of the study was to develop an adapter for a radiographic film holder model aiming to generate radiographs with greater sharpness and a more accurate geometric representation of dental implants. MATERIAL AND METHODS: The 2-piece adapter was designed using the SketchUp software program and was 3-dimensionally (3D) printed. Implants with internal conical connections were installed in 19 maxillary prototypes in the central incisor region. Five dentists obtained 285 digital periapical radiographs with 3 different radiographic film holders: standard Cone Indicator, Rinn XCP, and adapted Cone Indicator. They then evaluated the radiographic sharpness of the implants threads and their dimensions using the ImageJ software program. The data were analyzed using the Friedman test with the Durbin-Conover post hoc test and MANOVA with the Tukey post hoc test (α=.05). RESULTS: On the mesial surface of the implants, the threads were sharper for the adapted than for the standard Cone Indicator radiographic film holder (P<.05). The adapted Cone Indicator showed a smaller difference between the radiographic and actual implant diameters compared with the Rinn XCP and standard Cone Indicator radiographic film holders (P<.05). CONCLUSIONS: The developed adapter provided radiographs of dental implants with improved sharpness and geometric accuracy.

How well do large language model-based chatbots perform in oral and maxillofacial radiology?

OBJECTIVES: This study evaluated the performance of four large language model (LLM)-based chatbots by comparing their test results with those of dental students on an oral and maxillofacial radiology examination. METHODS: ChatGPT, ChatGPT Plus, Bard, and Bing Chat were tested on 52 questions from regular dental college examinations. These questions were categorized into three educational content areas: basic knowledge, imaging and equipment, and image interpretation. They were also classified as multiple-choice questions (MCQs) and short-answer questions (SAQs). The accuracy rates of the chatbots were compared with the performance of students, and further analysis was conducted based on the educational content and question type. RESULTS: The students' overall accuracy rate was 81.2%, while that of the chatbots varied: 50.0% for ChatGPT, 65.4% for ChatGPT Plus, 50.0% for Bard, and 63.5% for Bing Chat. ChatGPT Plus achieved a higher accuracy rate for basic knowledge than the students (93.8% vs. 78.7%). However, all chatbots performed poorly in image interpretation, with accuracy rates below 35.0%. All chatbots scored less than 60.0% on MCQs, but performed better on SAQs. CONCLUSIONS: The performance of chatbots in oral and maxillofacial radiology was unsatisfactory. Further training using specific, relevant data derived solely from reliable sources is required. Additionally, the validity of these chatbots' responses must be meticulously verified.

Note on testing of radiological events in conventional and dental radiology.

Since 2013, the adoption of Directive 2013/59/EURATOM in the European Union has mandated emergency plans for facilities housing radiology equipment, including radiology and dental clinics, and required periodical testing of these plans. However, the testing procedures have sparked widespread confusion regarding the definition of radiological emergencies in clinical settings. A potential solution lies in broadening the scope to include 'radiological events', covering accidents, incidents or other type of unjustified exposures. Utilizing realistic scenarios can enhance the radiological protection system within institutions, specifically addressing situations that might lead to unwanted patient exposure.

Deep learning for determining the difficulty of endodontic treatment: a pilot study.

BACKGROUND: To develop and validate a deep learning model for automated assessment of endodontic case difficulty from periapical radiographs. METHODS: A dataset of 1,386 periapical radiographs was compiled from two clinical sites. Two dentists and two endodontists annotated the radiographs for difficulty using the "simple assessment" criteria from the American Association of Endodontists' case difficulty assessment form in the Endocase application. A classification task labeled cases as "easy" or "hard", while regression predicted overall difficulty scores. Convolutional neural networks (i.e. VGG16, ResNet18, ResNet50, ResNext50, and Inception v2) were used, with a baseline model trained via transfer learning from ImageNet weights. Other models was pre-trained using self-supervised contrastive learning (i.e. BYOL, SimCLR, MoCo, and DINO) on 20,295 unlabeled dental radiographs to learn representation without manual labels. Both models were evaluated using 10-fold cross-validation, with performance compared to seven human examiners (three general dentists and four endodontists) on a hold-out test set. RESULTS: The baseline VGG16 model attained 87.62% accuracy in classifying difficulty. Self-supervised pretraining did not improve performance. Regression predicted scores with ± 3.21 score error. All models outperformed human raters, with poor inter-examiner reliability. CONCLUSION: This pilot study demonstrated the feasibility of automated endodontic difficulty assessment via deep learning models.

Efficacy of electronic apex locators in comparison with intraoral radiographs in working length determination- a systematic review and meta-analysis.

BACKGROUND: Successful endodontic treatment needs accurate determination of working length (WL). Electronic apex locators (EALs) were presented as an alternative to radiographic methods; and since then, they have evolved and gained popularity in the determination of WL. However, there is insufficient evidence on the post-operative pain, adequacy, and accuracy of EALs in determining WL. OBJECTIVE: The systematic review and meta-analysis aims to gather evidence regarding the effectiveness of EALs for WL determination when compared to different imaging techniques along with postoperative pain associated with WL determination, the number of radiographs taken during the procedure, the time taken, and the adverse effects. METHODS: For the review, clinical studies with cross-over and parallel-arm randomized controlled trials (RCTs) were searched in seven electronic databases, followed by cross-referencing of the selected studies and related research synthesis. Risk of bias (RoB) assessment was carried out with Cochrane's RoB tool and a random-effects model was used. The meta-analysis was performed with the RevMan software 5.4.1. RESULTS: Eleven eligible RCTs were incorporated into the review and eight RCTs into the meta-analysis, of which five had high RoB and the remaining six had unclear RoB. Following meta-analysis, no significant difference in postoperative pain was found among the EAL and radiograph groups (SMD 0.00, CI .29 to .28, 354 participants; P value = 0.98). Radiograph group showed better WL accuracy (SMD 0.55, CI .11 to .99, 254 participants; P value = 0.02), while the EAL group had 10% better WL adequacy (RR 1.10, CI 1.03-1.18, 573 participants; P value = 0.006). CONCLUSION: We found very low-certainty evidence to support the efficacy of different types of EAL compared to radiography for the outcomes tested. We were unable to reach any conclusions about the superiority of any type of EAL. Well-planned RCTs need to be conducted by standardizing the outcomes and outcome measurement methods.

Enhancement of early proximal caries annotations in radiographs: introducing the Diagnostic Insights for Radiographic Early-caries with micro-CT (ACTA-DIRECT) dataset.

BACKGROUND: Proximal caries datasets for training artificial intelligence (AI) algorithms commonly include clinician-annotated radiographs. These conventional annotations are susceptible to observer variability, and early caries may be missed. Micro-computed tomography (CT), while not feasible in clinical applications, offers a more accurate imaging modality to support the creation of a reference-standard dataset for caries annotations. Herein, we present the Academic Center for Dentistry Amsterdam-Diagnostic Insights for Radiographic Early-caries with micro-CT (ACTA-DIRECT) dataset, which is the first dataset pairing dental radiographs and micro-CT scans to enable higher-quality annotations. METHODS: The ACTA-DIRECT dataset encompasses 179 paired micro-CT scans and radiographs of early proximal carious teeth, along with three types of annotations: conventional annotations on radiographs, micro-CT-assisted annotations on radiographs, and micro-CT annotations (reference standard). Three dentists independently annotated proximal caries on radiographs, both with and without micro-CT assistance, enabling determinations of interobserver agreement and diagnostic accuracy. To establish a reference standard, one dental radiologist annotated all caries on the related micro-CT scans. RESULTS: Micro-CT support improved interobserver agreement (Cohen's Kappa), averaging 0.64 (95% confidence interval [CI]: 0.59-0.68) versus 0.46 (95% CI: 0.44-0.48) in its absence. Likewise, average sensitivity and specificity increased from 42% (95% CI: 34-51%) to 63% (95% CI: 54-71%) and from 92% (95% CI: 88-95%) to 95% (95% CI: 92-97%), respectively. CONCLUSION: The ACTA-DIRECT dataset offers high-quality images and annotations to support AI-based early caries diagnostics for training and validation. This study underscores the benefits of incorporating micro-CT scans in lesion assessments, providing enhanced precision and reliability.

Artificial intelligence for radiographic imaging detection of caries lesions: a systematic review.

BACKGROUND: The aim of this systematic review is to evaluate the diagnostic performance of Artificial Intelligence (AI) models designed for the detection of caries lesion (CL). MATERIALS AND METHODS: An electronic literature search was conducted on PubMed, Web of Science, SCOPUS, LILACS and Embase databases for retrospective, prospective and cross-sectional studies published until January 2023, using the following keywords: artificial intelligence (AI), machine learning (ML), deep learning (DL), artificial neural networks (ANN), convolutional neural networks (CNN), deep convolutional neural networks (DCNN), radiology, detection, diagnosis and dental caries (DC). The quality assessment was performed using the guidelines of QUADAS-2. RESULTS: Twenty articles that met the selection criteria were evaluated. Five studies were performed on periapical radiographs, nine on bitewings, and six on orthopantomography. The number of imaging examinations included ranged from 15 to 2900. Four studies investigated ANN models, fifteen CNN models, and two DCNN models. Twelve were retrospective studies, six cross-sectional and two prospective. The following diagnostic performance was achieved in detecting CL: sensitivity from 0.44 to 0.86, specificity from 0.85 to 0.98, precision from 0.50 to 0.94, PPV (Positive Predictive Value) 0.86, NPV (Negative Predictive Value) 0.95, accuracy from 0.73 to 0.98, area under the curve (AUC) from 0.84 to 0.98, intersection over union of 0.3-0.4 and 0.78, Dice coefficient 0.66 and 0.88, F1-score from 0.64 to 0.92. According to the QUADAS-2 evaluation, most studies exhibited a low risk of bias. CONCLUSION: AI-based models have demonstrated good diagnostic performance, potentially being an important aid in CL detection. Some limitations of these studies are related to the size and heterogeneity of the datasets. Future studies need to rely on comparable, large, and clinically meaningful datasets. PROTOCOL: PROSPERO identifier: CRD42023470708.

Technical Quality of Root Fillings Performed by Undergraduate Dental Students in Single-Canal Teeth: A 10-Year Retrospective Study.

OBJECTIVE: This study assessed the radiographic technical quality of root fillings in single-canal teeth performed over a decade (June 2013 to June 2023) by undergraduate dental students of the Federal University of Campina Grande. METHODS: All teeth underwent chemomechanical preparation using Gates-Glidden drills and hand instrumentation with stainless steel files up to 1 mm short of the root apex. Apical expansion was performed with up to two or three instruments above the initial anatomical apical diameter. The canal was filled in the absence of signs and symptoms of infection using gutta-percha cones and Sealer 26 or MTA Fillapex. A post-filling radiograph was routinely taken to assess the quality of root filling and coronal restoration. An experienced researcher trained and calibrated an examiner to evaluate post-operative periapical radiographs considering root-filling length, lateral adaptation and taper using ImageJ 1.52q software. Root filling was satisfactory when reaching acceptable classifications for the three parameters. The chi-squared test compared tooth type, dental arch and pulpal diagnosis at a 5% significance level. RESULTS: The study assessed 124 canals, showing 90 (72.6%) satisfactory root fillings. The sub-analysis of individual parameters demonstrated that 105 (84.7%) root fillings had acceptable length, 113 (91.1%) adapted well to lateral canal walls, and 109 (87.9%) had proper taper. Most cases occurred in maxillary teeth (n = 99), pulp necrosis was the most frequent pulpal diagnosis (n = 89), and root-filling quality showed no association with tooth type, dental arch or pulpal diagnosis. CONCLUSION: The technical quality of root fillings in single-canal teeth treated by dental students was predominantly satisfactory.

Radiographical diagnostic competences of dental students using various feedback methods and integrating an artificial intelligence application-A randomized clinical trial.

INTRODUCTION: Radiographic diagnostic competences are a primary focus of dental education. This study assessed two feedback methods to enhance learning outcomes and explored the feasibility of artificial intelligence (AI) to support education. MATERIALS AND METHODS: Fourth-year dental students had access to 16 virtual radiological example cases for 8 weeks. They were randomly assigned to either elaborated feedback (eF) or knowledge of results feedback (KOR) based on expert consensus. Students´ diagnostic competences were tested on bitewing/periapical radiographs for detection of caries, apical periodontitis, accuracy for all radiological findings and image quality. We additionally assessed the accuracy of an AI system (dentalXrai Pro 3.0), where applicable. Data were analysed descriptively and using ROC analysis (accuracy, sensitivity, specificity, AUC). Groups were compared with Welch's t-test. RESULTS: Among 55 students, the eF group by large performed significantly better than the KOR group in detecting enamel caries (accuracy 0.840 ± 0.041, p = .196; sensitivity 0.638 ± 0.204, p = .037; specificity 0.859 ± 0.050, p = .410; ROC AUC 0.748 ± 0.094, p = .020), apical periodontitis (accuracy 0.813 ± 0.095, p = .011; sensitivity 0.476 ± 0.230, p = .003; specificity 0.914 ± 0.108, p = .292; ROC AUC 0.695 ± 0.123, p = .001) and in assessing the image quality of periapical images (p = .031). No significant differences were observed for the other outcomes. The AI showed almost perfect diagnostic performance (enamel caries: accuracy 0.964, sensitivity 0.857, specificity 0.074; dentin caries: accuracy 0.988, sensitivity 0.941, specificity 1.0; overall: accuracy 0.976, sensitivity 0.958, specificity 0.983). CONCLUSION: Elaborated feedback can improve student's radiographic diagnostic competences, particularly in detecting enamel caries and apical periodontitis. Using an AI may constitute an alternative to expert labelling of radiographs.

An Artificial Intelligence model for implant segmentation on periapical radiographs.

OBJECTIVE: To segment dental implants on PA radiographs using a Deep Learning (DL) algorithm. To compare the performance of the algorithm relative to ground truth determined by the human annotator. Methodology: Three hundred PA radiographs were retrieved from the radiographic database and consequently annotated to label implants as well as teeth on the LabelMe annotation software. The dataset was augmented to increase the number of images in the training data and a total of 1294 images were used to train, validate and test the DL algorithm. An untrained U-net was downloaded and trained on the annotated dataset to allow detection of implants using polygons on PA radiographs. RESULTS: A total of one hundred and thirty unseen images were run through the trained U-net to determine its ability to segment implants on PA radiographs. The performance metrics are as follows: accuracy of 93.8%, precision of 90%, recall of 83%, F-1 score of 86%, Intersection over Union of 86.4% and loss = 21%. CONCLUSIONS: The trained DL algorithm segmented implants on PA radiographs with high performance similar to that of the humans who labelled the images forming the ground truth.

Severe radiographic artifact created by a large fenestration of the skin and labial mucosa following placement of a plate piercing: a case report.

The presence of facial jewelry and medical devices within a radiographic field of view may promote the formation of artifacts that challenge diagnostic interpretation. The objective of this article is to describe a previously unreported radiographic anomaly produced by an oral piercing site below the lower lip. This unusual artifact masqueraded as a severe resorptive defect, dental caries, or cervical abfraction and occurred following removal of an extremely large labret below the lower lip and subsequent acquisition of a radiographic image. The radiolucency was ultimately attributed to an extensive aperture below the lower lip created by a series of sequentially larger soft tissue expanders. Clinicians should seek correlation of atypical radiographic presentations with soft tissue defects secondary to injury or intentional oral piercing.

An application of the density standard and scaled-pixel-counting protocol to assess the radiodensity of equine incisor teeth affected by resorption and hypercementosis: preliminary advancement in dental radiography.

BACKGROUND: Equine Odontoclastic Tooth Resorption and Hypercementosis (EOTRH) syndrome is a dental disease where the radiographic signs may be quantified using radiographic texture features. This study aimed to implement the scaled-pixel-counting protocol to quantify and compare the image structure of teeth and the density standard in order to improve the identification of the radiographic signs of tooth resorption and hypercementosis using the EOTRH syndrome model. METHODS AND RESULTS: A detailed examination of the oral cavity was performed in 80 horses and maxillary incisor teeth were evaluated radiographically, including an assessment of the density standard. On each of the radiographs, pixel brightness (PB) was extracted for each of the ten steps of the density standard (S1-S10). Then, each evaluated incisor tooth was assigned to one of 0-3 EOTRH grade-related groups and annotated using region of interest (ROI). For each ROI, the number of pixels (NP) from each range was calculated. The linear relation between an original X-ray beam attenuation and PB was confirmed for the density standard. The NP values increased with the number of steps of the density standard as well as with EOTRH degrees. Similar accuracy of the EOTRH grade differentiation was noted for data pairs EOTRH 0-3 and EOTRH 0-1, allowing for the differentiation of both late and early radiographic signs of EOTRH. CONCLUSION: The scaled-pixel-counting protocol based on the use of density standard has been successfully implemented for the differentiation of radiographic signs of EOTRH degrees.