Detection Of Periapical Lesions Research Articles

Artificial intelligence and dental panoramic radiographs: where are we now?

Bielefeld Academic Search Engine (BASE), Google Scholar Association for Computing Machinery: Guide to Computing Literature (ACM) and National Library of Medicine: PubMed databases were searched for systematic reviews. This study addressed a structured PICO question (Population, Intervention, Comparison, Outcome). Population was panoramic radiographs in human subjects. Intervention was use of artificial intelligence (AI) diagnostics, compared to human-only diagnosis. Quantitative or qualitative AI efficiency was the outcome. Systematic reviews were considered if they stated 'systematic review' in their title or abstract, were published in English and were not bound by a certain time frame. No supplemental primary studies were included. Screening and removal of duplicates were performed using the Rayyan tool. Data were extracted from each systematic review by two authors, with a third author having the deciding vote in cases of inconsistency. Cohen's Kappa co-efficient was used to measure reliability between authors, resulting in almost perfect agreement. The risk of bias was accounted for using the ROBIS method which resulted in one paper being rejected, so only 11 included in results. Data were then grouped into seven domains which were detected by AI: teeth identification and numbering, detection of periapical lesions, periodontal bone loss, osteoporosis, maxillary sinusitis, dental caries, and other tasks. The effectiveness of the AI systems was assessed by various outcome metrics - accuracy, sensitivity, specificity, and precision being the most common variables. Results of this overview show a significant increase in accuracy of AI in analysing OPTs between 1988-2023. Latest AI models are most accurate in teeth identification and numbering (93.67%) whilst caries detection and osteoporosis showed 91.5% and 89.29% accuracy, respectively. Accurate results were also observed for the detection of maxillary sinusitis and periodontal bone loss. However, given the heterogeneity of source studies used in these systematic reviews, results should be interpreted with caution. With improving AI technology, its use in dental radiology can be increasingly effective in supporting dentists in the detection of different pathologies. This overview has shown that systematic reviews of AI can quickly become outdated and that results of any systematic review should be treated with caution as this field advances. As such, regular updating and ongoing research is required.

Uncertainty-based Active Learning by Bayesian U-Net for Multi-label Cone-beam CT Segmentation

IntroductionTraining of Artificial Intelligence (AI) for biomedical image analysis depends on large annotated datasets. This study assessed the efficacy of Active Learning (AL) strategies training AI models for accurate multilabel segmentation and detection of periapical lesions in cone-beam CTs (CBCTs) using a limited dataset. MethodsLimited field-of-view CBCT volumes (n = 20) were segmented by clinicians (clinician segmentation [CS]) and Bayesian U-Net-based AL strategies. Two AL functions, Bayesian Active Learning by Disagreement [BALD] and Max_Entropy [ME], were used for multilabel segmentation (“Lesion”-“Tooth Structure”-“Bone”-“Restorative Materials”-“Background”), and compared to a non-AL benchmark Bayesian U-Net function. The training-to-testing set ratio was 4:1. Comparisons between the AL and Bayesian U-Net functions versus CS were made by evaluating the segmentation accuracy with the Dice indices and lesion detection accuracy. The Kruskal-Wallis test was used to assess statistically significant differences. ResultsThe final training set contained 26 images. After 8 AL iterations, lesion detection sensitivity was 84.0% for BALD, 76.0% for ME, and 32.0% for Bayesian U-Net, which was significantly different (P < .0001; H = 16.989). The mean Dice index for all labels was 0.680 ± 0.155 for Bayesian U-Net and 0.703 ± 0.166 for ME after eight AL iterations, compared to 0.601 ± 0.267 for Bayesian U-Net over the mean of all iterations. The Dice index for “Lesion” was 0.504 for BALD and 0.501 for ME after 8 AL iterations, and at a maximum 0.288 for Bayesian U-Net. ConclusionsBoth AL strategies based on uncertainty quantification from Bayesian U-Net BALD, and ME, provided improved segmentation and lesion detection accuracy for CBCTs. AL may contribute to reducing extensive labeling needs for training AI algorithms for biomedical image analysis in dentistry.

Applications of artificial intelligence in the analysis of dental panoramic radiographs: an overview of systematic reviews.

This overview of systematic reviews aimed to establish the current state of knowledge on the suitability of artificial intelligence (AI) in dental panoramic radiograph analysis and illustrate its changes over time. Medical databases covered by the Association for Computing Machinery, Bielefeld Academic Search Engine, Google Scholar, and PubMed engines were searched. The risk of bias was assessed using ROBIS tool. Ultimately, 12 articles were qualified for the qualitative synthesis. The results were visualized with timelines, tables, and charts. In the years 1988-2023, a significant development of information technologies for the analysis of DPRs was observed. The latest analyzed AI models achieve high accuracy in detecting caries (91.5%), osteoporosis (89.29%), maxillary sinusitis (87.5%), periodontal bone loss (93.09%), and teeth identification and numbering (93.67%). The detection of periapical lesions is also characterized by high sensitivity (99.95%) and specificity (92%). However, due to the small number of heterogeneous source studies synthesized in systematic reviews, the results of this overview should be interpreted with caution. Currently, AI applications can significantly support dentists in dental panoramic radiograph analysis. As systematic reviews on AI become outdated quickly, their regular updating is recommended. PROSPERO registration number: CRD42023416048.

Detection of Periapical Lesions on Panoramic Radiographs Using Deep Learning

Dentists could fail to notice periapical lesions (PLs) while examining panoramic radiographs. Accordingly, this study aimed to develop an artificial intelligence (AI) designed to address this problem. Materials and methods: a total of 18618 periapical root areas (PRA) on 713 panoramic radiographs were annotated and classified as having or not having PLs. An AI model consisting of two convolutional neural networks (CNNs), a detector and a classifier, was trained on the images. The detector localized PRAs using a bounding-box-based object detection model, while the classifier classified the extracted PRAs as PL or not-PL using a fine-tuned CNN. The classifier was trained and validated on a balanced subset of the original dataset that included 3249 PRAs, and tested on 707 PRAs. Results: the detector achieved an average precision of 74.95%, while the classifier accuracy, sensitivity and specificity were 84%, 81% and 86%, respectively. When integrating both detection and classification models, the proposed method accuracy, sensitivity, and specificity were 84.6%, 72.2%, and 85.6%, respectively. Conclusion: a two-stage CNN model consisting of a detector and a classifier can successfully detect periapical lesions on panoramic radiographs.

Calibration improves observer reliability in detecting periapical pathology on panoramic radiographs

Objective To determine whether calibration improves observer reliability when assessing DMFT-score, root-filled teeth and periapical lesions on panoramic radiographs. Material and methods A sample of 100 panoramic radiographs was selected from a cohort of myocardial infarction patients (n = 797) and matched controls (n = 796). The following variables were assessed: DMFT-score, remaining teeth, root-filled teeth and periapical lesions. Two specialists, an endodontist and a radiologist, served as reference examiners and undertook two separate assessments. Disagreement cases were jointly assessed and the final results were used as the reference standard. Three observers undertook three separate assessments, the first without prior training, the second after calibration against the reference standard and the third with the sample concealed in the complete material. Statistical analysis was made with Wilcoxon Signed rank test and Sign test. Agreement was calculated as Intraclass Correlation Coefficient (ICC) (95% CI) and Weighted Kappa (κ) (95% CI). Results Periapical lesions disclosed high inter-observer variability for the reference examiners and diverged significantly between the observers and the reference standard. For the reference examiners, inter-observer agreement was κ = 0.53. The observers, in their first assessments had κ values ranging from 0.22 to 0.60 in relation to the reference standard. Following calibration, the κ values increased, ranging from 0.59 to 0.80. For the third assessment, the κ values ranged from 0.54 to 0.75. DMFT-score, remaining teeth and root-filled teeth disclosed high reliability throughout all assessments (ICC = 0.88-0.98 and κ = 0.98–0.99). Conclusions DMFT-score, remaining teeth and root-filled teeth can be reliably assessed on panoramic radiographs. Calibration against a reference standard improves observer reliability in the detection of periapical lesions.

Two-dimensional Periapical, Panoramic Radiography Versus Three-dimensional Cone-beam Computed Tomography in the Detection of Periapical Lesion After Endodontic Treatment: A Systematic Review.

Radiographic imaging is a common resource for endodontic diagnosis, treatment, and prognosis. Two-dimensional (2D) periapical and digital panoramic radiographs often showed image distortion; this issue was resolved with the emergence of three-dimensional (3D) cone-beam computed tomography (CBCT). This review examines the accuracy of various radiographic techniques in the assessment of periapical lesion after endodontic treatment. Our goal was to determine whether a 2D radiograph (periapical and panoramic) is as accurate as a 3D radiograph (i.e., CBCT) in the assessment of periapical lesion after endodontic treatment. We searched the electronic databases Medline and Cochrane and trial registries for ongoing trials. We included both retrospective and prospective studies comparing the efficacy of periapical healing with various radiographic techniques after endodontic treatment. The outcome of interest was the percentage detection of periapical lesions and periapical healing assessment after endodontic treatment. All data were collected using a specially designed extraction form. We assessed the risk of bias in the studies using the Cochrane tool for diagnostic tests (QUADAS). We judged two studies to be at low risk and two to be at moderate risk of bias. Although there was a difference in the percentage detection of periapical healing efficacy by various radiographic techniques, all studies reported that CBCT had higher accuracy in the detection of periapical lesions compared to periapical and panoramic radiography. The next best choice is periapical radiographs, followed by panoramic radiographs as they provide better visualization and accuracy.

Digital Orthopantomography vs Cone Beam Computed Tomography—Part 1: Detection of Periapical Lesions

Digital orthopantomography (OPT) is usually the first examination step in supervising an incoming patient. Cone beam computed tomography (CBCT) is the most refined and affordable method to search for different dental lesions. The aim of this paper is to evaluate the effectiveness of OPT and CBCT in detecting periapical lesions in different dental groups. An OPT and a CBCT scan of the dental arches of 45 patients were examined. The presence of AP was pointed out for OPT and CBCT. Sensitivity, specificity, predictive values, and accuracy were calculated for OPT, using CBCT as the reference standard. OPT showed low sensitivity (40.0), positive predictive value (90.4), negative predictive value (90.0), accuracy (90.0), and high specificity (99.2). It was found to have higher sensitivity in the lower front and premolar areas, while the lowest was found in the upper molar area. OPT can be used for endodontic diagnosis in the lower central and premolar sections, but CBCT plays a decisive role in the evaluation of molar areas and in the endodontic treatment planning, when a close relationship between apex and important anatomical structures exists. CBCT exposes the patient to higher doses of radiations when compared with OPT, but CBCT, with its more selective sensitivity and the possibility to offer a three-dimensional (3D) rendering of dental and periodontal structures, is an elective choice for uncertain cases and for specific dental areas.

Efficacy of Cone Beam Computed Tomography (CBCT) and Periapical (PA) Radiography in Endodontic Diagnosis and Treatment Planning

Aim: The benefits and limitations of cone beam computed tomography (CBCT) over conventional periapical (PA) radiographs have been studied by many authors since many years ago. The subtle point of negotiation is to understand to what extent the use of CBCT over periapical can have a positive influence on initial radiographic diagnosis in different dental specialties in last recent researches. This article research was achieved by identifying which modality is superior in diagnostic accuracy and outlining what can affect the efficacy of CBCT and PA radiography in the assessment of early periapical lesions, vertical root fractures and bone defects respectively. Material and Methods: A retrospective study was conducted with the use of two different electronic databases were search between years 2006–2017, PubMed Central® (PMC), and ProQuest, with a strict inclusion and exclusion criteria. Search was limited to English and articles that compared CBCT to PA radiography with the inclusion of the factors studied. The search strategy included a self made formula for the insertion of keywords into the search engine. Formula was to either enter one radiographic technique followed by the factor being studied, or two radiographic techniques followed by one factor being studied. Articles that appeared in more than one database were considered as duplicates and were only considered once. Two examiners (Hassan Al Basri (HAB) and Mohhamed Fadhul (MF)) searched for the articles on the search engines. HB was assigned to search in PubMed, while MF explored ProQuest. A total of 262 title/abstracts were identified through the data base search engines. Most of the articles were found on PubMed (n = 189) while the other were identified on ProQuest (n = 173). Relevant articles by title/abstract were all recorded and categorized according to the relevance to the factor being studied as shown in the results (n = 107). Results: The total number of articles were categorized according to the factor being studied (n = 39) to end up with (n = 15) for periapical lesions, (n = 13) for vertical root fracture and (n = 11) for bone defects. Each category had its own table for analysis and data recording as shown in tables and diagrams. The 13 out of 15 articles concluded that CBCT is superior to PA radiography in, while the rest (n = 2) concluded that no difference was seen between the two modalities in the detection of periapical lesions. 10 out of 13 articles for vertical root fracture and 5 out of 11 in bone defects also concluded that CBCT is superior to PA in the detection of each factor respectively. Pie charts were used to illustrate these differences. Conclusion: The main findings of this study demonstrate that with in all three factors studied, the majority of studies emphasized that CBCT was superior to periapical radiography. Despite the limitations of the review conducted, evidence suggests that cone beam computed tomography is superior to periapical radiography in image quality and diagnostic. However, it can be concluded that the specifications like field of view and voxel size affect the quality of CBCT images and therefore can affect its ability to detect periapical lesions, vertical root fractures and bone defects when compared to periapical radiographs. However, dental clinicians should be cautious with further search regarding the radiation dose of CBCT.

Application of cone beam computed tomography for detection of periapical lesions – clinical case

Application of cone beam computed tomography for detection of periapical lesions – clinical case

Cone-beam Computed Tomography Uses in Clinical Endodontics: Observer Variability in Detecting Periapical Lesions

IntroductionThe accurate interpretation of a cone-beam computed tomographic (CBCT) volume is critical in identifying the presence of disease correctly and consistently. The aim of this clinical study was to determine the effect of experience level on the detection of periapical lesions in CBCT volumes. MethodsCBCT volumes of 22 maxillary molars were interpreted by 3 endodontic faculty, 3 endodontic residents, and 3 dental students. These groups were compared with the consensus opinion of 2 experienced oral and maxillofacial radiologists. The observers determined the presence or absence of apical radiolucencies for each root using a 5-point Likert scale. ResultsCompared with the radiologists, the average weighted kappa value for endodontic faculty was 0.49, for endodontic residents it was 0.35 and for dental students it was 0.32. Intrarater reliability for each group showed endodontic faculty having the highest average weighted kappa value of 0.68 followed by endodontic residents (0.48) and dental students (0.28). ConclusionsClinicians' experience level appears to be correlated with their ability to correctly diagnose periapical disease in CBCT volumes. In addition, experience leads to better inter-rater reliability. In neither of these 2 categories was agreement found to be excellent, suggesting that more can be done to improve the CBCT interpretation skills of clinicians at various levels of experience.

Comparison of diagnostic accuracy of conventional radiography, digital radiography, and ultrasound imaging in the detection of periapical lesions

Introduction: Accurate diagnosis of periapical lesions may be necessary not only to predict the treatment outcome but also to decrease the incidence of root canal treatment failure. Ultrasound imaging is an easy, reproducible technique, which is based on the evaluation of reflected echoes and has the potential to differentiate the periapical lesions. Aim: To compare the diagnostic accuracy of conventional radiography, digital radiography, and ultrasound imaging in the detection of periapical lesions. Materials and Methods: Thirty patients aged between 20 and 40 years, presenting with well-defined periapical radiolucencies in relation to anterior maxillary or mandibular teeth, indicated for extraction or periapical surgery were subjected to conventional and digital radiographic examination by paralleling technique followed by ultrasonological examination. Three observers (A, B, C) gave their radiographic diagnosis twice at an interval of 2 weeks. A sonologist assessed the size, contents, echogenicity and vascular content of the lesions. The diagnosis was compared with histopathological examination of tissues obtained by extraction or periapical surgery. Results: The diagnostic accuracy of ultrasound imaging was 83.33%, which was higher than conventional radiographic examination by all observers (53.33-76.66%) and digital radiographs by observers A and B (70-80%). Conclusion: Our study revealed that ultrasound with color Doppler was an efficient tool for diagnosing periapical lesions as it had better diagnostic accuracy than conventional and digital radiography.

Comparison of cone beam computed tomography and intra oral periapical radiography in detecting periapical lesions –A systematic review

Introduction: Cone-beam computerized tomography (CBCT) is a medical image acquisition technique based on a cone-shaped X-ray beam centered on a two-dimensional (2D) detector. The source-detector system performs one rotation around the object producing a series of 2D images. The images are reconstructed in a three-dimensional (3D) data set using a modification of the original cone-beam algorithm developed by Feldkamp 1 et al in 1984. This technique is widely used in different industrial and biomedical applications such as micro- CT. Among the first clinical applications were single photon emission computerized tomography (SPECT), angiography and image-guided radiotherapy. Dedicated cone-beam computerized tomography scanners for the oral and maxillofacial (OMF) region were pioneered in the late 1990s independently by Arai 2 et al. in Japan. This Systematic review aims at comparing cone -beam computerized tomography and periapical radiography in detection of periapical lesion. Objective: To compare the accuracy of cone beam computed tomography (CBCT) and intra oral periapical radiography (IOPA) in diagnosis of periapical pathology Search Strategy: Database such as Pub med Central and Medline were searched for the related topics from February 1996 till July 2013. Selection Criteria: Trials were selected if they met the following criteria: Clinical trials comparing the accuracy of Cone beam computed tomography (CBCT) and intra oral periapical radiography (IOPA). Data Collection and Analysis: All the studies included were based on the data extraction and analysis of the studies for quality and publication bias. The data collection form was customized. The primary outcome is to compare Cone beam computed tomography (CBCT) and intra oral periapical radiography (IOPA) in detection of periapical lesions. Main Results: The review concluded that cone beam computed tomography is superior to conventional intra oral periapical radiography in detection of periapical lesions. Conclusion: The probability of detecting periapical lesions was more in case of cone-beam computerized tomography when compared to conventional intra oral periapical radiography where external factors such as anatomical noise and poor irradiation geometry which are not in operators control are eliminated. I. Background Traditionally, the diagnosis of periapical lesion was based on clinical and radiographic presentations; confirmatory diagnosis was only by a biopsy which was highly impossible in the case of a non surgical procedure. If biopsy is taken the treatment is no longer a non surgical procedure (Simon et al 1980)

Cone Beam Computed Tomography Evaluation of the Diagnosis, Treatment Planning, and Long-Term Followup of Large Periapical Lesions Treated by Endodontic Surgery: Two Case Reports

The aim of this case report is to present two cases where cone beam computed tomography (CBCT) was used for the diagnosis, treatment planning, and followup of large periapical lesions in relation to maxillary anterior teeth treated by endodontic surgery. Periapical disease may be detected sooner using CBCT, and their true size, extent, nature, and position can be assessed. It allows clinician to select the most relevant views of the area of interest resulting in improved detection of periapical lesions. CBCT scan may provide a better, more accurate, and faster method to differentially diagnose a solid (granuloma) from a fluid-filled lesion or cavity (cyst). In the present case report, endodontic treatment was performed for both the cases followed by endodontic surgery. Biopsy was done to establish the confirmatory histopathological diagnosis of the periapical lesions. Long-term assessment of the periapical healing following surgery was done in all the three dimensions using CBCT and was found to be more accurate than IOPA radiography. It was concluded that CBCT was a useful modality in making the diagnosis and treatment plan and assessing the outcome of endodontic surgery for large periapical lesions.

Comparison of two imaging systems in the detection of periapical lesions: Periapical vs CBCT

Comparison of two imaging systems in the detection of periapical lesions: Periapical vs CBCT

In Vitro, Comparison of the Diagnostic Efficacy of Conventional and Digital Imaging in the Detection of Periapical Lesions

In Vitro, Comparison of the Diagnostic Efficacy of Conventional and Digital Imaging in the Detection of Periapical Lesions

RadioVisiography in the Detection of Periapical Lesions

The periapical areas of 16 teeth from 6 human mandibular jaw specimens were randomly examined by 3 observers using conventional radiography with Kodak E-speed film and radiovisiography (with variable contrast and with fixed contrast). Each periapical area was examined preoperatively and after #2, #4, #6, and #8 sized bur periapical lesions were created in the cortical bone. The three radiographic methods were compared by repeated-measures ANOVA of the accuracy scores for the 16 periapical lesions. Accuracy increased with size of lesion, but did not vary by method. Repeated-measures ANOVA of the accuracy scores of only the smallest and no lesion condition showed that conventional radiography and radiovisiography (variable contrast) have opposite strengths. Conventional radiography tended to be more accurate in the no lesion condition, whereas radiovisiography using variable contrast was somewhat more accurate in the smallest lesion condition. The accuracy of radiovisiography with fixed contrast was not significantly different from the other two methods.