Bitewing Images Research Articles

Deep Convolutional Neural Network for Automated Staging of Periodontal Bone Loss Severity on Bite-wing Radiographs: An Eigen-CAM Explainability Mapping Approach.

Periodontal disease is a significant global oral health problem. Radiographic staging is critical in determining periodontitis severity and treatment requirements. This study aims to automatically stage periodontal bone loss using a deep learning approach using bite-wing images. A total of 1752 bite-wing images were used for the study. Radiological examinations were classified into 4 groups. Healthy (normal), no bone loss; stage I (mild destruction), bone loss in the coronal third (< 15%); stage II (moderate destruction), bone loss is in the coronal third and from 15 to 33% (15-33%); stage III-IV (severe destruction), bone loss extending from the middle third to the apical third with furcation destruction (> 33%). All images were converted to 512 × 400 dimensions using bilinear interpolation. The data was divided into 80% training validation and 20% testing. The classification module of the YOLOv8 deep learning model was used for the artificial intelligence-based classification of the images. Based on four class results, it was trained using fivefold cross-validation after transfer learning and fine tuning. After the training, 20% of test data, which the system had never seen, were analyzed using the artificial intelligence weights obtained in each cross-validation. Training and test results were calculated with average accuracy, precision, recall, and F1-score performance metrics. Test images were analyzed with Eigen-CAM explainability heat maps. In the classification of bite-wing images as healthy, mild destruction, moderate destruction, and severe destruction, training performance results were 86.100% accuracy, 84.790% precision, 82.350% recall, and 84.411% F1-score, and test performance results were 83.446% accuracy, 81.742% precision, 80.883% recall, and 81.090% F1-score. The deep learning model gave successful results in staging periodontal bone loss in bite-wing images. Classification scores were relatively high for normal (no bone loss) and severe bone loss in bite-wing images, as they are more clearly visible than mild and moderate damage.

Auxiliary Diagnosis of Dental Calculus Based on Deep Learning and Image Enhancement by Bitewing Radiographs.

In the field of dentistry, the presence of dental calculus is a commonly encountered issue. If not addressed promptly, it has the potential to lead to gum inflammation and eventual tooth loss. Bitewing (BW) images play a crucial role by providing a comprehensive visual representation of the tooth structure, allowing dentists to examine hard-to-reach areas with precision during clinical assessments. This visual aid significantly aids in the early detection of calculus, facilitating timely interventions and improving overall outcomes for patients. This study introduces a system designed for the detection of dental calculus in BW images, leveraging the power of YOLOv8 to identify individual teeth accurately. This system boasts an impressive precision rate of 97.48%, a recall (sensitivity) of 96.81%, and a specificity rate of 98.25%. Furthermore, this study introduces a novel approach to enhancing interdental edges through an advanced image-enhancement algorithm. This algorithm combines the use of a median filter and bilateral filter to refine the accuracy of convolutional neural networks in classifying dental calculus. Before image enhancement, the accuracy achieved using GoogLeNet stands at 75.00%, which significantly improves to 96.11% post-enhancement. These results hold the potential for streamlining dental consultations, enhancing the overall efficiency of dental services.

Developing the Benchmark: Establishing a Gold Standard for the Evaluation of AI Caries Diagnostics.

Background/Objectives: The aim of this study was to establish a histology-based gold standard for the evaluation of artificial intelligence (AI)-based caries detection systems on proximal surfaces in bitewing images. Methods: Extracted human teeth were used to simulate intraoral situations, including caries-free teeth, teeth with artificially created defects and teeth with natural proximal caries. All 153 simulations were radiographed from seven angles, resulting in 1071 in vitro bitewing images. Histological examination of the carious lesion depth was performed twice by an expert. A total of thirty examiners analyzed all the radiographs for caries. Results: We generated in vitro bitewing images to evaluate the performance of AI-based carious lesion detection against a histological gold standard. All examiners achieved a sensitivity of 0.565, a Matthews correlation coefficient (MCC) of 0.578 and an area under the curve (AUC) of 76.1. The histology receiver operating characteristic (ROC) curve significantly outperformed the examiners' ROC curve (p < 0.001). All examiners distinguished induced defects from true caries in 54.6% of cases and correctly classified 99.8% of all teeth. Expert caries classification of the histological images showed a high level of agreement (intraclass correlation coefficient (ICC) = 0.993). Examiner performance varied with caries depth (p ≤ 0.008), except between E2 and E1 lesions (p = 1), while central beam eccentricity, gender, occupation and experience had no significant influence (all p ≥ 0.411). Conclusions: This study successfully established an unbiased dataset to evaluate AI-based caries detection on bitewing surfaces and compare it to human judgement, providing a standardized assessment for fair comparison between AI technologies and helping dental professionals to select reliable diagnostic tools.

AI-Dentify: deep learning for proximal caries detection on bitewing x-ray - HUNT4 Oral Health Study.

Dental caries diagnosis requires the manual inspection of diagnostic bitewing images of the patient, followed by a visual inspection and probing of the identified dental pieces with potential lesions. Yet the use of artificial intelligence, and in particular deep-learning, has the potential to aid in the diagnosis by providing a quick and informative analysis of the bitewing images. A dataset of 13,887 bitewings from the HUNT4 Oral Health Study were annotated individually by six different experts, and used to train three different object detection deep-learning architectures: RetinaNet (ResNet50), YOLOv5 (M size), and EfficientDet (D0 and D1 sizes). A consensus dataset of 197 images, annotated jointly by the same six dental clinicians, was used for evaluation. A five-fold cross validation scheme was used to evaluate the performance of the AI models. The trained models show an increase in average precision and F1-score, and decrease of false negative rate, with respect to the dental clinicians. When compared against the dental clinicians, the YOLOv5 model shows the largest improvement, reporting 0.647 mean average precision, 0.548 mean F1-score, and 0.149 mean false negative rate. Whereas the best annotators on each of these metrics reported 0.299, 0.495, and 0.164 respectively. Deep-learning models have shown the potential to assist dental professionals in the diagnosis of caries. Yet, the task remains challenging due to the artifacts natural to the bitewing images.

Accuracy of Extraoral Bitewing Compared with Histopathology in Proximal Caries Detection of Primary Molar Teeth

An accurate diagnosis of dental caries leads to a suitable treatment plan and prevents premature loss of primary teeth. Intraoral bitewing radiography helps caries determination but has limitations in pediatric patients with severe gag reflexes while the extraoral bitewing radiograph resolved the patients who refused to undergo intraoral radiographs. The research objective was to compare the accuracy of extraoral bitewing radiography and the gold standard histopathological examination for proximal caries detection in the primary molars. Twenty-four extracted primary molars with and without proximal caries were divided into three groups and arranged in the mimetic alveolar sockets of a 3D-printed skull and mandible. Two observers evaluated extraoral bitewing images separately twice at one-week intervals. The weighted kappa coefficients showed excellent intra-observer and inter-observer agreements between each session of the extraoral bitewing radiographic assessments. The Mann-Whitney U test showed no difference between the radiographic grading scores of extraoral bitewing images and the gold standard. The sensitivity, positive predictive value (PPV), negative predictive value (NPV), and the area under the receiver operating characteristic (ROC) curve in cavitated carious lesions were higher than in non-cavitated carious lesions. In conclusion, extraoral bitewing is an alternative radiography for pediatric patients who are either uncooperative or intolerant to intraoral radiography.

Analysis of Artifacts and Errors on Intraoral Phosphor Plate Radiographs: A Retrospective Study

Introduction. The advantages of phosphor plates (PPs), including their flexibility, thinness, and wireless connectivity, have contributed to their widespread use in dentistry alongside the advancement of digital radiography techniques. Continuous use of PPs and certain errors may lead to artifacts on the images. This retrospective study aimed to determine the frequency and types of intraoral PP artifacts.&#x0D; Methods. This study was conducted on 814 intraoral PP radiographs, including periapical and bitewing images. The errors and artifacts were classified into 4 main categories: technical errors, plate-related artifacts, scanner-induced artifacts, and ambient light artifacts.&#x0D; Results. A total of 656 periapical and 158 bitewing radiographs were examined. The most observed artifacts on the radiographs were plate-related artifacts, followed by technical errors (n=542, n=461, respectively). Within the category of plate-related artifacts, the most common artifacts were cracks or scratches (n=418, 77.1%), while within the category of technical errors, these were cone-cut errors (n=188, 40.7%). Parallel or zigzag radiopaque lines were the most common scanner-induced artifacts (n=313, 98.7%) and fading was the most common ambient light artefact (n=93, 49.2%). On more than half of the PPs, more than one artifact group was observed.&#x0D; Conclusions. Cone-cut, cracks/scratches, parallel zigzag radiopaque lines, and fading were common PP artifacts and errors in this study. The analysis revealed that over half of the PPs exhibited appearance of more than one artifact group. The high frequency of artifacts poses a risk of incorrect and incomplete diagnoses in radiographs, emphasizing the crucial importance of understanding the causes and developing effective prevention strategies for artifacts to enhance the reliability of diagnostic imaging and ensure the accuracy of patient assessments.

A novel deep learning-based perspective for tooth numbering and caries detection.

The aim of this study was automatically detecting and numbering teeth in digital bitewing radiographs obtained from patients, and evaluating the diagnostic efficiency of decayed teeth in real time, using deep learning algorithms. The dataset consisted of 1170 anonymized digital bitewing radiographs randomly obtained from faculty archives. After image evaluation and labeling process, the dataset was split into training and test datasets. This study proposed an end-to-end pipeline architecture consisting of three stages for matching tooth numbers and caries lesions to enhance treatment outcomes and prevent potential issues. Initially, a pre-trained convolutional neural network (CNN) utilized to determine the side of the bitewing images. Then, an improved CNN model YOLOv7 was proposed for tooth numbering and caries detection. In the final stage, our developed algorithm assessed which teeth have caries by comparing the numbered teeth with the detected caries, using the intersection over union value for the matching process. According to test results, the recall, precision, and F1-score values were 0.994, 0.987 and 0.99 for teeth detection, 0.974, 0.985 and 0.979 for teeth numbering, and 0.833, 0.866 and 0.822 for caries detection, respectively. For teeth numbering and caries detection matching performance; the accuracy, recall, specificity, precision and F1-Score values were 0.934, 0.834, 0.961, 0.851 and 0.842, respectively. The proposed model exhibited good achievement, highlighting the potential use of CNNs for tooth detection, numbering, and caries detection, concurrently. CNNs can provide valuable support to clinicians by automating the detection and numbering of teeth, as well as the detection of caries on bitewing radiographs. By enhancing overall performance, these algorithms have the capacity to efficiently save time and play a significant role in the assessment process.

Dental Caries diagnosis from bitewing images using convolutional neural networks

BackgroundDental caries, also known as tooth decay, is a widespread and long-standing condition that affects people of all ages. This ailment is caused by bacteria that attach themselves to teeth and break down sugars, creating acid that gradually wears away at the tooth structure. Tooth discoloration, pain, and sensitivity to hot or cold foods and drinks are common symptoms of tooth decay. Although this condition is prevalent among all age groups, it is especially prevalent in children with baby teeth. Early diagnosis of dental caries is critical to preventing further decay and avoiding costly tooth repairs. Currently, dentists employ a time-consuming and repetitive process of manually marking tooth lesions after conducting radiographic exams. However, with the rapid development of artificial intelligence in medical imaging research, there is a chance to improve the accuracy and efficiency of dental diagnosis.MethodsThis study introduces a data-driven model for accurately diagnosing dental decay through the use of Bitewing radiology images using convolutional neural networks. The dataset utilized in this research includes 713 patient images obtained from the Samin Maxillofacial Radiology Center located in Tehran, Iran. The images were captured between June 2020 and January 2022 and underwent processing via four distinct Convolutional Neural Networks. The images were resized to 100 × 100 and then divided into two groups: 70% (4219) for training and 30% (1813) for testing. The four networks employed in this study were AlexNet, ResNet50, VGG16, and VGG19.ResultsAmong different well-known CNN architectures compared in this study, the VGG19 model was found to be the most accurate, with a 93.93% accuracy.ConclusionThis promising result indicates the potential for developing an automatic AI-based dental caries diagnostic model from Bitewing images. It has the potential to serve patients or dentists as a mobile app or cloud-based diagnosis service (clinical decision support system).

Impact of artificial intelligence on dentists’ gaze during caries detection: A randomized controlled trial

ObjectivesWe aimed to understand how artificial intelligence (AI) influences dentists by comparing their gaze behavior when using versus not using an AI software to detect primary proximal carious lesions on bitewing radiographs. Methods22 dentists assessed a median of 18 bitewing images resulting in 170 datasets from dentists without AI and 179 datasets from dentists with AI, after excluding data with poor gaze recording quality. We compared time to first fixation, fixation count, average fixation duration, and fixation frequency between both trial groups. Analyses were performed for the entire image and stratified by (1) presence of carious lesions and/or restorations and (2) lesion depth (E1/2: outer/inner enamel; D1–3 outer-inner third of dentin). We also compared the transitional pattern of the dentists’ gaze between the trial groups. ResultsMedian time to first fixation was shorter in all groups of teeth for dentists with AI versus without AI, although p>0.05. Dentists with AI had more fixations (median=68, IQR=31, 116) on teeth with restorations compared to dentists without AI (median=47, IQR=19, 100), p = 0.01. In turn, average fixation duration was longer on teeth with caries for the dentists with AI than those without AI; although p>0.05. The visual search strategy employed by dentists with AI was less systematic with a lower proportion of lateral tooth-wise transitions compared to dentists without AI. ConclusionsDentists with AI exhibited more efficient viewing behavior compared to dentists without AI, e.g., lesser time taken to notice caries and/or restorations, more fixations on teeth with restorations, and fixating for shorter durations on teeth without carious lesions and/or restorations. Clinical significanceAnalysis of dentists’ gaze patterns while using AI-generated annotations of carious lesions demonstrates how AI influences their data extraction methods for dental images. Such insights can be exploited to improve, and even customize, AI-based diagnostic tools, thus reducing the dentists’ extraneous attentional processing and allowing for more thorough examination of other image areas.

Gaze patterns of dentists while evaluating bitewing radiographs

ObjectivesUnderstanding dentists’ gaze patterns on radiographs may allow to unravel sources of their limited accuracy and develop strategies to mitigate them. We conducted an eye tracking experiment to characterize dentists’ scanpaths and thus their gaze patterns when assessing bitewing radiographs to detect primary proximal carious lesions. Methods22 dentists assessed a median of nine bitewing images each, resulting in 170 datasets after excluding data with poor quality of gaze recording. Fixation was defined as an area of attentional focus related to visual stimuli. We calculated time to first fixation, fixation count, average fixation duration, and fixation frequency. Analyses were performed for the entire image and stratified by (1) presence of carious lesions and/or restorations and (2) lesion depth (E1/2: outer/inner enamel; D1–3: outer-inner third of dentin). We also examined the transitional nature of the dentists’ gaze. ResultsDentists had more fixations on teeth with lesions and/or restorations (median=138 [interquartile range=87, 204]) than teeth without them (32 [15, 66]), p<0.001. Notably, teeth with lesions had longer fixation durations (407 milliseconds [242, 591]) than those with restorations (289 milliseconds [216, 337]), p<0.001. Time to first fixation was longer for teeth with E1 lesions (17,128 milliseconds [8813, 21,540]) than lesions of other depths (p = 0.049). The highest number of fixations were on teeth with D2 lesions (43 [20, 51]) and lowest on teeth with E1 lesions (5 [1, 37]), p<0.001. Generally, a systematic tooth-by-tooth gaze pattern was observed. ConclusionsAs hypothesized, while visually inspecting bitewing radiographic images, dentists employed a heightened focus on certain image features/areas, relevant to the assigned task. Also, they generally examined the entire image in a systematic tooth-by-tooth pattern.

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.

Automatic diagnosis and detection of dental caries in bitewing radiographs using pervasive deep gradient based LeNet classifier model

In the field of dental radiography, dental caries prevails to be an extremely common issues which affects major part of population. Radiographic images more specifically, the bitewing images are commonly used one in such cases. An incorrect or inaccurate interpretation will impact the process of diagnosis. So as to aid dentists in the caries assessment, an effective and new technique which integrates image processing and neural network approaches are presented for the exact and precise identification of dental caries in bitewing radiography by classifying them as per the severity of lesions. A deep learning based fully automatic model is proposed in this work for the effective classification of dental images. Initially, the input images are taken and are preprocessed by means of filtering, gray scaling and thresholding process so as to remove noise and to enhance the input images. The enhanced image if then segmented by means of region of interest (ROI) scheme thereby performing blob detection. From the segmented image, the features are extracted by means of Kernel Non-linear Fisher Discriminant Analysis (FDA) which is then followed by selection of suitable features through dimensionality reduction technique. The extracted and selected features are classified using Deep Gradient based LeNet classifier model (DG-LeNet) to diagnose the dental caries by classifying normal and abnormal images and by detecting the decayed region of teeth image. Finally, the dental caries are detected in bitewing radiographs successfully by this method of implementation. A performance of suggested method is estimated in terms of accuracy, sensitivity, specificity, PPV (positive predicted value), NPV (negative predicted value), and error rates. The outcomes attained are compared with existing methods to exemplify the efficacy of suggested model. Thus, the proposed model is effective in detecting the dental caries in bitewing radiographs with the use of pervasive deep gradient based LeNet classifier model.

Assessing the Degree of Concordance Between Panoramic and Digital Bitewing Images in Showing Cervical Burnout

Background and Objectives Cervical burnout is a diffuse radiolucent area in the interproximal surfaces of the posterior teeth in the cervical region. This phenomenon can mimic interproximal caries and cause false positive detection and irreversible destruction of unaffected tooth surfaces. Panoramic radiography is the most common radiography and bitewing radiography is the most useful radiography for detection of caries. The present study aims to assess the degree of concordance between panoramic and digital bitewing images in diagnosing cervical burnout. Subjects and Methods In this epidemiological analytical study, bitewing and panoramic images of 43 patients (172 first and second maxillary molars) referred to a oral &amp; maxillofacial radiology clinic in Ahvaz, Iran. The presence or absence of cervical burnout on interproximal surfaces of maxillary first and second molars was evaluated by two oral &amp; maxillofacial radiologists. The data were analyzed using McNemar test in SPSS software, version 22. Results There was a significant difference in showing cervical burnout on interproximal surfaces of maxillary first and second molar teeth between panoramic and digital bitewing images. Conclusion Bitewing radiography is superior to panoramic radiography in diagnosis of interproximal caries. Panoramic radiography is not a reliable method for this purpose

Detecting calcified pulp stones in patients with periodontal diseases using digital panoramic and periapical radiographies

Background/purposePulp stones are discrete calcified masses appearing in the dental pulp of healthy, disease and unerupted teeth. They are presented freely within the pulp tissue or attached and embedded in any part of coronal and radicular dentin. Here, the purposes of this study were to identify the presence of pulp stones in periodontal patients using digital panoramic and periapical radiographies, and to determine the association with gender, age, tooth type and dental arch.Materials and methodsThis is a retrospective study on selected records of 465 dental samples obtained between January and December, 2020. Data were collected from patients diagnosed with generalized chronic periodontitis and accepted the full periodontal treatment covered by the Government's Periodontal Health Care Program. Their digital panoramic (DPR) examination and full mouth periapical radiographic (DPA) examination (including 12 periapical and 4 bitewing images) were performed at the Outpatient Clinics of the Department of Stomatology, Taichung Veterans General Hospital. Patients were segregated into various groups according to their age, gender and tooth locations. All radiographic images were examined by a dental radiologist and two dentists to identify the presence of pulp stone calcifications and their associated factors using the Sirona applications software. Records were analyzed using SPSS version 22.0 based on tests of Pearson Chi-square and McNemar correlation.ResultsFrom 271 males and 194 females, a total of 465 DPR and 7440 DPA radiographs were studied. Pulp stone calcifications were identified in 270 (58.0%) subjects in DPR images and 348 (74.8%) subjects in DPA images (for 1 or more teeth per subject). We detected calcified opacities in 1031 teeth with DPR images and in 1326 teeth with DPA images from a total of 12,407 teeth. The incidence of pulp stones was similar across genders, but different in tooth locations and dental arch sextant. Moreover, pulp stones were detected more often on maxillary molars and subjects of old ages (>40 years). Digital panoramic and periapical radiography showed significant differences in the detection of pulp stone calcifications (P < 0.05), and detected better with digital periapical radiography examination.ConclusionWe found 58.0% (n = 645) of our patients with pulp stones using digital panoramic radiography, and 74.8% using digital periapical radiography. Regarding individual teeth, only 8.5% of pulp stones were observed in digital panoramic radiography and 10.6% in digital periapical radiography. Pulp stones were more often seen in maxillary molar teeth and old patients of ages >40 years old using periapical radiography examination especially in those patients with periodontally condition. As a two-dimensional imaging system, digital periapical radiography is recommended for a definitive and routine assessment in patients suspected of hard tissue abnormality and pulp calcification formation.

Prescription of bite-wing and panoramic radiographs in pediatric dental patients: An assessment of current trends and provider compliance

BackgroundThe aim of the authors was to evaluate prescription patterns for bite-wing and panoramic radiographs (PRs) for pediatric and adolescent dental patients after the implementation of the most recent guidelines from the American Dental Association and US Food and Drug Administration. MethodsThe authors accessed paid insurance claims data for all 50 states from January 1, 2013, through June 30, 2019, for patients 18 years and younger and extracted a 5% random sample population. The authors performed statistical analyses to evaluate various imaging metrics for pediatric dentists (PDs) and general practitioners (GPs). ResultsA total of 2,123,735 bite-wing images were ordered during 4,734,249 office visits. The average (standard deviation [SD]) time interval between bite-wing examinations ordered by GPs was 13.9 (7.4) months, and for PDs the average (SD) was 13.0 (6.7) months (P < .0001). When divided by age group, 3.5% of all bite-wings were obtained from patients aged 0 through 4 years. For PRs, the authors included 286,824 images in this study. The average (SD) time interval between PRs ordered for the same patient was 3.4 (1.3) years for PDs and 3.3 (1.4) years for GPs. One percent of all PRs were ordered for patients aged 0 through 4 years, with 403 images attributed to PDs and 2,348 to GPs. ConclusionsPDs were more likely to comply with the guidelines on radiograph prescriptions for pediatric and adolescent patients than GPs. Practical ImplicationsInclusion of patient caries risk with insurance claims data could be considered for more appropriate administration of dental radiography. Future guidelines should be developed to include more explicit recommendations for prescribing PRs.

Reproducibility and diagnostic value of a new wedge-guided bitewing image receptor-holding device.

To assess the reproducibility of a wedge-guided bitewing image receptor-holding device (IRHD-WG) compared to a commercially available bitewing image receptor-holding device (IRHD-XCP). Ten operators randomly acquired bitewing radiographs of four posterior regions (Premolar, Molar 1, Molar 2, Molar 3) distributed in two dry bone skulls and mandibles using 2 IRHDs (IRHD-WG and IRHD-XCP). The radiographs corresponding to the same region and IRHD but acquired by different operators were paired for reproducibility comparison. A total of 360 pairs of radiographs were randomized for analysis. Objective analysis consisted of extracting the pixel values from each radiograph and comparing the values between each pair by intraclass correlation coefficient. For subjective analysis, the IRHDs images were digitally removed. Five oral radiologists blinded for the study conditions classified the radiograph pairs according to their similarity and diagnostic value. The answers' relative frequencies were compared by the chi-square test (α = 0.05). The IRHD-WG presented a higher reproducibility (Mean = 0.850; SD = 0.144) than the IRHD-XCP (Mean = 0.615; SD = 0.287) in the objective analysis. Radiographs acquired with the IRHD-WG were more similar than those acquired with the IRHD-XCP (p < 0.001). The diagnostic value of bitewing radiographs acquired with the IRHD-WG was considered superior to those acquired with the IRHD-XCP (p < 0.001). For the objective and subjective analyses of reproducibility, the IRHD-WG performed better than the commercial IRHD-XCP.

Classification of Approximal Caries in Bitewing Radiographs Using Convolutional Neural Networks.

Dental caries is an extremely common problem in dentistry that affects a significant part of the population. Approximal caries are especially difficult to identify because their position makes clinical analysis difficult. Radiographic evaluation—more specifically, bitewing images—are mostly used in such cases. However, incorrect interpretations may interfere with the diagnostic process. To aid dentists in caries evaluation, computational methods and tools can be used. In this work, we propose a new method that combines image processing techniques and convolutional neural networks to identify approximal dental caries in bitewing radiographic images and classify them according to lesion severity. For this study, we acquired 112 bitewing radiographs. From these exams, we extracted individual tooth images from each exam, applied a data augmentation process, and used the resulting images to train CNN classification models. The tooth images were previously labeled by experts to denote the defined classes. We evaluated classification models based on the Inception and ResNet architectures using three different learning rates: 0.1, 0.01, and 0.001. The training process included 2000 iterations, and the best results were achieved by the Inception model with a 0.001 learning rate, whose accuracy on the test set was 73.3%. The results can be considered promising and suggest that the proposed method could be used to assist dentists in the evaluation of bitewing images, and the definition of lesion severity and appropriate treatments.

Caries and Restoration Detection Using Bitewing Film Based on Transfer Learning with CNNs.

Caries is a dental disease caused by bacterial infection. If the cause of the caries is detected early, the treatment will be relatively easy, which in turn prevents caries from spreading. The current common procedure of dentists is to first perform radiographic examination on the patient and mark the lesions manually. However, the work of judging lesions and markings requires professional experience and is very time-consuming and repetitive. Taking advantage of the rapid development of artificial intelligence imaging research and technical methods will help dentists make accurate markings and improve medical treatments. It can also shorten the judgment time of professionals. In addition to the use of Gaussian high-pass filter and Otsu’s threshold image enhancement technology, this research solves the problem that the original cutting technology cannot extract certain single teeth, and it proposes a caries and lesions area analysis model based on convolutional neural networks (CNN), which can identify caries and restorations from the bitewing images. Moreover, it provides dentists with more accurate objective judgment data to achieve the purpose of automatic diagnosis and treatment planning as a technology for assisting precision medicine. A standardized database established following a defined set of steps is also proposed in this study. There are three main steps to generate the image of a single tooth from a bitewing image, which can increase the accuracy of the analysis model. The steps include (1) preprocessing of the dental image to obtain a high-quality binarization, (2) a dental image cropping procedure to obtain individually separated tooth samples, and (3) a dental image masking step which masks the fine broken teeth from the sample and enhances the quality of the training. Among the current four common neural networks, namely, AlexNet, GoogleNet, Vgg19, and ResNet50, experimental results show that the proposed AlexNet model in this study for restoration and caries judgments has an accuracy as high as 95.56% and 90.30%, respectively. These are promising results that lead to the possibility of developing an automatic judgment method of bitewing film.

An artificial intelligence proposal to automatic teeth detection and numbering in dental bite-wing radiographs

Objectives Radiological examination has an important place in dental practice, and it is frequently used in intraoral imaging. The correct numbering of teeth on radiographs is a routine practice that takes time for the dentist. This study aimed to propose an automatic detection system for the numbering of teeth in bitewing images using a faster Region-based Convolutional Neural Networks (R-CNN) method. Methods The study included 1125 bite-wing radiographs of patients who attended the Faculty of Dentistry of Ordu University from 2018 to 2019. A faster R-CNN an advanced object identification method was used to identify the teeth. The confusion matrix was used as a metric and to evaluate the success of the model. Results The deep CNN system (CranioCatch, Eskisehir, Turkey) was used to detect and number teeth in bitewing radiographs. Of 715 teeth in 109 bite-wing images, 697 were correctly numbered in the test data set. The F1 score, precision and sensitivity were 0.9515, 0.9293 and 0.9748, respectively. Conclusions A CNN approach for the analysis of bitewing images shows promise for detecting and numbering teeth. This method can save dentists time by automatically preparing dental charts.

The role of stationary intraoral tomosynthesis in reducing proximal overlap in bitewing radiography.

This study examined the utility of stationary intraoral tomosynthesis (s-IOT) in opening proximal contacts in bitewing radiography. 11 DENTSPLY Rinn Dental X-ray Teaching and Training Replica mannequins (Model #546002, Elgin, Ill) were imaged with a prototype s-IOT device (Surround Medical Systems, Morrisville, NC) and standard bitewing (SBW) technique. Premolar and molar bitewings were acquired with each system. Image receptor holders were used to position receptors and aid in the alignment of the position indicating devices. An expert operator (having more than 5 years of experience in intraoral radiography) acquired the images with the s-IOT prototype and standard intraoral X-ray devices. Images were assessed to analyze percentage overlap of the proximal surfaces using the tools available in ImageJ (NIH, Bethesda Maryland). 253-paired surfaces were included in the analysis. The difference in overlap was statistically significant with standard bitewing (SBW) images resulting in a median overlap of 13%, a minimum of 0%, a maximum of 100% and an interquartile range of 40%. s-IOT resulted in a median overlap of 1%, a minimum of 0%, a maximum of 37% and an interquartile range of 0%. The s-IOT prototype substantially reduced proximal surface overlap compared to conventional bitewing radiography. The use of s-IOT reduced proximal contact overlap compared to standard bitewing radiography for an experienced radiographer. Stationary intraoral tomosynthesis may be a potential alternative to SBW radiography, reducing the number of retakes due to closed contacts.