Bitewing Radiographs Research Articles

Detection of pulpal calcifications on bite-wing radiographs using deep learning.

Pulpal calcifications are discrete hard calcified masses of varying sizes in the dental pulp cavity. This study is aimed at measuring the performance of the YOLOv4 deep learning algorithm to automatically determine whether there is calcification in the pulp chambers in bite-wing radiographs. In this study, 2000 bite-wing radiographs were collected from the faculty database. The oral radiologists labeled the pulp chambers on the radiographs as "Present" and "Absent" according to whether there was calcification. The data were randomly divided into 80% training, 10% validation, and 10% testing. The weight file for pulpal calcification was obtained by training the YOLOv4 algorithm with the transfer learning method. Using the weights obtained, pulp chambers and calcifications were automatically detected on the test radiographs that the algorithm had never seen. Two oral radiologists evaluated the test results, and performance criteria were calculated. The results obtained on the test data were evaluated in two stages: detection of pulp chambers and detection of pulpal calcification. The detection performance of pulp chambers was as follows: recall 86.98%, precision 98.94%, F1-score 91.60%, and accuracy 86.18%. Pulpal calcification "Absent" and "Present" detection performance was as follows: recall 86.39%, precision 85.23%, specificity 97.94%, F1-score 85.49%, and accuracy 96.54%. The YOLOv4 algorithm trained with bite-wing radiographs detected pulp chambers and calcification with high success rates. Automatic detection of pulpal calcifications with deep learning will be used in clinical practice as a decision support system with high accuracy rates in diagnosing dentists.

Radiographic and clinical signs of periodontitis and associated bacterial species in a Swedish adolescent population.

Periodontitis in adolescents has historically been rare in the Nordic countries but could be expected to increase due to changing demographics. The primary aim was to cross-sectionally examine the presence of radiographic bone loss in adolescents in Västerbotten County, Sweden. The secondary aim was to compare periodontal and microbial parameters, as well as demographic patterns, between controls without bone loss and cases with bone loss. Adolescents born in 2001 who had a dental examination in 2016 (n= 1656) were screened for proximal bone loss using bitewing radiographs taken during dental examinations (2014-2016). Individuals exhibiting proximal bone loss (>2 mm) were invited to participate in a complete periodontal examination. Subgingival plaque and saliva were also sampled. For each adolescent with bone loss, two healthy individuals as controls were examined. Selected bacterial species in saliva and subgingival plaque were examined by quantitative PCR. The subgingival plaque samples were also analyzed via cultivation technique. Proximal bone loss was identified in 24 individuals (1.45%) based on the radiographs. Thirteen of these cases were periodontally examined and matched with 26 controls. Most cases were diagnosed with periodontitis (12/13 [92%]), whereas none of the controls had periodontitis. Higher concentrations and higher prevalence of the bacteria Aggregatibacter actinomycetemcomitans, Porphyromonas gingivalis, and Filifactor alocis were generally found in the cases. The results suggest that periodontitis is increasing among adolescents in Sweden because of demographic differences (an increasingly heterogenous population), and emphasize the importance of radiographs for early detection of this disease.

Alveolar Bone Loss in Diabetic Patients: A Case-Control Study.

Based on literature, very few case-control studies have been executed to confirm the relationship between diabetes mellitus and the severity of mean alveolar bone loss. Therefore, the aim was to assess the differences in mean alveolar bone loss among diabetic (type 2) and nondiabetic patients in the Saudi population. Nine-hundred eighty-two patient records were seen in this retrospective study. Patient demographic data and medical records were examined. The mean alveolar bone loss was measured in posterior teeth by calculating the distance from the base of cementoenamel junction to the alveolar crest using the bitewing radiographs. SPSS 20.0 was used for data analysis. An unpaired t-test was utilized to analyze the mean alveolar bone loss across multiple variables. p-Value less than or equal to 0.05 was contemplated as significant. The overall mean alveolar bone loss for all 124 patients was 2.83 ± 1.13 mm. Diabetic patients had greater mean alveolar bone loss measured in millimeters than nondiabetic patients (3.07 ± 1.14mm vs. 2.59 ± 1.08mm, respectively), and the difference was significant (p = 0.018). In terms of the severity of mean alveolar bone loss, diabetic patients experience statistically higher mean alveolar bone loss as compared with nondiabetic patients. In our study population, the overall mean alveolar bone loss prevalence was greater in diabetes patients than in nondiabetic individuals. According to the severity of bone loss, the distribution of moderate and severe periodontitis was higher in diabetic patients. To enhance patients' quality of life, the awareness and education among patients regarding the association among diabetes mellitus and oral health, particularly periodontal disease, should be promoted.

Study Regarding the Optimal Dimension of Intraoral Bitewing Radiographs in Patients with Primary Dentition.

The aim of this study was to determine the optimum dimensions of a radiographic plate to allow correct visualization of dental tissues and correct fit in the oral cavity of children with deciduous dentition. A quasi-experimental clinical study was carried out in children of both sexes aged between 3 and 5 years. The study variables were the complete visualization of the dental structures, the surveillance of ischemia on soft tissues, stimulation of the gag reflex, and acceptance of the radiographic plate by the pediatric patient through a validated visual analogue scale that measures anxiety. The data obtained were subjected to a descriptive and comparative statistical analysis carried out for both study phases. A total of 80 children participated in the study. The optimal dimensions obtained for the radiographic plate were 19.5 mm in height and 27.3 mm in width. Visualization of the dental tissues during both phases was not statistically significant (p = 0.412). However, there were statistically significant differences regarding the presence of ischemia, gag reflex, and child rejection (p < 0.001). A smaller radiographic plate allows correct visualization of the coronal dental tissues without causing rejection, ischemia, or gag reflex in patients in the deciduous dentition.

Dental Students' Ability to Detect Only-Enamel Proximal Caries on Bitewing Radiographs.

Introduction The dental students are trained to identify the proximal carious lesion using clinical tools and radiography over three years of academic curriculum. During these years the students are expected to learn detection of incipient carious lesions and take appropriate preventive/restorative measure. Method This study aimed at evaluating the ability of the students and interns to detect only-enamel proximal caries on the five digital bitewing radiographs. The digital bitewing radiographs were having incipient carious lesions involving enamel on proximal surface of mandibular first molars. Results A total of 101 participants (M = 29, F = 72) from fifth (D5) and sixth (D6) years of dentistry evaluated the radiographs and the KR20 values for D5, D6, and total sample were 0.79, 0.64, and 0.41 respectively. Conclusion Overall students' assessment of detection of incipient carious lesion was low. There is need to enhance clinical and radiological cognitive skills among students with emphasis on interdisciplinary learning objectives.

Do preterm-born children and adolescents have greater need for dental care as compared to full term-born controls?

BackgroundPreterm birth has been shown to cause various long-term health issues. Children who were born preterm have also been observed to have more dental behaviour management problems (DBMP) during dental examinations and treatment than children born full term. It is known that dental radiographic examinations can be uncomfortable and cause anxiety in paediatric patients. Thus, our aims were to retrospectively compare dental care related examinations and treatments carried out in three different age intervals (3–6 years, 7–12 years, and 13–19 years) among preterm- and full-term born children and adolescents.MethodsThe present study included 311 patient files: 122 very preterm–born and 33 extremely preterm–born children and adolescents (< 32 gestational weeks). A matched control group of 156 full term–born children and adolescents (≥ 37 gestational weeks) was analysed for comparison. Various factors, including DBMP, missed appointments, dental caries, and radiographic examinations, were retrieved from the dental records for three age intervals: 3–6 years, 7–12 years, and 13–19 years.ResultsExtremely preterm–born children missed significantly more dental appointments and presented with more DBMP during dental examinations and treatment than full term–born children in the 3–6-year age group; the same was observed for the very preterm–born in the 7–12-year age group. No significant differences in DBMP during bitewing and periapical examinations or in number of bitewing, periapical and panoramic radiographs occurred between the groups in any age interval.ConclusionPreterm–born children and adolescents may need more flexibility in booking and receive reminders for scheduled visits with the general dental team. Due to the non-significant differences in dental care related oral examinations and treatments, the same dental care service may be applied to the preterm- and full-term born children and adolescents.

Diagnosis of Interproximal Caries Lesions in Bitewing Radiographs Using a Deep Convolutional Neural Network-Based Software

The aim of this study was to evaluate the diagnostic reliability of a web-based artificial intelligence program for the detection of interproximal caries in bitewing radiographs. Three hundred bitewing radiographs of patients were subjected to the evaluation of a convolutional neural network. First, the images were visually evaluated by a previously trained and calibrated operator with radiodiagnosis experience. Then, ground truth was established and was clinically validated. For enamel caries, clinical assessment included a combination of clinical-visual and radiography evaluations. For dentin caries, clinical validation was performed by instrumentally accessing the cavity. Second, the images were uploaded and analyzed by the web-based software. Four different models were established to analyze its evaluations according to the confidence threshold (0–100%) offered by the program: model 1 (values >0% were considered positive and values of 0% were considered negative), model 2 (values ≥25% were considered positive and values <25% were considered negative), model 3 (values ≥50% were considered positive and values <50% were considered negative), and model 4 (values ≥75% were considered positive and values <75% were considered negative). The accuracy rate (A), sensitivity (S), specificity (E), positive predictive value (PPV), negative predictive value (NPV), positive likelihood ratio (PLR), negative likelihood ratio (NLR), and areas under receiver operating characteristic curves (AUC) were calculated for the four models of agreement with the software. Models showed the following results respectively: A = 70.8%, 82%, 85.6%, 86.1%; S = 87%, 69.8%, 57%, 41.6%; E = 66.3%, 85.4%, 93.7%, 98.5%; PPV = 42%, 57.2%, 71.6%, 88.6%; NPV = 94.8%, 91%, 88.6%, 85.8%; PLR = 2.58, 4.78, 9.05, 27.73; NLR = 0.2, 0.35, 0.46, 0.59; AUC = 0.767, 0.777, 0.753, 0.701. Findings in the present study suggest that the artificial intelligence web-based software provides a good diagnostic reliability on the detection of dental caries. Our study highlighted model 2 for showing the best results to differentiate between healthy teeth and decayed teeth.

Detection of Proximal Caries Lesions on Bitewing Radiographs Using Deep Learning Method

This study aimed to evaluate the validity of a deep learning-based convolutional neural network (CNN) for detecting proximal caries lesions on bitewing radiographs. A total of 978 bitewing radiographs, 10,899 proximal surfaces, were evaluated by two endodontists and a radiologist, of which 2,719 surfaces were diagnosed and annotated with proximal caries and 8,180 surfaces were sound. The data were randomly divided into two datasets, with 818 bitewings in the training and validation dataset and 160 bitewings in the test dataset. Each annotation in the test set was then classified into 5 stages according to the extent of the lesion (E1, E2, D1, D2, D3). Faster R-CNN, a deep learning-based object detection method, was trained to detect proximal caries in the training and validation dataset and then was assessed on the test dataset. The diagnostic accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and receiver operating characteristic curve were calculated. The performance of the network in the overall and different stages of lesions was compared with that of postgraduate students on the test dataset. A total of 388 carious lesions and 1,435 sound surfaces were correctly identified by the neural network; hence, the accuracy was 0.87. Furthermore, 27.6% of lesions went undetected, and 7% of sound surfaces were misdiagnosed by the neural network. The sensitivity, specificity, PPV, and NPV of the neural network were 0.72, 0.93, 0.77, and 0.91, respectively. In contrast with the network, 52.8% of lesions went undetected by the students, yielding a sensitivity of only 0.47. The F1-score of the students was 0.57, while the F1-score of the network was 0.74 despite the accuracy of 0.82. A significant difference in the sensitivity was found between the model and the postgraduate students when detecting different stages of lesions (p < 0.05). For early lesions which limited in enamel and the outer third of dentin, the neural network had sensitivities all above or at 0.65, while students showed sensitivities below 0.40. From our results, we conclude that the CNN may be an assistant in detecting proximal caries on bitewings.

Evaluation of Diagnostic Efficacy of Improved Interproximal Program and Bitewing Program in Proximal Caries Detection- An Extraoral Radiographic Comparative Study

Background: To look for an alternative to intraoral bitewing radiographs when the intraoral placement of film is not feasible or multiple teeth have to be screened. Objectives: A study to evaluate and compare the efficacy of improved interproximal and bitewing programs for detection of proximal caries Planmeca ProMax was conducted. Materials and Methods: Fifty patients who were screened for proximal caries and confirmed with intraoral bitewing radiography were subjected to improved interproximal program and bitewing program in Planmeca ProMax (Planmeca Oy, Helsinki, Finland) after obtaining informed consent. These radiographs were evaluated by three observers. Intra- and interclass correlation was done to check reliability of the observers, and ROC analysis was done to evaluate the diagnostic accuracy. Critical ratio analysis was done to know the significance. Results: Both improved interproximal program and bitewing programs have similar diagnostic efficacy. ROC curve area of improved interproximal program was 0.833 while bitewing program showed 0.878. Bitewing program showed specificity value of 76% compared to 67% in improved interproximal program while both were equally sensitive. Conclusion: Both bitewing program and improved interproximal program are highly sensitive in detecting proximal caries when compared to intraoral bitewing radiography which is still considered the gold standard in diagnosis of an interproximal caries.

Three-dimensional characterization of naturally developed early caries lesions using high-resolution micro-computed tomography

ObjectivesThe goal of this micro-Computed-Tomography (μCT) study was to characterize the structural parameters of natural, early proximal enamel caries lesions and correlate them with two-dimensional radiographic findings. MethodsExtracted human premolar teeth with ICDAS score 2 proximal lesions were examined using visual-tactile, μCT and simulated bitewing radiographs (BTX). Sound enamel and caries-lesions’ structural and mineral density (MD) parameters were analyzed which included surface layer (SL) status and thickness, depth of lesion, and MD. ResultsThirty-six extracted premolars with 54 proximal early enamel caries lesions were analyzed. Lesions varied notably in lesion depth and MD. SL thickness ranged between 20 and 139μm. Three teeth (5.6%) had micro-cavitations upon the μCT examination despite being “clinically” non-cavitated. Cavitation status had no significant association with μCT nor BTX radiographic depth. Depth of lesions correlated weakly but statistically significantly with mineral loss (ML) at body of lesion (r=0.301, p=0.027). SL thickness also correlated negatively with ML at SL (r=-0.501, p<0.001). ConclusionsEarly proximal enamel lesions with ICDAS 2 score as determined by visual-tactile examination exhibited a wide range of lesion parameters and cavitation status when examined by μCT. Visual-tactile examination may fail to detect micro-cavitations in enamel surface that are detectable by μCT. Clinical SignificanceClinicians have direct access to early proximal enamel lesions during orthodontic separation, exfoliation, extraction or restoration of adjacent teeth. This study invites the clinician to consider more decisive management options in high risk individuals (e.g. micro-invasive techniques), given the finding of vast structural variability of such lesions.

Effectiveness of Machine Learning in Assessing the Diagnostic Quality of Bitewing Radiographs

Background: Identifying the diagnostic value of bitewing radiographs (BW) is highly dependent on the operator’s knowledge and experience. The aim of this study is to assess the effectiveness of machine learning (ML) to classify the BW according to their diagnostic quality. Methods: 864 BW radiographs from records of 100 patients presented at King Abdulaziz University Dental Hospital, Jeddah, Saudi Arabia were assessed. The radiographic errors in representing proximal contact areas (n = 1951) were categorized into diagnostic and non-diagnostic. Labeling and training of the BW were done using Roboflow. Data were divided into validation, training, and testing sets to train the pre-trained model Efficientdet-d0 using TensorFlow. The model’s performance was assessed by calculating recall, precision, F1 score, and log loss value. Results: The model excelled at detecting “overlap within enamel” and “overlap within restoration (clear margins) with F1 score of 0.89 and 0.76, respectively. The overall system errors made by the built model showed a log loss value of 0.15 indicating high accuracy of the model. Conclusions: The model is a “proof of concept” for the effectiveness of ML in diagnosing the quality of the BW radiographs based on the contact areas. More dataset specification and optimization are needed to overcome the class imbalance.

Artificial intelligence based on Convolutional Neural Network for detecting dental caries on bitewing and periapical radiographs

Objectives: This narrative review is written to describe the accuracy of caries detection and find out the clinical implications and future prospects of using Convolutional Neural Network (CNN) to determine radio-diagnosis of dental caries in bitewing and periapical radiographs.&#x0D; Review: The databases used for literature searching in this narrative review were PubMed, Google Scholar, and Science Direct. The inclusion criteria were original article, case report, and textbook written in English and Bahasa Indonesia, published within 2011-2021. The exclusion criteria were articles that the full text could not be accessed, research article that did not provide the methods used, and duplication articles. In this narrative review, a total of 33 literatures consisting of 30 articles and three textbooks reviewed, including four original articles on CNN for caries detection.&#x0D; Conclusion: Results of the review reveal that GoogLeNet produces the best detection compared to Fully Convolutional Network (FCN) and U-Net for caries detection in bitewing and periapical radiographs. Nonetheless, the positive predictive value (PPV), recall, negative predictive value (NPV), specificity, F1-score, and accuracy values in these architectures indicate good performance. The differences of each CNN’s performances to detect caries are determined by the number of trained datasets, the architecture’s layers, and the complexity of the CNN architectures. The conclusion of this review is CNN can be used as an alternative to detect caries, increasing the diagnostic accuracy and time efficiency as well as preventing errors due to dentist fatigue. Yet the CNN is not able to substitute the expertise of a radiologist. Therefore, it is need to be revalidated by the radiologist to avoid diagnostic errors.

A comparison of the horizontal and vertical bitewing images in detecting approximal caries and interdental bone loss in posterior teeth: A diagnostic accuracy randomized cross over clinical trial

Background/purposeHorizontal bitewing radiographs are widely and frequently used in dentistry and are very reliable in diagnosing proximal caries and interproximal alveolar bone level. However, it is challengeable in detecting interproximal root caries, horizontal and/or vertical alveolar bone loss, and furcation involvements. The aim of this article was to assess the accuracy of vertical bitewing images in the diagnosis of caries and alveolar bone level compared to the horizontal bitewing technique. Materials and methodsEach one of the 20 patients had eight bitewing radiographs to get four horizontal bitewing (control) and four vertical bitewing (experimental) images for the same posterior area; a steel wire (3 mm) was used on the sensor plate to help measure the magnification later on. The radiographs were processed digitally and were evaluated for caries by two expert restorative specialists and for bone loss by two experienced periodontists. They were also compared to the “gold standard,” which is using of both clinical and radiographic examination for diagnosis. They were blinded to each other during images evaluation. ResultsOf the 20-patient sample size, 70% were male and 30% were female, with a mean age of 29.9. The average number of radiographs taken to achieve four standard bitewing radiographs was 5.9 ± 1.7 for vertical bitewings and 5.3 ± 1.3 for horizontal bitewing radiograph. The measurements from the cementoenamel junction (CEJ) to the level of crestal bone didn't show a significant difference between the horizontal and vertical bitewing radiographs. The detection of furcation area in the molar teeth was much higher in the vertical bitewing (100%) compared to the horizontal bitewing (57.5%) (P < 0.0001). Conclusion: The vertical bitewing radiograph has the upper hand over the horizontal bitewing radiograph in the detection of furcation involvement, caries detection, and alveolar bone loss. Therefore, it is highly recommended to use vertical bitewing in caries and patients with periodontal disease rather than the conventional horizontal bitewing.

Artificial Intelligence for Caries Detection: Value of Data and Information

If increasing practitioners’ diagnostic accuracy, medical artificial intelligence (AI) may lead to better treatment decisions at lower costs, while uncertainty remains around the resulting cost-effectiveness. In the present study, we assessed how enlarging the data set used for training an AI for caries detection on bitewings affects cost-effectiveness and also determined the value of information by reducing the uncertainty around other input parameters (namely, the costs of AI and the population’s caries risk profile). We employed a convolutional neural network and trained it on 10%, 25%, 50%, or 100% of a labeled data set containing 29,011 teeth without and 19,760 teeth with caries lesions stemming from bitewing radiographs. We employed an established health economic modeling and analytical framework to quantify cost-effectiveness and value of information. We adopted a mixed public–private payer perspective in German health care; the health outcome was tooth retention years. A Markov model, allowing to follow posterior teeth over the lifetime of an initially 12-y-old individual, and Monte Carlo microsimulations were employed. With an increasing amount of data used to train the AI sensitivity and specificity increased nonlinearly, increasing the data set from 10% to 25% had the largest impact on accuracy and, consequently, cost-effectiveness. In the base-case scenario, AI was more effective (tooth retention for a mean [2.5%–97.5%] 62.8 [59.2–65.5] y) and less costly (378 [284–499] euros) than dentists without AI (60.4 [55.8–64.4] y; 419 [270–593] euros), with considerable uncertainty. The economic value of reducing the uncertainty around AI’s accuracy or costs was limited, while information on the population’s risk profile was more relevant. When developing dental AI, informed choices about the data set size may be recommended, and research toward individualized application of AI for caries detection seems warranted to optimize cost-effectiveness.

An educational method for learning and assessing interproximal dental caries diagnosis in children's radiographs

<h3>Background</h3> Dental caries is common in children, and intraoral bitewing radiographs are the gold standard for diagnosing interproximal caries. Accurate interpretation of radiographs is a key competency for dentists treating children to minimize the consequences of misdiagnosis. There are currently no validated methods for assessment of this important competency for Canadian dental trainees. <h3>Objective</h3> We developed an interactive computer-assisted learning (CAL) tool designed to permit the deliberate practice of pediatric bitewing radiograph interpretation. The main objective of this study was to measure the amount and rate of skill acquisition in the diagnosis of interproximal dental caries amongst dental trainees, and to determine the effect size of our education intervention. <h3>Study Design</h3> This multi-center prospective cohort study used a convenience sample of Canadian dental trainees ranging in experience from undergraduate dental education to graduate pediatric dentistry. Reference standard caries diagnosis was determined by consensus between three dental specialists. Study participants learned to interpret children's bitewing radiographs on a web-based platform by deliberately practicing 193 cases with the goal of achieving a performance benchmark of 75% accuracy, sensitivity, and specificity. Participants identified the presence/absence of interproximal dental caries, and if present, identified the specific location of all lesions. <h3>Results</h3> To date, 60 participants have completed all 193 cases, and 10 participants have achieved the performance benchmark. There was a significant increase of 17.8% (95% CI 14.6, 21.0) from mean initial to maximal accuracy amongst participants. The median number of cases to achieve competency was 180 (min 84, max 550). The effect size of the education intervention was large, with a Cohen's d=1.6 (95% CI 1.2-2.10). <h3>Conclusion</h3> The learning intervention evaluated in this study has led to effective and feasible skill improvement in the interpretation of interproximal dental caries on bitewing radiographs amongst dental trainees and may be a valuable adjunct to existing educational methods in dental radiology. <b>Statement of Ethical Review</b> Human/Animal subjects were used and this study was approved by an institutional ethics panel

A deep learning approach to automatic detection and profiling of dental caries in bitewing and periapical radiographs

<h3>Objective</h3> Dental caries is the most prevalent noncommunicable disease among humans, but routine misdiagnosis remains an underappreciated challenge. This study aimed to answer the challenge with the latest advances in artificial intelligence (AI), machine/deep learning, and computer vision. This study was conducted by an interdisciplinary team of academic clinicians and a dental AI startup. <h3>Study Design</h3> We curated and methodically annotated an imbalanced database of bitewing and periapical radiographs using a caries ontology derived from the ICDAS framework. Using this dataset, we leveraged machine learning algorithms to train predictive models to perform segmentation and classification of dental caries on novel radiographs. Given the trained model, we designed a comparison study to measure the qualitative and quantitative performance of the trained neural networks vs a set of experts. The objective of the study was to assess the expected effectiveness of model performance, and validate model behavior in direct comparison with humans on the same tasks. The study consisted of 3 dentists interacting with a web-based platform for collecting annotations of de-identified radiographs. Fifteen radiographs were used for the pilot study. <h3>Results</h3> In the human-human comparisons, there was 4% strong disagreement, 48% minor disagreement, and 48% agreement. In the majority of cases (69%), the neural network model was either perfectly correct or close with some nuance. In no case was the model completely incorrect (0%); it either missed one or more caries or produced a false positive (the remaining 31%). In general, it matched or exceeded the expert evaluation of radiographs. <h3>Conclusion</h3> We contend that these results show how neural network-based machine learning models hold considerable promise in providing assistance to dentists. We intend to pursue larger-scale human-machine comparison studies in subsequent efforts. <b>Statement of Ethical Review</b> Ethical review was sought and study was exempted from ethical review

A comparison of doses from contemporary extraoral bitewing radiography: Child and adult examinations

<h3>Objective</h3> To compare the effective doses (E) from two panoramic (PAN)/extraoral bitewing (EOBW) systems with an industry-standard intraoral bitewing (IOBW) system for adult and child phantoms. The feasibility and impact of thyroid shielding during EOBW was also evaluated. <h3>Study Design</h3> This preclinical experimental study utilizing anthropomorphic phantoms (average adult and 10-year-old child) modified to accept optically stimulated luminescence dosimeters evaluated E from two extraoral units: RayScan ALPHA (Buena Park, CA) and Sirona ORTHOPHOS SL (Charlotte, NC), and one conventional IO unit using circular (CC) and rectangular (RC) collimation (FOCUS Instrumentarium, Brea, CA). Phantom sequences were triplicated for all modality combinations and average E was calculated. Exposure parameters were: Orthophos- 85kV, 7-13mA, 5.1s; RayScan- 80kV, 12-14mA, 7.2s; Focus- 70kV, 7mA, 0.5-1.28s. <h3>Results</h3> E from child and adult PAN and EOBW examinations was significantly lower for Orthophos compared to RayScan (p<.0001). Standard adult EOBW E (µSv) was 4.3 and 28.1 (child) and 8.6 and 30.2 (adult) for Orthophos and RayScan, respectively. For both extraoral units, EOBW E was reduced compared to PAN E. IOBW E (µSv) ranged from 7.0-11.8 (child) and 4.6-14.2 (adult) for CC and RC, respectively. IOBW examinations with CC yielded higher E than Orthophos EOBW and lower E than RayScan EOBW for the adult phantom. Significant reductions in thyroid dose (53%) from EOBW examinations were achieved using shielding with RayScan adult scans (p<.0001). Shielding did not yield notable thyroid dose reductions for child EOBW scans and produced minor artifacts intermittently. <h3>Conclusion</h3> IOBW examinations employing RC continue to yield lower E than alternative EOBW systems for adults. Dramatic dose differences may be associated with extraoral equipment selection. Detector type (2D-array vs. flat-panel) may be an indicator of potential dose differences among machines. Shielding during EOBW imaging can reduce adult thyroid dose without negatively affecting image quality. <b>Statement of Ethical Review</b> Ethical review was sought and study was exempted from ethical review

Design of hybrid dental caries segmentation and caries detection with meta-heuristic-based ResneXt-RNN

The early identification of dental caries is necessary for corresponding treatments and the above reason, the bitewing radiography is utilized to offer initial caries detection. In clinical imaging, the usage of deep structured architectures with renowned neural network schemes helps process the vast amount of images, which has been researched actively in recent years and provided competitive performance. Therefore, deep learning approaches have attained remarkable diagnosis efficiency in the domain of radiology. Owing to this emerging intelligence, this paper aims to use the deep learning method for dental caries segmentation in an effective way. At first, contrast enhancement via Contrast Limited Adaptive Histogram Equalization (CLAHE), and noise filtering via bilateral filtering are performed under the pre-processing phase. Further, the segmentation of the caries is performed by the Fused Optimal Centroid K-means with K-Mediods Clustering (FOC-KKC), which will be enhanced by the Hybrid Sea Lion-Squirrel Search Optimization (HSLnSSO), inducing the best parameter optimization. Once the caries are segmented, the post-pre-processing of images is done by morphological operations. Finally, the detection of caries from the segmented image is employed by the meta-heuristic-based ResneXt with Recurrent Neural Network (RNN) (M−ResneXt−RNN), where the architecture modification is performed by the HSLnSSO algorithm. The new segmentation model and well-trained M−ResneXt−RNN for caries detection have exhibited superior performance when compared to the conventional techniques.

Augmented Vision for Dental Students’ Education in Detecting Proximal Carious Lesions on Bitewing Radiographs: A Randomized Controlled Trial

This two-arm, parallel, randomized controlled trial aimed to assess the effect of augmented vision (AV, using interactive color overlays) on the education of dental students in detecting proximal carious lesions on bitewing radiographs compared to black-and-white textbook-like illustrations. Forty-eight preclinical third-year dental students were randomized using a random number generator into two learning groups: test (AV, allowing interaction with color-highlighted carious lesions, n = 24) and control (showing the native radiograph and a black-and-white illustration displaying the carious lesion, n = 24). First, students had 2 weeks to assess 50 bitewings (lesion prevalence on the tooth level: 54.5%) in the test or control. Due to the nature of the intervention, participants could not be blinded toward the intervention. After that, they were asked to detect lesions on 10 independent bitewings and to assess lesion extent (outer/inner enamel; outer/middle/inner dentin). The reference test was constituted by two experienced dentists. No significant differences in accuracy (test 0.84 [95% CI: 0.79, 0.88]; control 0.83 [0.78, 0.87]), AUC (test 0.82 [0.81, 0.84]; control 0.81 [0.80, 0.83]) and F1 score (test 0.79 [0.75, 0.82]; control 0.77 [0.72, 0.81]) were observed between groups. Students of both groups showed difficulties in differentiating enamel from dentin carious lesions. While AV was reported to be motivating by students, it did not increase their accuracy.

Deep carious lesions and their management among Finnish adolescents: a retrospective radiographic study

ObjectiveThe objective of this retrospective study was to find out (i) the prevalence of deep carious lesions, both untreated and previously treated, among 14- and 15-year olds and (ii) how deep carious lesions were managed in a Finnish public health care setting.Materials and methodsA random sample of 278 patients was taken from 3990 patients at the oral health care of the City of Helsinki. Radiographic subsample consisted of patients with bitewing and periapical radiographs (n = 128, 46% of the total sample). Deep carious lesions (extending to at least the inner half of dentine), deep restorations, direct pulp cappings, root canal treatments, and extractions in permanent premolars and molars were recorded from the radiographs. Patients with untreated deep carious lesions were followed up for 24 months.ResultsIn the total sample 12% had at least one untreated deep carious lesion, 10% at least one deep restoration, and 19% at least one untreated or previously treated deep carious lesion. The follow-up cohort included 48 deep carious lesions in 26 patients. Complete excavation was the most frequently chosen method (81% for lesions reaching the inner half of dentine and 56% the inner third or deeper), followed by stepwise excavation (19% and 37%, respectively).ConclusionsOne-fifth of 14–15-year-olds had at least one untreated or previously treated deep carious lesion. The choice for the carious tissue removal did not follow the current recommendations for less invasive methods.Clinical relevanceContinuing education is needed to improve the diagnostics and management of deep carious lesions.