Is Panoramic Radiography an Accurate Imaging Technique for the Detection of Endodontically Treated Asymptomatic Apical Periodontitis?

COVID-19 Severity in Patients With Apical Periodontitis: A Case Control Study

OBJECTIVES

Apical periodontitis (AP) has been associated with systemic inflammatory biomarkers that have also been associated with COVID-19 severity. This study was designed to test the hypothesis that the presence of apical periodontitis could be associated with increased risk of COVID-19 complications.

METHODS

A case control study (N = 949) was performed using the medical and dental records of patients diagnosed with COVID-19 in the State of Qatar between March 2020 and February 2021. Cases comprised COVID-19 patients (n = 63) who experienced complications (death, intensive care unit admissions, mechanical ventilation), and controls were COVID-19 patients (n = 886) who recovered without such complications. The presence of periapical apical periodontitis was assessed on the radiographic records taken prior to COVID-19 infection. Associations between apical periodontitis and COVID 19 complications were analysed using logistic regression models adjusted for demographic and medical factors. Blood biomarkers were assessed in both groups and compared using the Kruskal-Wallis test.

RESULTS

COVID-19 complications were found to be associated with the presence of apical periodontitis (adjusted odds ratio = 2.72; 95% CI, 1.30-5.68; P = .008). Blood analyses revealed that COVID-19 patients with apical periodontitis had higher levels of white blood cells and haemoglobin A1c than the patients without apical periodontitis.

CONCLUSIONS

The presence of apical periodontitis could be associated with increased risk of COVID-19 complications.

Multi-model deep learning approach for segmentation of teeth and periapical lesions on pantomographs

INTRODUCTION

The fields of medicine and dentistry are beginning to integrate artificial intelligence (AI) in diagnostics. This may reduce subjectivity and improve the accuracy of diagnoses and treatment planning. Current evidence on pathosis detection on pantomographs (PGs) indicates the presence or absence of disease in the entire radiographic image, with little evidence of the relation of periapical pathosis to the causative tooth.

OBJECTIVE

To develop a deep learning (DL) AI model for the segmentation of periapical pathosis and its relation to teeth on PGs.

METHOD

250 PGs were manually annotated by subject experts to lay down the ground truth for training AI algorithms on the segmentation of periapical pathosis. Two approaches were used for lesion detection: Multi-models 1 and 2, using U-net and Mask RCNN algorithms, respectively. The resulting segmented lesions generated on the testing data set were superimposed with results of teeth segmentation and numbering algorithms trained separately to relate lesions to causative teeth. Hence, both multi-model approaches related periapical pathosis to the causative teeth on PGs.

RESULTS

The performance metrics of lesion segmentation carried out by U-net are as follows: Accuracy = 98.1%, precision = 84.5%, re-call = 80.3%, F-1 score = 82.2%, dice index = 75.2%, and Intersection over Union = 67.6%. Mask RCNN carried out lesion segmentation with an accuracy of 46.7%, precision of 80.6%, recall of 55%, and F-1 score of 63.1%.

CONCLUSION

In this study, the multi-model approach successfully related periapical pathosis to the causative tooth on PGs. However, U-net outperformed Mask RCNN in the tasks performed, suggesting that U-net will remain the standard for medical image segmentation tasks. Further training of the models on other findings and an increased number of images will lead to the automation of the detection of common radiographic findings in the dental diagnostic workflow.

Developing deep learning methods for classification of teeth in dental panoramic radiography

OBJECTIVES

We aimed to develop an artificial intelligence-based clinical dental decision-support system using deep-learning methods to reduce diagnostic interpretation error and time and increase the effectiveness of dental treatment and classification.

STUDY DESIGN

We compared the performance of 2 deep-learning methods, You Only Look Once V4 (YOLO-V4) and Faster Regions with the Convolutional Neural Networks (R-CNN), for tooth classification in dental panoramic radiography for tooth classification in dental panoramic radiography to determine which is more successful in terms of accuracy, time, and detection ability. Using a method based on deep-learning models trained on a semantic segmentation task, we analyzed 1200 panoramic radiographs selected retrospectively. In the classification process, our model identified 36 classes, including 32 teeth and 4 impacted teeth.

RESULTS

The YOLO-V4 method achieved a mean 99.90% precision, 99.18% recall, and 99.54% F1 score. The Faster R-CNN method achieved a mean 93.67% precision, 90.79% recall, and 92.21% F1 score. Experimental evaluations showed that the YOLO-V4 method outperformed the Faster R-CNN method in terms of accuracy of predicted teeth in the tooth classification process, speed of tooth classification, and ability to detect impacted and erupted third molars.

CONCLUSIONS

The YOLO-V4 method outperforms the Faster R-CNN method in terms of accuracy of tooth prediction, speed of detection, and ability to detect impacted third molars and erupted third molars. The proposed deep learning based methods can assist dentists in clinical decision making, save time, and reduce the negative effects of stress and fatigue in daily practice.

Evaluating the Diagnostic Accuracy of an AI-Driven Platform for Assessing Endodontic Treatment Outcomes Using Panoramic Radiographs: A Preliminary Study

Background/Objectives: The purpose of this preliminary study was to evaluate the diagnostic performance of an AI-driven platform, Diagnocat (Diagnocat Ltd., San Francisco, CA, USA), for assessing endodontic treatment outcomes using panoramic radiographs (PANs). Materials and Methods: The study included 55 PAN images of 55 patients (15 males and 40 females, aged 12-70) who underwent imaging at a private dental center. All images were acquired using a Hyperion X9 PRO digital cephalometer and were evaluated using Diagnocat, a cloud-based AI platform. The AI system assessed the following endodontic treatment features: filling probability, obturation adequacy, density, overfilling, voids in filling, and short filling. Two human observers independently evaluated the images, and their consensus served as the reference standard. The diagnostic accuracy metrics were calculated. Results: The AI system demonstrated high accuracy (90.72%) and a strong F1 score (95.12%) in detecting the probability of endodontic filling. However, the system showed variable performance in other categories, with lower accuracy metrics and unacceptable F1 scores for short filling and voids in filling assessments (8.33% and 14.29%, respectively). The accuracy for detecting adequate obturation and density was 55.81% and 62.79%, respectively. Conclusions: The AI-based system showed very high accuracy in identifying endodontically treated teeth but exhibited variable diagnostic accuracy for other qualitative features of endodontic treatment.

Periapical Lesions in Panoramic Radiography and CBCT Imaging-Assessment of AI's Diagnostic Accuracy

Background/Objectives: Periapical lesions (PLs) are frequently detected in dental radiology. Accurate diagnosis of these lesions is essential for proper treatment planning. Imaging techniques such as orthopantomogram (OPG) and cone-beam CT (CBCT) imaging are used to identify PLs. The aim of this study was to assess the diagnostic accuracy of artificial intelligence (AI) software Diagnocat for PL detection in OPG and CBCT images. Methods: The study included 49 patients, totaling 1223 teeth. Both OPG and CBCT images were analyzed by AI software and by three experienced clinicians. All the images were obtained in one patient cohort, and findings were compared to the consensus of human readers using CBCT. The AI's diagnostic accuracy was compared to a reference method, calculating sensitivity, specificity, accuracy, positive predictive value (PPV), negative predictive value (NPV), and F1 score. Results: The AI's sensitivity for OPG images was 33.33% with an F1 score of 32.73%. For CBCT images, the AI's sensitivity was 77.78% with an F1 score of 84.00%. The AI's specificity was over 98% for both OPG and CBCT images. Conclusions: The AI demonstrated high sensitivity and high specificity in detecting PLs in CBCT images but lower sensitivity in OPG images.

A 22-year follow-up cross-sectional study on periapical health in relation to the quality of root canal treatment in a Belgian population

AIM

To investigate the prevalence of apical periodontitis (AP) and the technical standard of root canal treatment in a Belgian population, assess the association of different variables with periapical status, and compare the results to a similar study conducted 22 years previously.

METHODOLOGY

In this cross-sectional study, 614 panoramic radiographs of first-time adult attendees at the Dental School of the University Hospital of Ghent were examined. Recorded patient-level parameters included gender, age, number of teeth, number of root filled teeth, presence of any AP lesion, and number of implants. The following tooth-level data were collected: tooth presence, coronal status, quality of coronal restoration, post presence, type of root-filling material, length and density of root filling, root-end filling material, presence of AP, and adjacent implant. Multivariable multilevel binary logistic regression was used to explore the association between patient and tooth characteristics and AP prevalence. Risk differences and confidence intervals were calculated to compare the present with the previous study.

RESULTS

The prevalence of AP at patient and tooth level was 46.9% and 5.6%, respectively. Fifty-one per cent of the 614 patients had at least one root filled tooth, and 5.9% of the 14 655 teeth studied were root filled. AP was found in 45% of root filled teeth. Fifty-four per cent of the root-filled teeth were rated as inadequate. Multivariable multilevel logistic regression revealed that more teeth, more implants, fewer root-filled teeth, adequate density, adequate coronal restoration, and no caries reduced the likelihood of AP. There were no statistically significant differences between the two studies regarding the prevalence of root-filled teeth or AP and the technical quality of root canal treatment.

CONCLUSIONS

The prevalence of AP and the technical quality of root canal treatment in Belgium have not substantially changed over the last 22 years, despite the technological advancements and continuing education in the field.

Deep Learning Models for Classification of Deciduous and Permanent Teeth From Digital Panoramic Images

INTRODUCTION

Dental radiographs are essential in the diagnostic process in dentistry. They serve various purposes, including determining age, analyzing patterns of tooth eruption/shedding, and treatment planning and prognosis. The emergence of digital radiography technology has piqued interest in using artificial intelligence systems to assist and guide dental professionals. These cutting-edge technologies assist in streamlining decision-making processes by enabling entity classification and localization tasks. With the integration of artificial Intelligence algorithms tailored for pediatric dentistry applications and utilizing automated tools, there is an optimistic outlook on improving diagnostic capabilities while reducing stress and fatigue among clinicians.

METHODOLOGY

The dataset comprised 620 images (mixed dentition: 314, permanent dentition: 306). Panoramic radiographs taken were within the age range of 4-16 years. The classification of deciduous and permanent teeth involved training CNN-based models using different architectures such as Resnet, AlexNet, and EfficientNet, among others. A ratio of 70:15:15 was utilized for training, validation, and testing, respectively.

RESULT AND CONCLUSION

The findings indicated that among the models proposed, EfficientNetB0 and EfficientNetB3 exhibited superior performance. Both EfficientNetB0 and EfficientNetB3 achieved an accuracy rate, precision, recall, and F1 scores of 98% in classifying teeth as either deciduous or permanent. This implies that these models were highly accurate in identifying patterns/features within the dataset used for evaluation.

Machine Learning to Predict Apical Lesions: A Cross-Sectional and Model Development Study

(1) Background: We aimed to identify factors associated with the presence of apical lesions (AL) in panoramic radiographs and to evaluate the predictive value of the identified factors. (2) Methodology: Panoramic radiographs from 1071 patients (age: 11-93 a, mean: 50.6 a ± 19.7 a) with 27,532 teeth were included. Each radiograph was independently assessed by five experienced dentists for AL. A range of shallow machine learning algorithms (logistic regression, k-nearest neighbor, decision tree, random forest, support vector machine, adaptive and gradient boosting) were employed to identify factors at both the patient and tooth level associated with AL and to predict AL. (3) Results: AL were detected in 522 patients (48.7%) and 1133 teeth (4.1%), whereas males showed a significantly higher prevalence than females (52.5%/44.8%; p < 0.05). Logistic regression found that an existing root canal treatment was the most important risk factor (adjusted Odds Ratio 16.89; 95% CI: 13.98-20.41), followed by the tooth type 'molar' (2.54; 2.1-3.08) and the restoration with a crown (2.1; 1.67-2.63). Associations between factors and AL were stronger and accuracy higher when using fewer complex models like decision tree (F1 score: 0.9 (0.89-0.9)). (4) Conclusions: The presence of AL was higher in root-canal treated teeth, those with crowns and molars. More complex machine learning models did not outperform less-complex ones.

Evaluation of an artificial intelligence system for the diagnosis of apical periodontitis on digital panoramic images

Aims

The aim of the present study was to evaluate the effectiveness of an artificial intelligence (AI) system in the detection of roots with apical periodontitis (AP) on digital panoramic radiographs.

Materials and Methods

Three hundred and six panoramic radiographs containing 400 roots with AP (an equal number for both jaws) were used to test the diagnostic performance of an AI system. Panoramic radiographs of the patients were selected with the terms 'apical lesion' and 'apical periodontitis' from the archive and then with the agreement of two oral and maxillofacial radiologists. The radiologists also carried out the grouping and determination of the lesion borders. A deep learning (DL) model was built and the diagnostic performance of the model was evaluated by using recall, precision, and F measure.

Results

The recall, precision, and F-measure scores were 0.98, 0.56, and 0.71, respectively. While the number of roots with AP detected correctly in the mandible was 169 of 200 roots, it was only 56 of 200 roots in the maxilla. Only four roots without AP were incorrectly identified as those with AP.

Conclusions

The DL method developed for the automatic detection of AP on digital panoramic radiographs showed high recall, precision, and F measure values for the mandible, but low values for the maxilla, especially for the widened periodontal ligament (PL)/uncertain AP.

Artificial Intelligence for Classifying the Relationship between Impacted Third Molar and Mandibular Canal on Panoramic Radiographs

The purpose of this investigation was to evaluate the diagnostic performance of two convolutional neural networks (CNNs), namely ResNet-152 and VGG-19, in analyzing, on panoramic images, the rapport that exists between the lower third molar (MM3) and the mandibular canal (MC), and to compare this performance with that of an inexperienced observer (a sixth year dental student). Utilizing the k-fold cross-validation technique, 142 MM3 images, cropped from 83 panoramic images, were split into 80% as training and validation data and 20% as test data. They were subsequently labeled by an experienced radiologist as the gold standard. In order to compare the diagnostic capabilities of CNN algorithms and the inexperienced observer, the diagnostic accuracy, sensitivity, specificity, and positive predictive value (PPV) were determined. ResNet-152 achieved a mean sensitivity, specificity, PPV, and accuracy, of 84.09%, 94.11%, 92.11%, and 88.86%, respectively. VGG-19 achieved 71.82%, 93.33%, 92.26%, and 85.28% regarding the aforementioned characteristics. The dental student's diagnostic performance was respectively 69.60%, 53.00%, 64.85%, and 62.53%. This work demonstrated the potential use of deep CNN architecture for the identification and evaluation of the contact between MM3 and MC in panoramic pictures. In addition, CNNs could be a useful tool to assist inexperienced observers in more accurately identifying contact relationships between MM3 and MC on panoramic images.

Pre-Chemotherapy Dental Screening: Is There Additional Diagnostic Value for a Panoramic Radiograph?

BACKGROUND

The oral cavity is a potential source of infectious complications in patients treated with myelosuppressive chemotherapy (CT). Pre-chemotherapy oral examination to identify foci of infection is recommended, but it is unclear whether this should include panoramic radiography. The present study aimed to evaluate the additional diagnostic merit of panoramic radiography as part of pre-CT oral screening.

METHODS

Patients with solid tumors scheduled to receive a myelosuppressive CT were eligible. The foci definition followed the guidelines of the Dutch Association of Maxillofacial Surgery. Oral foci assessed by clinical evaluation and panoramic radiography were compared.

RESULTS

In 33 out of 93 patients (35.5%), one or more foci were identified by clinical examination, whereas in 49.5% of patients, panoramic radiography showed pathology. In 19 patients, an oral focus was missed by clinical examination only, whereas in 11 patients, panoramic radiography indicated periodontal bone loss, but advanced periodontitis was not substantiated by clinical examination.

CONCLUSIONS

Panoramic radiographs complement clinical examinations and have additional diagnostic value. Nevertheless, the additional merit seems small, and the clinical relevance may vary depending on the anticipated risk of developing oral complications and the need for detailed diagnosis and rigorous elimination of oral foci prior to the start of cancer therapy.

A Cone Beam CT Study on the Correlation between Crestal Bone Loss and Periapical Disease

The aim of this study was to determine whether the degree of bone loss around teeth can be linked to the loss of vitality of adjacent teeth and periapical disease, which necessitates root canal treatments. Three hundred and twenty-one full maxilla cone-beam computed tomography scans were examined. The parameters investigated included the degree of crestal bone loss in relation to the cementoenamel junction, the presence/absence of apical periodontitis, and the presence/absence of root canal treatments. Out of the 2001 teeth examined, 696 (34.8%) showed evidence of crestal bone loss. The degree of crestal bone loss was classified as mild, moderate, or severe. A significant association (p < 0.001) was found between the presence of crestal bone loss around a tooth and root canal treatment of that tooth. It was found that it is more likely for teeth with crestal bone loss to be root canal treated compared to teeth with existing root canal treatment and healthy crestal bone levels. Furthermore, teeth with buccal or lingual crestal bone loss were significantly associated with a higher rate of periapical disease than teeth without crestal bone loss (p < 0.001). CBCT identified the severity of bone loss on all surfaces of the teeth, and the most common presentation was bone loss to the mid-root level. Teeth with crestal bone loss were significantly more likely to be associated with a higher rate of periapical disease. Teeth with crestal bone loss were more likely to be root treated than teeth with healthy crestal bone levels.

Spectral photon counting for panoramic dental imaging

Panoramic x-ray imaging is a versatile, low-dose imaging tool, which is routinely used for dental applications. In this work, we explore a further improvement of the concept by introducing recently developed spectral photon-counting detector technology into a conventional panoramic imaging unit. In addition we adapt spectral material decomposition algorithms to panoramic imaging needs. Finally, we provide first experimental results, demonstrating decomposition of an anthropomorphic head phantom into soft tissue and dentin basis material panoramic images, while keeping the noise level acceptable using regularization approaches. The obtained results reveal a potential benefit of spectral photon-counting technology also for dental imaging applications.

Developments and Performance of Artificial Intelligence Models Designed for Application in Endodontics: A Systematic Review

Technological advancements in health sciences have led to enormous developments in artificial intelligence (AI) models designed for application in health sectors. This article aimed at reporting on the application and performances of AI models that have been designed for application in endodontics. Renowned online databases, primarily PubMed, Scopus, Web of Science, Embase, and Cochrane and secondarily Google Scholar and the Saudi Digital Library, were accessed for articles relevant to the research question that were published from 1 January 2000 to 30 November 2022. In the last 5 years, there has been a significant increase in the number of articles reporting on AI models applied for endodontics. AI models have been developed for determining working length, vertical root fractures, root canal failures, root morphology, and thrust force and torque in canal preparation; detecting pulpal diseases; detecting and diagnosing periapical lesions; predicting postoperative pain, curative effect after treatment, and case difficulty; and segmenting pulp cavities. Most of the included studies (n = 21) were developed using convolutional neural networks. Among the included studies. datasets that were used were mostly cone-beam computed tomography images, followed by periapical radiographs and panoramic radiographs. Thirty-seven original research articles that fulfilled the eligibility criteria were critically assessed in accordance with QUADAS-2 guidelines, which revealed a low risk of bias in the patient selection domain in most of the studies (risk of bias: 90%; applicability: 70%). The certainty of the evidence was assessed using the GRADE approach. These models can be used as supplementary tools in clinical practice in order to expedite the clinical decision-making process and enhance the treatment modality and clinical operation.

Deep learning-based apical lesion segmentation from panoramic radiographs

Purpose

Convolutional neural networks (CNNs) have rapidly emerged as one of the most promising artificial intelligence methods in the field of medical and dental research. CNNs can provide an effective diagnostic methodology allowing for the detection of early-staged diseases. Therefore, this study aimed to evaluate the performance of a deep CNN algorithm for apical lesion segmentation from panoramic radiographs.

Materials and Methods

A total of 1000 panoramic images showing apical lesions were separated into training (n=800, 80%), validation (n=100, 10%), and test (n=100, 10%) datasets. The performance of identifying apical lesions was evaluated by calculating the precision, recall, and F1-score.

Results

In the test group of 180 apical lesions, 147 lesions were segmented from panoramic radiographs with an intersection over union (IoU) threshold of 0.3. The F1-score values, as a measure of performance, were 0.828, 0.815, and 0.742, respectively, with IoU thresholds of 0.3, 0.4, and 0.5.

Conclusion

This study showed the potential utility of a deep learning-guided approach for the segmentation of apical lesions. The deep CNN algorithm using U-Net demonstrated considerably high performance in detecting apical lesions.

Analysis of Deep Learning Techniques for Dental Informatics: A Systematic Literature Review

Within the ever-growing healthcare industry, dental informatics is a burgeoning field of study. One of the major obstacles to the health care system’s transformation is obtaining knowledge and insightful data from complex, high-dimensional, and diverse sources. Modern biomedical research, for instance, has seen an increase in the use of complex, heterogeneous, poorly documented, and generally unstructured electronic health records, imaging, sensor data, and text. There were still certain restrictions even after many current techniques were used to extract more robust and useful elements from the data for analysis. New effective paradigms for building end-to-end learning models from complex data are provided by the most recent deep learning technology breakthroughs. Therefore, the current study aims to examine the most recent research on the use of deep learning techniques for dental informatics problems and recommend creating comprehensive and meaningful interpretable structures that might benefit the healthcare industry. We also draw attention to some drawbacks and the need for better technique development and provide new perspectives about this exciting new development in the field.

Apical status and prevalence of endodontic treated teeth among Saudi adults in Eastern province: A prospective radiographic evaluation

Introduction

The main cause for developing periapical lesions (PA) is the root canal infection. The mentioned causes may play a role in not controlling it but are not a “true” cause.

Objective

To determine apical status and prevalence of endodontic treated tooth using radiograph assessment in relation to quality of root canal treatment and clinical factors among Saudi adults in the Eastern province.

Patients and methods

This prospective case series study included 2161 patients who received root canal treatment (RCT) at Dammam Specialized Dental Center, Dammam Medical Complex, Ministry of Health, Saudi Arabia, between October 21, 2019 and April 22, 2020, after getting ethical approval from the Institutional Research Board (IRB). Saudi natives of either gender, age ≥ 18, with at least one fixed bridge or single dental crown evaluated on a clear, high-quality radiography image were recruited for the study. To determine the periapical state of root canal-filled teeth, the 'periapical index' (PAI) was used. All pertinent patient information was analyzed in SPSS verion-20 (IBM product, Chicago).

Results

Out of 2161 cases, a PA lesion was present in 756 (35.0%). The prevalence of periapical lesions in endodontically treated teeth was 31.2%. PA lesion was associated with molar involvement (50.8% vs. 36.6%, p = 0.001), poor RCT quality (85.2% vs. 51.0%, p = 0.001), and smoking (13.6% vs. 10.5%, p = 0.028). According to logistic regression model, female gender, molar tooth, and poor RCT quality were more likely to expose PA lesion 1.5 times, 1.8 times, and 5 times, respectively.

Conclusion

It is concluded that approximately 1/3rd of endodontically treated teeth are susceptible to the occurrence of periapical lesions in radiographic assessment, which are significantly associated with females, molars, and poor RCT quality, indicating a challenge for endodontists to improve their root canal assessment accuracy.

Periapical and Endodontic Status of Patients with Inflammatory Bowel Disease: Age- and Sex- matched Case-control Study

AIM

Crohn's disease (CD) and ulcerative colitis (UC) are two chronic recurrent inflammatory processes of the gastrointestinal tract, grouped under the name Inflammatory Bowel Disease (IBD), causing clinical episodes of intestinal inflammation. The aim of this study was to investigate the possible association between IBD and the prevalence of apical periodontitis and root canal treatment.

METHODOLOGY

A case-control study design matched to age and sex was used. The study group (SG) included 28 patients with IBD (13 with CD, 15 with UC). Another 28 healthy subjects, without IBD and age- and sex- matched, were included in the control group (CG). Radiographic records were analyzed and apical periodontitis (AP) was diagnosed as radiolucent periapical lesions (RPLs), using the periapical index score (PAI). Student's t test, χ² test and multivariate logistic regression were used in the statistical analysis.

RESULTS

In the CG, only 17 subjects (61%) had at least one tooth with AP, while in the SG group they were 23 patients (82%) (OR = 2.98; CI 95% = 0.87 - 10.87; p = 0.08). The number of subjects with one or more root filled teeth (RFT) in the CG was 14 (50%), while in the SG they were 22 (79%) (OR = 3.67; 95% CI = 1.14 - 11.79; p = 0.026). At least one RFT with AP was evident in 3 subjects (10.7%) in the control group, while in the study group 15 patients (53.6%) showed RFT with AP (OR = 9.60; 95% CI = 2.35 - 39.35; p = 0.001). In the multivariate logistic regression analysis, only endodontic status was found to be associated with IBD (OR = 1.86; 95% CI = 1.24 - 2.80; p = 0.003).

CONCLUSION

IBD, ulcerative colitis and Crohn´s disease, is associated with higher prevalence of RFT and higher percentage of RFT with periapical lesions. Dentists should consider these findings when caring for IBD patients by monitoring the evolution of periapical lesions of endodontically treated teeth.

Artificial Intelligence Application in Assessment of Panoramic Radiographs

The aim of this study was to assess the reliability of the artificial intelligence (AI) automatic evaluation of panoramic radiographs (PRs). Thirty PRs, covering at least six teeth with the possibility of assessing the marginal and apical periodontium, were uploaded to the Diagnocat (LLC Diagnocat, Moscow, Russia) account, and the radiologic report of each was generated as the basis of automatic evaluation. The same PRs were manually evaluated by three independent evaluators with 12, 15, and 28 years of experience in dentistry, respectively. The data were collected in such a way as to allow statistical analysis with SPSS Statistics software (IBM, Armonk, NY, USA). A total of 90 reports were created for 30 PRs. The AI protocol showed very high specificity (above 0.9) in all assessments compared to ground truth except from periodontal bone loss. Statistical analysis showed a high interclass correlation coefficient (ICC > 0.75) for all interevaluator assessments, proving the good credibility of the ground truth and the reproducibility of the reports. Unacceptable reliability was obtained for caries assessment (ICC = 0.681) and periapical lesions assessment (ICC = 0.619). The tested AI system can be helpful as an initial evaluation of screening PRs, giving appropriate credibility reports and suggesting additional diagnostic methods for more accurate evaluation if needed.

Is periapical surgery follow-up with only two-dimensional radiographs reliable? A retrospective cohort type sensitivity study

Background

Two-dimensional (2D) radiographic techniques are commonly used for assessing lesion prognosis after endodontic surgery. The present retrospective cohort study analyzes the sensitivity and ability of different radiographic techniques in obtaining area and volume measurements of periapical lesions.

Material and Methods

Preoperative and follow-up (6-48 months) periapical and panoramic radiographs (index test) and cone-beam computed tomography (CBCT) images (reference standard) were selected from an endodontic microsurgery database. Sensitivity was analyzed independently by two examiners. The areas of the 2D radiographic images and CBCT volumes were studied using Itk-Snap software and Romexis viewer.

Results

The sample comprised 105 patients and 105 teeth, with a mean follow-up of 21 months (range 6-48). Preoperatively, CBCT detected all the periapical areas, periapical radiography detected 67, and panoramic radiography detected 60. Postoperatively, of the 52 cases in which CBCT detected remains of the periapical area, periapical radiography detected 22, and panoramic radiography detected 17. The measurements of the areas obtained by the 2D methods, and the volumes obtained by CBCT, had to be transformed into linear measures for comparison purposes. The measurements were found to be significantly different in both the preoperative and the follow-up images.

Conclusions

 Periapical radiography showed greater sensitivity than panoramic radiography, both preoperatively and at follow-up. The lesions measured with CBCT were larger, with significant differences than as evidenced by the periapical and panoramic radiographs.

Key words:Periapical radiography, panoramic radiography, CBCT, sensitivity, treatment outcome, size of periapical radiolucency, area, volume.

Which factors related to apical radiolucency may influence its radiographic detection? A study using CBCT as reference standard

Objectives

This study aimed to evaluate the detection rate of apical radiolucencies in 2-dimensional images using cone-beam computed tomography (CBCT) as the reference standard, and to determine which factors related to the apical radiolucencies and the teeth could influence its detection.

Materials and Methods

The sample consisted of exams of patients who had panoramic (PAN) and/or periapical (PERI) radiography and CBCT. The exams were assessed by 2 oral radiologists and divided into PAN+CBCT (227 teeth–285 roots) and PERI+CBCT (94 teeth–115 roots). Radiographic images were evaluated for the presence of apical radiolucency, while CBCT images were assessed for presence, size, location, and involvement of the cortical bone (thinning, expansion, and destruction). Diagnostic values were obtained for PERI and PAN.

Results

PERI and PAN presented high accuracy (0.83 and 0.77, respectively) and specificity (0.89 and 0.91, respectively), but low sensitivity, especially for PAN (0.40 vs. 0.65 of PERI). The size of the apical radiolucency was positively correlated with its detection in PERI and PAN (p < 0.001). For PAN, apical radiolucencies were 3.93 times more frequently detected when related to single-rooted teeth (p = 0.038). The other factors did not influence apical radiolucency detection (p > 0.05).

Conclusions

PERI presents slightly better accuracy than PAN for the detection of apical radiolucency. The size is the only factor related to radiolucency that influences its detection, for both radiographic exams. For PAN, apical radiolucency is most often detected in single-rooted teeth.

Artificial Intelligence Model to Detect Real Contact Relationship between Mandibular Third Molars and Inferior Alveolar Nerve Based on Panoramic Radiographs

This study aimed to develop a novel detection model for automatically assessing the real contact relationship between mandibular third molars (MM3s) and the inferior alveolar nerve (IAN) based on panoramic radiographs processed with deep learning networks, minimizing pseudo-contact interference and reducing the frequency of cone beam computed tomography (CBCT) use. A deep-learning network approach based on YOLOv4, named as MM3-IANnet, was applied to oral panoramic radiographs for the first time. The relationship between MM3s and the IAN in CBCT was considered the real contact relationship. Accuracy metrics were calculated to evaluate and compare the performance of the MM3-IANnet, dentists and a cooperative approach with dentists and the MM3-IANnet. Our results showed that in comparison with detection by dentists (AP = 76.45%) or the MM3-IANnet (AP = 83.02%), the cooperative dentist-MM3-IANnet approach yielded the highest average precision (AP = 88.06%). In conclusion, the MM3-IANnet detection model is an encouraging artificial intelligence approach that might assist dentists in detecting the real contact relationship between MM3s and IANs based on panoramic radiographs.

Comparison of the diagnostic efficacy of 2D radiography and cone beam computed tomography in persistent apical periodontal disease: A PRISMA-DTA systematic review and meta-analysis

OBJECTIVE

The objective of this study was to answer the question: Do conventional radiographs (periapical/panoramic) afford better diagnostic outcomes than cone beam computed tomography (CBCT) as a complement for clinical diagnosis of apical lesions with persistent apical periodontitis or disease after root canal treatment?

STUDY DESIGN

Five electronic databases were searched and provided information to enable construction of a table to determine primary diagnostic measures and secondary parameters. The evidence was appraised with the Quality Assessment of Diagnostic Accuracy Studies tool and GRADEpro software.

RESULTS

Twenty-seven articles (9903 diagnostic images) were included. The pooled sensitivity, specificity, area under the receiver operating characteristic curve (AUC_ROC), positive predictive value, negative predictive value, negative likelihood ratio, and accuracy were 0.58, 1, 0.77, 1, 0.68, 0.45, and 0.79, respectively.

CONCLUSIONS

Moderate certainty evidence suggested that conventional radiographs showed poor sensitivity and excellent specificity but good diagnostic performance in terms of AUC_ROC and accuracy. Sensitivity, AUC_ROC, and negative likelihood ratio values could be reduced if the time elapsed to diagnosis after root canal treatment exceeded 5 years. The use of CBCT with a reduced field of view or a 2D radiographic technique should be weighed considering patient-specific and indication-oriented criteria as taking precedence over the therapeutic goal.

A Validation Employing Convolutional Neural Network for the Radiographic Detection of Absence or Presence of Teeth

Dental radiography plays an important role in clinical diagnosis, treatment and making decisions. In recent years, efforts have been made on developing techniques to detect objects in images. The aim of this study was to detect the absence or presence of teeth using an effective convolutional neural network, which reduces calculation times and has success rates greater than 95%. A total of 8000 dental panoramic images were collected. Each image and each tooth was categorized, independently and manually, by two experts with more than three years of experience in general dentistry. The neural network used consists of two main layers: object detection and classification, which is the support of the previous one. A Matterport Mask RCNN was employed in the object detection. A ResNet (Atrous Convolution) was employed in the classification layer. The neural model achieved a total loss of 0.76% (accuracy of 99.24%). The architecture used in the present study returned an almost perfect accuracy in detecting teeth on images from different devices and different pathologies and ages.

Comparative analysis of different periapical index systems used in cone-beam computed tomography

This study aimed to compare the three index systems designed for cone-beam computed tomography (CBCT) in terms of intra- and inter-observer agreement. 117 root-filled teeth with or without periapical radiolucency from 77 of already existing CBCT images were chosen randomly. Two observers evaluated the periapical status of the selected teeth and graded the scores twice using CBCT periapical index (CBCTPAI), endodontic radiolucency index (ERI) and complex periapical index (COPI) part of the periapical and endodontic status scale (PESS), respectively. The researchers' self-agreement kappa values ranged from substantial to almost perfect. A moderate inter-observer agreement was present for the COPI and ERI, whereas a fair agreement was present for CBCTPAI. The researchers' ICC for the inter-observer reliability of CBCTPAI, ERI and COPI was 0.75, 0.77 and 0.80, respectively. COPI had the highest self-agreement and inter-observer reliability. ERI showed the highest intra-observer variation, whereas CBCTPAI showed the highest inter-observer variation.

Elevated Coronary Artery Calcium scores are associated with tooth loss

Aim

This study explores the association between Coronary Artery Calcium (CAC) scores and dental pathology such as missing teeth, the (peri-apical) health status and restoration grade of the teeth, and the grade of alveolar bone loss seen on a dental panoramic radiograph (Orthopantomograph–OPG).

Materials and methods

In this retrospective cross-sectional study, data was collected from three hospitals spread in the Netherlands. Patients were included when a CAC score and an OPG were available, both recorded within a maximum period of 365 days from 2009–2017. The CAC score was measured on a CT scan, using the Agatston method. To assess dental pathology, the number of missing teeth, the number of dental implants, alveolar bone loss, caries, endodontic treatments, peri-apical radiolucencies, bone loss at implants, impacted teeth and dental cysts, were determined on the OPG. All observers were calibrated. The electronic health records provided information about: gender, age, smoking, Diabetes Mellitus, hypercholesterolemia, hypertension and Body Mass Index (BMI).

Results

212 patients were included. We found a statistically significant association between the number of missing teeth and the CAC score. When modeling age, sex, and other well-known risk factors for cardiovascular disease, the significant correlation was no longer present after multivariate correction. Furthermore, the results showed a trend for more teeth with peri-apical lesions and a higher percentage of mean alveolar bone loss in the group with the highest CAC scores.

Conclusion

This study showed that being edentulous or missing teeth is correlated to higher CAC scores however failed to be an independent predictor of atherosclerotic cardiovascular diseases. The number of (missing) teeth is an easily accessible marker and could be used as a marker for atherosclerotic cardiovascular disease (ACVD) risk by almost any healthcare worker. The current study needs to be considered as an explorative pilot study and could contribute to the design of further (prospective) studies on the relationship between dental pathology and coronary artery calcification by adding clinical information and extra cardiovascular biomarkers.

How massed practice improves visual expertise in reading panoramic radiographs in dental students: An eye tracking study

The interpretation of medical images is an error-prone process that may yield severe consequences for patients. In dental medicine panoramic radiography (OPT) is a frequently used diagnostic procedure. OPTs typically contain multiple, diverse anomalies within one image making the diagnostic process very demanding, rendering students’ development of visual expertise a complex task. Radiograph interpretation is typically taught through massed practice; however, it is not known how effective this approach is nor how it changes students’ visual inspection of radiographs. Therefore, this study investigated how massed practice–an instructional method that entails massed learning of one type of material–affects processing of OPTs and the development of diagnostic performance. From 2017 to 2018, 47 dental students in their first clinical semester diagnosed 10 OPTs before and after their regular massed practice training, which is embedded in their curriculum. The OPTs contained between 3 to 26 to-be-identified anomalies. During massed practice they diagnosed 100 dental radiographs without receiving corrective feedback. The authors recorded students’ eye movements and assessed the number of correctly identified and falsely marked low- and high prevalence anomalies before and after massed practice. Massed practice had a positive effect on detecting anomalies especially with low prevalence (p < .001). After massed practice students covered a larger proportion of the OPTs (p < .001), which was positively related to the detection of low-prevalence anomalies (p = .04). Students also focused longer, more frequently, and earlier on low-prevalence anomalies after massed practice (p_s < .001). While massed practice improved visual expertise in dental students with limited prior knowledge, there is still substantial room for improvement. The results suggest integrating massed practice with more deliberate practice, where, for example, corrective feedback is provided, and support is adapted to students’ needs.

Development of a Deep Learning Algorithm for Periapical Disease Detection in Dental Radiographs

Periapical radiolucencies, which can be detected on panoramic radiographs, are one of the most common radiographic findings in dentistry and have a differential diagnosis including infections, granuloma, cysts and tumors. In this study, we seek to investigate the ability with which 24 oral and maxillofacial (OMF) surgeons assess the presence of periapical lucencies on panoramic radiographs, and we compare these findings to the performance of a predictive deep learning algorithm that we have developed using a curated data set of 2902 de-identified panoramic radiographs. The mean diagnostic positive predictive value (PPV) of OMF surgeons based on their assessment of panoramic radiographic images was 0.69(± 0.13), indicating that dentists on average falsely diagnose 31% of cases as radiolucencies. However, the mean diagnostic true positive rate (TPR) was 0.51(± 0.14), indicating that on average 49% of all radiolucencies were missed. We demonstrate that the deep learning algorithm achieves a better performance than 14 of 24 OMF surgeons within the cohort, exhibiting an average precision of 0.60(± 0.04), and an F1 score of 0.58(± 0.04) corresponding to a PPV of 0.67(± 0.05) and TPR of 0.51(± 0.05). The algorithm, trained on limited data and evaluated on clinically validated ground truth, has potential to assist OMF surgeons in detecting periapical lucencies on panoramic radiographs.

Prevalence of Apical Periodontitis in patients with Multiple Myeloma

BACKGROUND

Aim Previous reports have been analyzed the prevalence/association of apical periodontitis (AP) with systemic diseases. The present study aims to analyze the prevalence of healthy/diseased periapex and endodontic treatments in patients with Multiple Myeloma (MM) and compare the results with those of control subjects.

MATERIAL AND METHODS

Methodology Panoramic radiographs of 50 individuals with MM were evaluated and compared with 50 controls that were sex and age matched exactly with the diseased group. Radiographic analysis was performed by 2 two experienced endodontists under standardized conditions. The periapical status (presence or not of AP) was assessed using the periapical index (PAI). Data included systemic health, technical quality of root fillings, total number of teeth, quality of restoration, and periapical status. Statistical evaluation of differences between groups included used chi-squared tests and Fisher's exact tests.

RESULTS

The prevalence of root canal-treated teeth was 10.11% in the MM group and 12.05% in the control group (p=0.90). The average root canal-treated teeth in the test group was 2,34 and 2.48 in the control group, where the difference was statistically significant (p=0.05). AP in 1 or more teeth was found in 86 % and in 78% of the patients in the MM and the control groups, respectively. When analyzed by subject, there was no statistically significant difference in the prevalence of AP (p>0.72). Similarly there was also no statistically significant difference in the prevalence of PA (p=0.85), when analyzed by tooth, AP was found in 63.2% and 62.9% in MM and control groups.

CONCLUSIONS

The presence of AP and endodontic treatment was not significantly different in individuals with MM compared with control subjects. Future studies are needed to elucidate and confirm the association between MM and AP.

Imaging of mandibular fractures: a pictorial review

Mandibular fractures are among the most common maxillofacial fractures observed in emergency rooms and are mainly caused by road accidents. The clinical features of mandibular fractures include malocclusion and loss of mandibular function. Panoramic radiography is usually limited to isolated lesions, whereas computed tomography is the tool of choice for all other facial traumatic events. No reference standard classification system for the different types of mandibular fractures is defined. Therapeutic options include a conservative approach or surgical treatment based on the anatomic area and the severity of fracture. The main purpose of this pictorial review is to illustrate a practical description of the pathophysiology of mandibular fractures and describe both the imaging techniques to recognise them and the therapeutic indications.

Electronic processing of digital panoramic radiography for the detection of apical periodontitis

INTRODUCTION

This study aimed to evaluate the accuracy of both digital complete and small portion of panoramic radiography (PAN) in the detection of clinically/surgically confirmed asymptomatic apical periodontitis (AP) lesions with and without endodontic treatment.

METHODS

A total of 480 patients/teeth including 120 AP with and without endodontic treatment, and 120 healthy periapex with and without endodontic treatment were detected via CBCT using the periapical index system. Each diseased and healthy patient underwent PAN first and a CBCT scan within 40 days. All 480 cases were assessed by four different methods, as follows: complete PAN with clinical examination of each tooth available and not available, respectively, and small portion of PAN in which a root with crown and root without crown were displayed, respectively. Periapical index system was also used to assess AP by PAN. Accuracy for both complete and small portion of PAN with respect to CBCT was analyzed.

RESULTS

The overall accuracy of the four methods for teeth with endodontic treatment (73.4) was higher than teeth without endodontic treatment (66.6). Accuracy of complete PAN and portion of PAN was 71.3 and 68.7, respectively. As regards teeth without endodontic treatment, accuracy was higher for complete PAN in the upper/lower incisive area and for small portion of PAN in the upper molar area. No difference was found in teeth with endodontic treatment.

CONCLUSION

Complete and small portion of PAN showed greater accuracy in the upper/lower incisive area and upper molar area of untreated teeth, respectively, whereas no difference was found in treated teeth.

Evaluation of an artificial intelligence system for detecting vertical root fracture on panoramic radiography

OBJECTIVES

The aim of this study was to evaluate the use of a convolutional neural network (CNN) system for detecting vertical root fracture (VRF) on panoramic radiography.

METHODS

Three hundred panoramic images containing a total of 330 VRF teeth with clearly visible fracture lines were selected from our hospital imaging database. Confirmation of VRF lines was performed by two radiologists and one endodontist. Eighty percent (240 images) of the 300 images were assigned to a training set and 20% (60 images) to a test set. A CNN-based deep learning model for the detection of VRFs was built using DetectNet with DIGITS version 5.0. To defend test data selection bias and increase reliability, fivefold cross-validation was performed. Diagnostic performance was evaluated using recall, precision, and F measure.

RESULTS

Of the 330 VRFs, 267 were detected. Twenty teeth without fractures were falsely detected. Recall was 0.75, precision 0.93, and F measure 0.83.

CONCLUSIONS

The CNN learning model has shown promise as a tool to detect VRFs on panoramic images and to function as a CAD tool.

Clinical and Radiographic Assessment of Cases Referred to Endodontic Surgery

Objective

The objective of the study was to assess the quality of root canal fillings of cases referred to endodontic surgery using preoperative radiographs and correlate it with endodontic surgery treatment decision. The objective was also to analyse clinical symptoms and size of periapical lesions on radiographs and correlate them with treatment decisions including non-surgical retreatment, endodontic surgery and extraction.

Materials and Methods

A questionnaire was composed to record the data. Eighty-six patients with 109 teeth, who were referred to endodontic surgery, participated in the research. The quality of root canal filling was assessed according to its homogeneity and filling length on digital radiographs. The data were analyzed using χ2-test and t-test.

Results

Of the teeth referred to endodontic surgery, 97.2% were treated by a general practice dentist, endodontic retreatment was attempted in 20.6%, and root canal filling was homogeneous and within 1 mm from the apex in 21.6%. Endodontic surgery, retreatment, extraction and no treatment were selected in 90.1%, 5.4%, 1.8% and 2.7% of the cases, respectively.

Conclusions

Low percentage of adequate root canal fillings and high percentage of endodontic surgery decisions suggest that there is a need to increase awareness of non-surgical retreatment options.

Deep Learning for the Radiographic Detection of Apical Lesions

INTRODUCTION

We applied deep convolutional neural networks (CNNs) to detect apical lesions (ALs) on panoramic dental radiographs.

METHODS

Based on a synthesized data set of 2001 tooth segments from panoramic radiographs, a custom-made 7-layer deep neural network, parameterized by a total number of 4,299,651 weights, was trained and validated via 10 times repeated group shuffling. Hyperparameters were tuned using a grid search. Our reference test was the majority vote of 6 independent examiners who detected ALs on an ordinal scale (0, no AL; 1, widened periodontal ligament, uncertain AL; 2, clearly detectable lesion, certain AL). Metrics were the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and positive/negative predictive values. Subgroup analysis for tooth types was performed, and different margins of agreement of the reference test were applied (base case: 2; sensitivity analysis: 6).

RESULTS

The mean (standard deviation) tooth level prevalence of both uncertain and certain ALs was 0.16 (0.03) in the base case. The AUC of the CNN was 0.85 (0.04). Sensitivity and specificity were 0.65 (0.12) and 0.87 (0.04,) respectively. The resulting positive predictive value was 0.49 (0.10), and the negative predictive value was 0.93 (0.03). In molars, sensitivity was significantly higher than in other tooth types, whereas specificity was lower. When only certain ALs were assessed, the AUC was 0.89 (0.04). Increasing the margin of agreement to 6 significantly increased the AUC to 0.95 (0.02), mainly because the sensitivity increased to 0.74 (0.19).

CONCLUSIONS

A moderately deep CNN trained on a limited amount of image data showed satisfying discriminatory ability to detect ALs on panoramic radiographs.