Diagnostic Accuracy of Cone-beam Computed Tomography and Conventional Radiography on Apical Periodontitis: A Systematic Review and Meta-analysis

Healing of apical periodontitis in type II diabetes mellitus patients: A prospective study

OBJECTIVE

This study aimed to compare the healing of periapical bone between type II diabetes patients and healthy patients after root canal treatment.

SUBJECTS AND METHODS

This study included 26 diabetic patients and the control group with healthy patients matching the diabetic group in age and sex. The study included only teeth with satisfactory coronal restoration. The periapical index system was used to evaluate the periapical status of treated teeth at follow-ups after 6 and 12 months.

RESULTS

Analysis of the results revealed a significantly higher healing rate in the control group compared to the diabetic group only at the 6-month follow-up (66.6 vs. 33.3%; Χ2 = 4.857; p = 0.0275). Analysis of the full-scale PAI index disclosed significantly higher PAI values in the diabetic subjects at 6- and 12-month follow-up. The regression analysis showed that the risk of apical periodontitis persistence increased significantly with female gender (OR = 3.92; 95% CI = 1.04-14.79; p = 0.043), diabetes mellitus (OR = 4.27; 95% CI: 1.18-15.50; p = 0.027) and higher household income (OR = 5.39; 95% CI = 1.33-21.89; p = 0.018).

CONCLUSION

Root canal treatment remains an effective means of conservative treatment in diabetic patients. While the healing is not compromised, regular follow-ups are necessary to monitor the healing process.

Impact of passive ultrasonic irrigation on the outcome of non-surgical root canal treatment: a systematic review and meta-analysis of randomized clinical trials

OBJECTIVE

This systematic review aimed to assess the impact of Passive Ultrasonic Irrigation on the periapical healing rate of primary root canal treatment compared to conventional syringe irrigation.

METHODS

Registered a priori in the PROSPERO database, this review was conducted by two independent reviewers who performed an electronic search up to December 2023. The search included databases such as MEDLINE (PubMed), Scopus, Web of Science, Embase, LILACS, and the Cochrane Library, as well as grey literature. We included randomized clinical trials (RCTs) that focused on patients undergoing primary root canal treatments. The study compared intervention groups using PUI with control groups that did not use activation techniques. Periapical healing was assessed over follow-up periods of at least six months, utilizing either periapical radiographs or cone-beam computed tomography. To synthesize the findings, a meta-analysis and trial sequence analysis were conducted, employing the Relative Risk as the measure of effect, with a 95% confidence interval. The GRADE approach was utilized to assess the certainty of the evidence.

RESULTS

The meta-analysis incorporated three RCTs, involving 474 patients (501 teeth). The analysis revealed that PUI led to a higher rate of periapical healing compared to CSI (Relative Risk: 1.10; 95% Confidence Interval: 1.01-1.21, I² = 0%), with moderate certainty of evidence.

CONCLUSIONS

Despite the limited number of high-quality RCTs, the findings showed a positive impact of PUI on periapical healing rates in primary root canal treatments, in comparison to CSI.

REGISTER

CRD42021290894.

Improved soft-tissue visibility on cone-beam computed tomography with an image-generating artificial intelligence model using a cyclic generative adversarial network

OBJECTIVES

The objective of this study was to enhance the visibility of soft tissues on cone-beam computed tomography (CBCT) using a CycleGAN network trained on CT images.

METHODS

Training and evaluation of the CycleGAN were conducted using CT and CBCT images collected from Aichi Gakuin University (α facility) and Osaka Dental University (β facility). Synthesized images (sCBCT) output by the CycleGAN network were evaluated by comparing them with the original images (oCBCT) and CT images, and assessments were made using histogram analysis and human scoring of soft-tissue anatomical structures and cystic lesions.

RESULTS

The histogram analysis showed that on sCBCT, soft-tissue anatomical structures showed significant shifts in voxel intensity toward values resembling those on CT, with the mean values for all structures approaching those of CT and the specialists' visibility scores being significantly increased. However, improvement in the visibility of cystic lesions was limited.

CONCLUSIONS

Image synthesis using CycleGAN significantly improved the visibility of soft tissue on CBCT, with this improvement being particularly notable from the submandibular region to the floor of the mouth. Although the effect on the visibility of cystic lesions was limited, there is potential for further improvement through refinement of the training method.

Classification of Caries Based on CBCT: A Deep Learning Network Interpretability Study

This study aimed to create a caries classification scheme based on cone-beam computed tomography (CBCT) and develop two deep learning models to improve caries classification accuracy. A total of 2713 axial slices were obtained from CBCT images of 204 carious teeth. Both classification models were trained and tested using the same pretrained classification networks on the dataset, including ResNet50_vd, MobileNetV3_large_ssld, and ResNet50_vd_ssld. The first model was used directly to classify the original images (direct classification model). The second model incorporated a presegmentation step for interpretation (interpretable classification model). Performance evaluation metrics including accuracy, precision, recall, and F1 score were calculated. The Local Interpretable Model-agnostic Explanations (LIME) method was employed to elucidate the decision-making process of the two models. In addition, a minimum distance between caries and pulp was introduced for determining the treatment strategies for type II carious teeth. The direct model that utilized the ResNet50_vd_ssld network achieved top accuracy, precision, recall, and F1 score of 0.700, 0.786, 0.606, and 0.616, respectively. Conversely, the interpretable model consistently yielded metrics surpassing 0.917, irrespective of the network employed. The LIME algorithm confirmed the interpretability of the classification models by identifying key image features for caries classification. Evaluation of treatment strategies for type II carious teeth revealed a significant negative correlation (p < 0.01) with the minimum distance. These results demonstrated that the CBCT-based caries classification scheme and the two classification models appeared to be acceptable tools for the diagnosis and categorization of dental caries.

Treatment opinions for dens invaginatus: A case series

Dens invaginatus (DI) is a rare congenital dental malformation characterized by enamel or cementum folded into dentine. Such teeth are susceptible to caries, pulp infection or necrosis and periradicular lesion. The complex anatomy of this disease results in difficult treatment and a high rate of therapeutic failure. Therapeutic options, such as debriding and filling invagination, root canal treatment (RCT) and intentional replantation, vary according to the morphology and infection of the involved tooth. The present study reports five cases of DI with chronic apical periodontitis. The treatment strategies and procedures, including RCT, removing the invagination, intentional replantation and surgical treatment, are discussed according to the classification and the condition of pulp and periapical tissue. The study also reports the prognosis: All patients were followed up for ≥12 months and all teeth demonstrated periapical healing and clinical asymptomatic. In summary, appropriate treatment is based on accurate analysis of the anatomical variation in different types of DI and intentional replantation is a reliable and viable treatment to preserve the tooth.

The outcome of combined use of iRoot BP Plus and iRoot SP for root-end filling in endodontic microsurgery: a randomized controlled trial

OBJECTIVES

Root-end filling is important for the clinical outcome of endodontic microsurgery. Our previous study showed that combined application of iRoot BP Plus Root Repair Material (BP-RRM) and iRoot SP Injectable Root Canal Sealer (SP-RCS) in root-end filling exhibited better apical sealing as compared to the application of BP-RRM alone. The aim of this randomized controlled clinical trial was to evaluate the effect of the combined use of BP-RRM and SP-RCS on the prognosis of teeth with refractory periapical diseases after endodontic microsurgery.

MATERIALS AND METHODS

240 teeth with refractory periapical diseases scheduled for endodontic microsurgery were randomly divided into BP-RRM/SP-RCS group (n = 120) and BP-RRM group (n = 120). The patients were followed up at 3 months, 6 months, and 12 months after endodontic microsurgery. Pre- and post-operative clinical and radiographic examinations were performed to evaluate the treatment outcome. The 1-year success rate of endodontic microsurgery in BP-RRM/SP-RCS and BP-RRM groups was compared by Chi-square test. Factors that might impact the prognosis were further analyzed using Chi-square test or Fisher's exact test.

RESULTS

A total of 221 teeth completed the 12-month follow-up. The 1-year success rates of the BP-RRM/SP-RCS and BP-RRM groups were 94.5% (104/110) and 92.8% (103/111), respectively. The combined use of BP-RRM and SP-RCS achieved a clinical outcome comparable to BP-RRM alone (P = 0.784). Tooth type (P = 0.002), through-and-through/apico-marginal lesion (P = 0.049), periodontal status (P < 0.0001), and Kim's lesion classification (P < 0.0001) were critical factors associated with the 1-year success of endodontic microsurgery.

CONCLUSIONS

The combined use of BP-RRM and SP-RCS is a practicable method for root-end filling in endodontic microsurgery with a satisfactory 1-year clinical outcome.

CLINICAL RELEVANCE

The combined application of BP-RRM and SP-RCS in EMS is an effective root-end filling method with a satisfactory 1-year clinical outcome.

TRIAL REGISTRATION

This study was registered in the Chinese Clinical Trial Registry (ChiCTR2100052174).

Endodontic treatment of a C-shaped mandibular second molar with narrow dentinal thickness: A case report

Formulating an effective root canal treatment plan necessitates clinician awareness of the complexities of the root canal system and possible anatomic challenges. The C-shaped canal variation accompanying the radicular lingual groove makes the lingual dentinal wall so thin that cleaning and shaping of canals require accurate management. This report presents endodontic treatment of a C-shaped mandibular second molar diagnosed with pulpal necrosis and asymptomatic apical periodontitis, that initial radiographic assessment revealed extremely thin (0.3 mm) width of the lingual wall of the canals prone to perforation. Mechanical preparation was performed through the anti-curvature technique and basically by chemical irrigation rather than mechanical instrumentation. The C-shaped isthmus was prepared up to 25/02 rotary system without dentinal defect while maintaining adequate dentin thickness so as to not significantly reduce the strength of the root. Follow-up radiographs showed normal periodontal ligament and lamina dura indicating significant healing of the periapical lesion.

The association of endodontic prognostic factors with the presence of periapical lesion, its volume, and bone characteristics in endodontically treated molars: a cross-sectional study

BACKGROUND

This study intended to evaluate the association between several endodontic prognostic factors with the presence of periapical lesions (PLs), their volume, and bone characteristics including cortical bone destruction (CBD) and buccal plate bone height (BPBH) in root-filled molar teeth using cone-beam computed tomography.

METHODS

A collection of 143 scans of endodontically treated maxillary/mandibular first or second molars recorded over 8 years, were obtained from a specialized radiology center. Data on prognostic factors including tooth number, gender, jaw type, the status and number of missed canals, obturation length, restoration type, presence of a separated instrument, presence of a post or screw in the canals, and presence of perforation were collected. The assessed outcomes included PL presence, PL volume, CBD, and BPBH. The association between prognostic factors and outcomes was evaluated using multiple logistic regression models with adjusted covariates and multifactorial ANOVA at a significance level of 0.05.

RESULTS

A total of 282 molars from 82 women and 50 men with a mean age of 40.6 ± 12.27 were included. Among those, 139 teeth presented PL with a mean volume of 18.68 mm3. CBD was prevalent in 137 teeth and the mean BPBH appeared to be 9.45 mm. The presence of a missed canal (OR = 10.022, P < .05), underfilled canal (OR = 3.725, P < .05), overfilled canal (OR = 15.859, P = .018), and perforation (OR = 15.261, P = .013) was significantly associated with PLs. None of the prognostic factors could considerably contribute to the CBD (P > .05). The presence of a missed canal was positively associated with the PL volume (P < .05). Similarly, missed canals (P < .05), perforation (P < .05), and separated instruments (P = .004) were associated with a significantly reduced BPBH.

CONCLUSIONS

Overfillings, perforations, missed canals, and underfillings were identified as remarkable predictors of PL, arranged in descending order of their respective impact. The only factor capable of significantly increasing the PL volume was the missed canal. In brief, obturation length errors, perforations, missed canals, and separated instruments were robustly correlated with endodontic failure, which highlights the importance of mitigating the potential for errors by following the fundamentals of endodontics.

Evaluating a Periapical Lesion Detection CNN on a Clinically Representative CBCT Dataset-A Validation Study

The aim of this validation study was to comprehensively evaluate the performance and generalization capability of a deep learning-based periapical lesion detection algorithm on a clinically representative cone-beam computed tomography (CBCT) dataset and test for non-inferiority. The evaluation involved 195 CBCT images of adult upper and lower jaws, where sensitivity and specificity metrics were calculated for all teeth, stratified by jaw, and stratified by tooth type. Furthermore, each lesion was assigned a periapical index score based on its size to enable a score-based evaluation. Non-inferiority tests were conducted with proportions of 90% for sensitivity and 82% for specificity. The algorithm achieved an overall sensitivity of 86.7% and a specificity of 84.3%. The non-inferiority test indicated the rejection of the null hypothesis for specificity but not for sensitivity. However, when excluding lesions with a periapical index score of one (i.e., very small lesions), the sensitivity improved to 90.4%. Despite the challenges posed by the dataset, the algorithm demonstrated promising results. Nevertheless, further improvements are needed to enhance the algorithm's robustness, particularly in detecting very small lesions and the handling of artifacts and outliers commonly encountered in real-world clinical scenarios.

Association between rheumatoid arthritis and pulpal-periapical pathology: a systematic review

OBJECTIVES

Rheumatoid arthritis (RA) is a debilitating disease where numerous pro-inflammatory cytokines have a proven role in its pathology. These cytokines are also involved in the pathogenesis of apical periodontitis (AP) where they have a pro-inflammatory role and induce bone resorption. Patients with RA may therefore be more prone to develop pulpal-periapical pathology (PPP). This study systematically reviewed the existing literature evaluating the association between RA and PPP.

MATERIALS AND METHODS

Studies including human participants with both RA and PPP were included. The search was performed in PubMed, Web of Science, and The Cochrane Library databases using keywords and Medical Subject Headings (MeSH) search terms. The risk of bias was assessed using Newcastle-Ottawa Quality Assessment Scale. The following parameters were extracted and analyzed by the reviewers; author, journal, year, design of the study, diagnostic criteria for periapical pathology, the association between rheumatoid arthritis and periapical pathology, and the evidence level.

RESULTS

The search identified 142 records. Inclusion criteria were as follows; studies in the English language, including human participants only, including patients with RA and PPP, cohort studies, cross-sectional studies, clinical trials, and case-control studies. According to the inclusion criteria, 5 studies were included in this systematic review. Three of the five studies reported significant association between RA and PPP.

CONCLUSIONS

Existing evidence suggests there may be an association between RA and PPP.

CLINICAL RELEVANCE

Clinicians should be aware that RA patients can be more prone to develop PPP which may result in a reduced quality of life.

Applying artificial intelligence to detect and analyse oral and maxillofacial bone loss-A scoping review

Radiographic evaluation of bone changes is one of the main tools in the diagnosis of many oral and maxillofacial diseases. However, this approach to assessment has limitations in accuracy, inconsistency and comparatively low diagnostic efficiency. Recently, artificial intelligence (AI)-based algorithms like deep learning networks have been introduced as a solution to overcome these challenges. Based on recent studies, AI can improve the detection accuracy of an expert clinician for periapical pathology, periodontal diseases and their prognostication, as well as peri-implant bone loss. Also, AI has been successfully used to detect and diagnose oral and maxillofacial lesions with a high predictive value. This study aims to review the current evidence on artificial intelligence applications in the detection and analysis of bone loss in the oral and maxillofacial regions.

Artificial Intelligence and Its Application in Endodontics: A Review

AIM AND BACKGROUND

Artificial intelligence (AI) since it was introduced into dentistry, has become an important and valuable tool in many fields. It was applied in different specialties with different uses, for example, in diagnosis of oral cancer, periodontal disease and dental caries, and in the treatment planning and predicting the outcome of orthognathic surgeries. The aim of this comprehensive review is to report on the application and performance of AI models designed for application in the field of endodontics.

MATERIALS AND METHODS

PubMed, Web of Science, and Google Scholar were searched to collect the most relevant articles using terms, such as AI, endodontics, and dentistry. This review included 56 papers related to AI and its application in endodontics.

RESULT

The applications of AI were in detecting and diagnosing periapical lesions, assessing root fractures, working length determination, prediction for postoperative pain, studying root canal anatomy and decision-making in endodontics for retreatment. The accuracy of AI in performing these tasks can reach up to 90%.

CONCLUSION

Artificial intelligence has valuable applications in the field of modern endodontics with promising results. Larger and multicenter data sets can give external validity to the AI models.

CLINICAL SIGNIFICANCE

In the field of dentistry, AI models are specifically crafted to contribute to the diagnosis of oral diseases, ranging from common issues such as dental caries to more complex conditions like periodontal diseases and oral cancer. AI models can help in diagnosis, treatment planning, and in patient management in endodontics. Along with the modern tools like cone-beam computed tomography (CBCT), AI can be a valuable aid to the clinician. How to cite this article: Ahmed ZH, Almuharib AM, Abdulkarim AA, et al. Artificial Intelligence and Its Application in Endodontics: A Review. J Contemp Dent Pract 2023;24(11):912-917.

Non-surgical root canal treatment and retreatment versus apical surgery in treating apical periodontitis: A systematic review

BACKGROUND

In addition to non-surgical root canal treatment or retreatment, apical surgery may be carried out to manage teeth with apical periodontitis. However, it is unclear which treatment option is more effective.

OBJECTIVE

To systematically review the effectiveness of apical surgery compared with non-surgical treatment or retreatment in terms of clinical and patient-related outcomes in teeth with apical periodontitis.

METHODS

A literature search of electronic databases, the grey literature, the reference lists of included articles and previous reviews, and a hand search of leading endodontic journals, was conducted. Randomised and non-randomised control trials, and longitudinal observational studies on patients undergoing surgical (treatment group) and non-surgical root canal treatment or retreatment (control group) of teeth with apical periodontitis were included. The risk of bias was appraised using the Cochrane risk-of-bias tool; ROBINS-I and the Newcastle-Ottawa Scale.

RESULTS

Five studies, consisting of two randomised clinical trials, two non-randomised clinical trials, and a retrospective cohort study, were included. The interobserver agreement was high and kappa correlation coefficient was good. In total 529 teeth were available for follow-up that varied from 6 months to 8.7 years. The overall risk of bias was high for four studies and raised some concerns in one study. Apical surgery showed seemly better results regarding periapical healing and less need for more and further intervention, although tooth survival was higher in the control group. Given the heterogeneity of the studies, meta-analysis was not possible.

DISCUSSION

Previous systematic reviews have conducted an indirect comparison by separately pooling the outcomes of studies analysing either non-surgical, or surgical, treatment. In this systematic review, only studies that compared both treatments were included. Most results of this and previous reviews were similar.

CONCLUSION

No treatment option showed clear superiority. However, to arrive at statistically supported conclusions there is a need for additional high-quality comparative trials.

REGISTRATION

PROSPERO database (Registration number CRD42021260300).

Revolutionizing Dental Care: A Comprehensive Review of Artificial Intelligence Applications Among Various Dental Specialties

Since the beginning of recorded history, the human brain has been one of the most intriguing structures for scientists and engineers. Over the centuries, newer technologies have been developed based on principles that seek to mimic their functioning, but the creation of a machine that can think and behave like a human remains an unattainable fantasy. This idea is now known as "artificial intelligence". Dentistry has begun to experience the effects of artificial intelligence (AI). These include image enhancement for radiology, which improves the visibility of dental structures and facilitates disease diagnosis. AI has also been utilized for the identification of periapical lesions and root anatomy in endodontics, as well as for the diagnosis of periodontitis. This review is intended to provide a comprehensive overview of the use of AI in modern dentistry's numerous specialties. The relevant publications published between March 1987 and July 2023 were identified through an exhaustive search. Studies published in English were selected and included data regarding AI applications among various dental specialties. Dental practice involves more than just disease diagnosis, including correlation with clinical findings and administering treatment to patients. AI cannot replace dentists. However, a comprehensive understanding of AI concepts and techniques will be advantageous in the future. AI models for dental applications are currently being developed.

Pre-medical assessment of root-canal-filled teeth with asymptomatic apical periodontitis-A multifaceted balancing act

AIM

Prior to certain medical therapies, dental assessment and treatment of oral foci of infection are recommended. The aim of the present study was to acquire a deeper understanding of the decision-making process regarding the pre-medical management of root-canal-filled teeth with asymptomatic apical periodontitis (AAP).

METHODOLOGY

Hospital-affiliated dentists in Sweden were contacted for a semi-structured, in-depth interview. The absolute inclusion criterion was that the dentists had experienced and could recount at least two authentic cases involving root-canal-filled teeth with AAP-one case having resulted in pre-medical treatment, and one having resulted in expectancy. Fourteen interviews, with fourteen informants, were conducted and included in the study. During the interviews, open-ended questions and comments encouraging the informants to elaborate and clarify their experiences were offered. The interviews were digitally recorded, transcribed verbatim and analysed using Qualitative Content Analysis with an inductive approach.

RESULTS

A theme describing the latent content was identified through interpretation of the collected data: A multifaceted balancing act characterized by a sometimes-difficult risk-benefit-estimation, where an increased uncertainty entails an increased reliance on external opinions. Three main categories, comprising four sub-categories, describing the manifest content were recognized: The tipping scale, The team effort and The frame of reference.

CONCLUSIONS

The current interview study found pre-medical decision-making regarding root-canal-filled teeth with AAP to be a multifactorial and contextual process marked by uncertainty and collaborative measures. Further research, resulting in the development of evidence-based treatment guidelines, is suggested necessary.

The Limitations of Periapical X-ray Assessment in Endodontic Diagnosis-A Systematic Review

Diagnosis is a key aspect in endodontic treatment, in a decade where invasive interventions are misapprehended as social tendency instead of medical necessity. All diagnostic facets should be considered before intending the operative phase. Intraoral endodontic radiology-based diagnosis has been shown to be limited. Periapical X-ray is the most used endodontic imaging, yet it does not provide high accuracy. Traditionally, dentists have been trained to diagnose a cyst by certain aspects (size, shape and appearance); hence, an assumption that teeth are affected by "periapical cyst" were subjected to unnecessary extraction or apicoectomy. The aim of this systematic review is to critically appraise the publications that relate the histological diagnosis of a periapical lesion (considered the gold standard) to intraoral X-ray investigation. Ovid Medline, PubMed, ScienceDirect, Mendeley and Scopus were searched for English-language studies comparing periapical diagnosis obtained by using two techniques (histopathology and X-ray). Sixteen articles were included for the final analysis (qualitative and quantitative evaluation) out of which only two supported the statement that periapical diagnosis can be coherently assessed through periapical imaging. Although there is not enough evidence to deliver a definitive conclusion, there are many publications that refute the diagnosis of a cyst via periapical X-ray.

CBCT in contemporary endodontics

Cone-beam computed tomography (CBCT) is a three-dimensional imaging modality which can aid endodontic diagnosis and treatment planning. While there are guidelines available describing the indications, there are divergent philosophies on when this technology should be applied in clinical practice. This paper reviews the applications of CBCT including the clinical relevance of parameters which can be assessed, highlights the limitations of this technology, and provides guidance on how to maximise its clinical utility.

Evaluation of histogram equalization and contrast limited adaptive histogram equalization effect on image quality and fractal dimensions of digital periapical radiographs

OBJECTIVES

This study aims to evaluate the effects of histogram equalization (HE) and contrast limited adaptive histogram equalization (CLAHE) on periapical images and fractal dimensions in the periapical region.

METHODS

In this cross-sectional study, digital periapical images were selected from the archive of Dentistry School of Isfahan University of Medical Sciences. The radiographs were taken from mandibular and maxillary anterior single root teeth with healthy root and periodontium. After applying HE and CLAHE algorithms to images, two radiologists evaluated the quality of apex detection from using a 5-point Likert scale (from 5 for very good image quality to 1 for very bad image quality). Afterward, all the images were imported to the ImageJ application, and the region of interest (ROI) was specified as the region between the two central incisors. The fractal box-counting method was used to determine fractal dimensions (FD) values. Nonparametric Wilcoxon-Friedman test, Intraclass Correlation Coefficient test, T-test, and Pair T-test were performed as statistical analysis (α = 0.05).

RESULTS

Fifty-three radiographs were analyzed and the image quality assessments were significantly different between raw images and images after performing HE, CLAHE (p value < 0.001), and using CLAHE algorithm significantly increases image quality assessments more than HE (p value = 0.009). There was a significant difference in FD values for images after applying CLAHE and HE compared to raw images (p value < 0.001), and HE decreased the FD value significantly more than CLAHE (p value = 0.019).

CONCLUSIONS

Employing CLAHE and HE algorithm via OpenCV python library improves the periapical image quality, which is more significant using the CLAHE algorithm. Moreover, applying CLAHE and HE reduces trabecular bone structure detection and FD values in periapical images, especially in HE.

Dental MRI-only a future vision or standard of care? A literature review on current indications and applications of MRI in dentistry

MRI is increasingly used as a diagnostic tool for visualising the dentoalveolar complex. A comprehensive review of the current indications and applications of MRI in the dental specialities of orthodontics (I), endodontics (II), prosthodontics (III), periodontics (IV), and oral surgery (V), pediatric dentistry (VI), operative dentistry is still missing and is therefore provided by the present work.The current literature on dental MRI shows that it is used for cephalometry in orthodontics and dentofacial orthopaedics, detection of dental pulp inflammation, characterisation of periapical and marginal periodontal pathologies of teeth, caries detection, and identification of the inferior alveolar nerve, impacted teeth and dentofacial anatomy for dental implant planning, respectively. Specific protocols regarding the miniature anatomy of the dentofacial complex, the presence of hard tissues, and foreign body restorations are used along with dedicated coils for the improved image quality of the facial skull.Dental MRI poses a clinically useful radiation-free imaging tool for visualising the dentoalveolar complex across dental specialities when respecting the indications and limitations.

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.

Deep Learning for Detection of Periapical Radiolucent Lesions: A Systematic Review and Meta-analysis of Diagnostic Test Accuracy

INTRODUCTION

The aim of this systematic review and meta-analysis was to investigate the overall accuracy of deep learning models in detecting periapical (PA) radiolucent lesions in dental radiographs, when compared to expert clinicians.

METHODS

Electronic databases of Medline (via PubMed), Embase (via Ovid), Scopus, Google Scholar, and arXiv were searched. Quality of eligible studies was assessed by using Quality Assessment and Diagnostic Accuracy Tool-2. Quantitative analyses were conducted using hierarchical logistic regression for meta-analyses on diagnostic accuracy. Subgroup analyses on different image modalities (PA radiographs, panoramic radiographs, and cone beam computed tomographic images) and on different deep learning tasks (classification, segmentation, object detection) were conducted. Certainty of evidence was assessed by using Grading of Recommendations Assessment, Development, and Evaluation system.

RESULTS

A total of 932 studies were screened. Eighteen studies were included in the systematic review, out of which 6 studies were selected for quantitative analyses. Six studies had low risk of bias. Twelve studies had risk of bias. Pooled sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, and diagnostic odds ratio of included studies (all image modalities; all tasks) were 0.925 (95% confidence interval [CI], 0.862-0.960), 0.852 (95% CI, 0.810-0.885), 6.261 (95% CI, 4.717-8.311), 0.087 (95% CI, 0.045-0.168), and 71.692 (95% CI, 29.957-171.565), respectively. No publication bias was detected (Egger's test, P = .82). Grading of Recommendations Assessment, Development and Evaluationshowed a "high" certainty of evidence for the studies included in the meta-analyses.

CONCLUSION

Compared to expert clinicians, deep learning showed highly accurate results in detecting PA radiolucent lesions in dental radiographs. Most studies had risk of bias. There was a lack of prospective studies.

Volumetric Assessment of Apical Periodontitis Using Cone-Beam Computed Tomography-A Systematic Review

This systematic review aimed to investigate the scientific literature on volumetric studies concerning the diagnosis and treatment of apical periodontitis using CBCT. A systematic review protocol was written following the preferred reporting items for the systematic reviews and meta-analyses (PRISMA) checklist. Four electronic databases were searched for relevant publications in English, which were published up to 21 January 2023. The inclusion criteria and corresponding search keys were applied. The risk of bias was assessed using the Joanna Briggs Institute Meta-Analysis of Statistic Assessment and Review Instrument. The search strategy identified 202 studies, with 123 studies excluded during the title and abstract screening and 47 studies left for full text screening. A total of 17 studies met the inclusion criteria. The lesion volume was measured and classified according to different indices which compared the effectiveness of their diagnostics. Moreover, the volume of AP lesions increased with the thickness of the maxillary sinus mucosa in primary and secondary infections and decreased due to endodontic treatment. Volumetric measurements using CBCT are useful in the correct definition of periapical tissue pathosis using a CBCT periapical volume index and assessment of the dynamics of the treatment of apical lesions.

Global Prevalence of Maxillary Sinusitis of Odontogenic Origin and Associated Factors: A Systematic Review and Meta-Analysis

INTRODUCTION

The overall prevalence of maxillary sinusitis of odontogenic origin (MSOO) is still unknown. Therefore, this study aimed to determine the pooled prevalence of MSOO and verify associations between different odontogenic conditions and MSOO.

METHODS

Six electronic databases and the gray literature were searched on August 25, 2022. Two independent reviewers selected observational studies reporting the prevalence of MSOO and associated conditions in adults. Studies that did not use computed tomography for diagnosis were excluded. The methodological quality of the studies was assessed using the Joanna Briggs Institute Critical Appraisal Checklist for Cross-Sectional Studies. Data were analyzed by proportion and association meta-analyses. The certainty of evidence was assessed using the Grading of Recommendations Assessment, Development and Evaluation approach.

RESULTS

Thirty-eight studies were included in the qualitative analysis and thirty-one in the meta-analyses. Only 12 studies (31.6%) fulfilled all items of the methodological quality checklist. Overall, the studies reported prevalence measures per maxillary sinus or patient. Thus, the pooled prevalence of MSOO was 51% per sinus (95% confidence interval [CI] [40%-61%]) and 50% per patient (95% CI [41%-59%]). Apical lesion (odds ratio [OR]: 4.03, 95% CI [2.26-7.19]), periodontitis (OR: 5.49, 95% CI [2.27-13.24]), moderate (OR: 2.57, 95% CI [1.85-3.57]) and severe bone loss (OR: 13.80, 95% CI [2.81-67.85] were significantly associated with MSOO. The certainty of the evidence for the associations was very low.

CONCLUSIONS

The pooled prevalence of MSOO on computed tomography assessment was 51% per maxillary sinus and 50% per patient. Therefore, half of the maxillary sinusitis may be of odontogenic origin. Apical lesion, periodontitis, and moderate and severe bone loss were significantly associated with MSOO.

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.

Clinical, radiographic characterizations and complications of maxillary molar in a periodontitis population: a retrospective study based on CBCT radiography

OBJECTIVE

This study was aimed to delineate the clinical, CBCT radiographic characteristics, and complications of maxillary molar in a periodontitis population.

MATERIALS AND METHODS

Medical records and CBCT images were utilized to identify adult patients with periodontitis in a tertiary referral dental hospital between June 2019 and December 2020. CBCT scan images were used to characterize the detailed bone thickness, absorbing height, and position of maxillary molar as well as their associated conditions. All relevant descriptive epidemiological data, clinical information, radiographic details, and associated complications were recorded and statistically analyzed.

RESULTS

According to the above criteria, 577 eligible periodontitis patients were enrolled and defined as research cohort here with mean age 45 ± 4.8 years. Male patients outnumbered females with a gender ratio of 1.23:1. Our results demonstrated that the bone loss of maxillary first molar was more serious than that of second molar with tooth position symmetry. The occurrence of various complications (periodontal abscess, pulp lesions, furcation lesion, and mucosal thickening) was significantly correlated to periodontal-related clinical parameters of maxillary molar.

CONCLUSIONS

Our results demonstrated the more serious bone loss of maxillary first molar with tooth position symmetry. The occurrence of various complications was significantly correlated to periodontal-related clinical parameters. Our findings offer valuable information concerning the clinical, radiographic characteristics, and complications of maxillary molar in a periodontitis population.

CLINICAL RELEVANCE

These findings are beneficial for clinicians to comprehensively understand the bone status, pathogenesis, and clinical management of maxillary molar in periodontitis.

Prevalence, classification and dental treatment requirements of dens invaginatus by cone-beam computed tomography

Background

This study aimed the evaluation of the prevalence, characteristics, types of dens invaginatus (DI) and co-observed dental anomalies to understand dental treatment requirements in anterior teeth that are susceptible to developmental anomalies by using cone-beam computed tomography (CBCT).

Methods

In this retrospective study, the anterior teeth of 958 patients were evaluated by using CBCT for the presence of DI. The demographic features, types of DI and treatment requirements were also recorded. The association between sex and the presence of DI was evaluated using chi-squared test.

Results

Seventy-three DI anomalies were detected in the anterior teeth of 49 patients (18 females, 31 males). The frequency of DI was 5.11% and the most frequently involved teeth were lateral (57.53%). Forty-six teeth were classified as Type I (63.01%), 24 as Type II (32.87%), and three as Type III (4.10%). Apical pathosis was found to be 20.54% in all DIs detected and accounted for all Type III and one-third of Type II.

Conclusions

CBCT imaging can be effective in the detection of dental anomalies such as DI and planning for root canal therapy and surgical treatments. Prophylactic interventions might be possible to prevent apical pathosis with the data obtained from CBCT images.

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.

The effect of imaging modality on the evaluation of the outcome of endodontic surgery

OBJECTIVES

The aim of this study was to assess the effect of the imaging modality on the evaluation of the outcome of modern surgical endodontic treatments, based on a systematic review of the literature.

METHODS

Strict inclusion criteria were adopted in order to identify studies that assessed the outcome of surgical endodontic treatments. Treatment success rates were pooled. The effect of the imaging modality used for the outcome assessment, and the methodological quality of the studies (based on the risk of bias (ROB)), were evaluated.

RESULTS

Nineteen articles were included. The success rates assessed by periapical (PA) radiography were significantly higher than when cases were evaluated by cone beam computed tomography (CBCT; 90 and 35% respectively). This difference was mainly due to a significant proportion of cases that were assessed by CBCT as uncertain healing (48%) compared to only 4% using PA. The success rates ranged between 86 and 92% in low ROB studies, and between 19-100% in high ROB studies.

CONCLUSIONS

Outcome assessment based on CBCT may lead to significantly lower estimates of rate of success, and higher rates of uncertain healing, thus presenting a dilemma in the decision-making following surgical endodontic treatment. The success rates of studies with lower methodological quality are more variable than for high quality studies.

The Changes in Size of Periapical Lesions after Root Canal Treatments Assessed by Digital Periapical Radiography and Cone-Beam Computed Tomography: A 2-Years Prospective Clinical Study

Background and Objectives: There is limited information regarding comparison of long-term dynamics of periapical bone destruction estimated by digital periapical radiography (DPR) and by cone-beam computed tomography (CBCT). This study aimed to compare the radiographically assessed periapical changes of endodontically treated teeth over 2 years of follow-up and to analyse disagreements in periapical lesion size estimates around the same roots using DPR and CBCT. Materials and Methods: A total of 176 endodontically treated teeth, of 128 patients with apical periodontitis, were assessed by DPR and CBCT, at baseline and after 2 years. All periapical radiolucencies were categorised by severity (S0, S1, S2, S3) concerning their size. Descriptive statistics were used to report distribution of the radiolucencies at baseline and at follow-up, and their size transitions over 2 years. Site-specific comparison of the radiolucencies identified by two methods was performed using Z test and Pearson’s chi-square test. Results: majority of the detected radiolucencies were scored as S0: 65% and 68% at baseline; 89% and 83% at follow-up, by DPR and CBCT, respectively. Site-specific score comparison showed that disagreements comprised 18% and 20% of the total number of radiolucencies detected by DPR and CBCT, respectively. There were more disagreements between DPR and CBCT within categories S1 and S2 + S3 compared to S0: at baseline, they comprised 17–33% and after two years 62–95% of all detected radiolucencies within the category. 65% of non-matching score transitions over two years occurred between S0 and S1. The CBCT-based evaluation resulted in negative treatment outcomes for 10 more root canals than the DPR-based result. Conclusions: Most remarkable disagreement between DPR and CBCT recordings was observed within the radiolucency categories S2 and S3. However, the diagnostic accuracy of both radiographic methods was questionable as it resulted in a high proportion of non-matching S0-S1 lesion transitions over 2 years.

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.

Automatic Detection of Periapical Osteolytic Lesions on CBCT Using Deep CNNs

INTRODUCTION

Cone beam computed tomography (CBCT) is an essential diagnostic tool in oral radiology. Radiolucent periapical lesions (PALs) represent the most frequent jaw lesions. However, the description, interpretation, and documentation of radiological findings, especially incidental findings, are time-consuming and resource-intensive, requiring a high degree of expertise. To improve quality, dentists may use artificial intelligence in the form of deep learning tools. This study was conducted to develop and validate a deep convolutional neuronal network for the automated detection of osteolytic PALs in CBCT datasets.

METHODS

CBCT datasets from routine clinical operations (maxilla, mandible, or both) performed from January to October 2020 were retrospectively screened and selected. A two-step approach was used for automatic PAL detection. First, tooth localization and identification were performed using the SpatialConfiguration-Net based on heatmap regression. Second, binary segmentation of lesions was performed using a modified U-Net architecture. A total of 144 CBCT images were used to train and test the networks. The method was evaluated using the four-fold cross-validation technique.

RESULTS

The success detection rate of the tooth localization network ranged between 72.6% and 97.3%, whereas the sensitivity and specificity values of lesion detection were 97.1% and 88.0%, respectively.

CONCLUSIONS

Although PALs showed variations in appearance, size, and shape in the CBCT dataset, and a high imbalance existed between teeth with and without PALs, the proposed fully automated method provided excellent results compared with related literature.

Artificial Intelligence in Dentistry: Past, Present, and Future

Artificial intelligence (AI) has remarkably increased its presence and significance in a wide range of sectors, including dentistry. It can mimic the intelligence of humans to undertake complex predictions and decision-making in the healthcare sector, particularly in endodontics. The models of AI, such as convolutional neural networks and/or artificial neural networks, have shown a variety of applications in endodontics, including studying the anatomy of the root canal system, forecasting the viability of stem cells of the dental pulp, measuring working lengths, pinpointing root fractures and periapical lesions and forecasting the success of retreatment procedures. Future applications of this technology were considered in relation to scheduling, patient care, drug-drug interactions, prognostic diagnosis, and robotic endodontic surgery. In endodontics, in terms of disease detection, evaluation, and prediction, AI has demonstrated accuracy and precision. AI can aid in the advancement of endodontic diagnosis and therapy, which can enhance endodontic treatment results. However, before incorporating AI models into routine clinical operations, it is still important to further certify the cost-effectiveness, dependability, and applicability of these models.

Prevalence of dens invaginatus and its association with periapical lesions in a Western Indian population-a study using cone-beam computed tomography

OBJECTIVES

This study aimed to assess the prevalence of dens invaginatus (DI) and its association with periapical lesions (PLs) in a Western Indian population by means of cone-beam computed tomography (CBCT).

MATERIALS AND METHODS

CBCT volumes of 5201 subjects were evaluated. Associations among gender, tooth type, DI type (Oehler's classification), and presence of PL were investigated. PL was codified using Estrela's Cone Beam Computed Tomography Periapical Index (CBCTPAI). Chi-square tests and descriptive statistics were used at p = 0.05.

RESULTS

Overall, 7048 CBCTs were assessed, containing 19,798 maxillary and mandibular anteriors, of which 77 maxillary teeth demonstrated DI (0.39% of all anteriors). Of all 5201 subjects, 57 had DI (1.1%). Bilateral DI was more common in females than in males (p = 0.046). DI type distribution was as follows: type I (22.1%), type II (61.03%), type IIIa (10.4%), and type IIIb (6.5%), which was significantly different (p < 0.001). Maxillary lateral incisors were the most associated with PL (p < 0.001). Type I was frequently associated with CBCTPAI scores 1 and 2 (absence of PL), whereas types II, IIIa, and IIIb were associated with CBCTPAI scores 3, 4, and 5 (presence of PL).

CONCLUSIONS

A prevalence of 1.1% identifies DI as a common developmental tooth anomaly in a Western Indian subpopulation. The percentage of maxillary anteriors affected by DI and associated PLs should be considered before diagnosis and treatment planning.

CLINICAL RELEVANCE

Knowledge about the prevalence of DI and its subtypes, and their association with/without periapical pathosis may aid clinicians in treatment planning and execution to improve patient outcomes.

Prognostic Predictors of Endodontic Microsurgery: Radiographic Assessment

Objective

This study aimed to compare the healing outcomes of endodontic microsurgery (EMS) using 2-dimensional (2D) and 3-dimensional (3D) radiographic evaluation in a Chinese population. The prognostic factors of EMS were identified according to the 2D and 3D healing classifications.

Materials and methods

The teeth (n = 82) were studied using 2D and 3D radiographic examinations. The 2D and 3D healing criteria were used to evaluate the healing outcome. Prognostic factors were investigated based on healing outcomes. Data were analysed using SPSS, and P < .05 was considered significant.

Results

There were significant differences between 2D and 3D healing outcomes (P = .004). For the 3D images, age older than 45 years was found to be a significant negative predictor (P = .005).

Conclusions

Cone-beam computed tomographic images provided more precise evaluation of periapical lesions and healing outcomes of EMS than conventional periapical radiographs. Age (>45 years) of the patients exhibited a significant influence on the healing outcome of EMS as determined using 3D images.

A U-Net Approach to Apical Lesion Segmentation on Panoramic Radiographs

The purpose of the paper was the assessment of the success of an artificial intelligence (AI) algorithm formed on a deep-convolutional neural network (D-CNN) model for the segmentation of apical lesions on dental panoramic radiographs. A total of 470 anonymized panoramic radiographs were used to progress the D-CNN AI model based on the U-Net algorithm (CranioCatch, Eskisehir, Turkey) for the segmentation of apical lesions. The radiographs were obtained from the Radiology Archive of the Department of Oral and Maxillofacial Radiology of the Faculty of Dentistry of Eskisehir Osmangazi University. A U-Net implemented with PyTorch model (version 1.4.0) was used for the segmentation of apical lesions. In the test data set, the AI model segmented 63 periapical lesions on 47 panoramic radiographs. The sensitivity, precision, and F1-score for segmentation of periapical lesions at 70% IoU values were 0.92, 0.84, and 0.88, respectively. AI systems have the potential to overcome clinical problems. AI may facilitate the assessment of periapical pathology based on panoramic radiographs.

Reproducibilidad y validez de criterio de dos técnicas radiográficas para variaciones de premolares mandibulares comparadas con CBCT

Introducción: La existencia de variaciones anatómicas ocasiona fracasos en tratamientos endodónticos, por lo que es importante diagnosticarlas. El objetivo fue determinar la reproducibilidad y la validez de criterio de las radiografías con placa de fósforo y la radiovisografía con sensor para identificar las variaciones anatómicas detectadas por tomografía computarizada de haz cónico (CBCT) en premolares inferiores. Métodos: En 140 premolares se obtuvieron imágenes por CBCT, radiografía y radiovisografía. Se realizó lectura independiente por dos endodocistas, evaluándose la clasificación de Vertucci y las ramificaciones. Se determinó la reproducibilidad intraobservador e interobservador. Se calcularon sensibilidad, especificidad y áreas bajo la curva operador-receptor (AUC) utilizando como estándar de oro la CBCT. Resultados: La reproducibilidad intraobservador e interobservador fue mayor para radiografía. Para la Clase I de Vertucci, la radiografía presentó mayor sensibilidad (94,7%), especificidad (64,9%) y AUC (0,795) que la radiovisiografía (89,3%, 62,2% y 0,757, respectivamente), al igual que para la Clase V (Radiografía 69,2%, 93% y 0,811; Radiovisiografía 50%, 84,2% y 0,671, respectivamente). Ninguna de las técnicas aportó al diagnóstico de la Clase III (AUC <0,5). Las ramificaciones fueron infrecuentes (2,9%) y su detección fue baja (Sensibilidad 25% para radiografía y 0% para radiovisiografía). Discusión: Este es el primer estudio que evalúa la reproducibilidad y validez de estas dos técnicas radiográficas comparadas con la CBCT para la detección de variaciones anatómicas en dientes. Conclusiones: La radiografía con placa de fósforo presentó mayor reproducibilidad y validez para el diagnóstico de las Clase I y V de Vertucci, que fueron las variaciones más frecuentes.

An Update on Nickel-Titanium Rotary Instruments in Endodontics: Mechanical Characteristics, Testing and Future Perspective-An Overview

Since the introduction of Nickel-Titanium alloy as the material of choice for the manufacturing of endodontic rotary instruments, the success rate of the root canal therapies has been significantly increased. This success mainly arises from the properties of the Nickel-Titanium alloy: the biocompatibility, the superelasticity and the shape memory effect. Those characteristics have led to a reduction in time of endodontic treatments, a simplification of instrumentation procedures and an increase of predictability and effectiveness of endodontic treatments. Nevertheless, the intracanal separation of Nickel-Titanium rotary instruments is still a major concern of endodontists, with a consequent possible reduction in the outcome rate. As thoroughly demonstrated, the two main causes of intracanal separation of endodontic instruments are the cyclic fatigue and the torsional loads. As results, in order to reduce the percentage of intracanal separation research and manufacturers have been focused on the parameters that directly or indirectly influence mechanical properties of endodontic rotary instruments. This review describes the current state of the art regarding the Nickel-Titanium alloy in endodontics, the mechanical behavior of endodontic rotary instruments and the relative stresses acting on them during intracanal instrumentation, highlighting the limitation of the current literature.

Magnetic resonance imaging versus cone beam computed tomography in diagnosis of periapical pathosis – A systematic review

Objective

The diagnosis of any dental pathology can vary from being simple to challenging. While the use of cone beam computed tomography (CBCT) is well established, magnetic resonance imaging (MRI) remains a proof of concept. This systematic review aims to compare the diagnostic ability of MRI with CBCT in diagnosing periapical pathosis.

Materials and Methods

This systematic search was performed using the electronic databases of MEDLINE, Cochrane Library, Google Scholar, and Science Direct to identify relevant articles from 2010 to 2020. The search terms used were magnetic resonance imaging, cone beam computed tomography, diagnosis, and periapical diseases.

Result

In total, 3218 potentially relevant abstracts and titles were identified. After removing duplicates, 1288 articles were reviewed for titles and abstracts, and 29 articles were selected for full-text reading. From those, 19 articles were finally selected that included original research studies, case reports, and case series and were included for systematic review. Most of the studies included in this review suggested that the combined use of CBCT and MRI is needed for a better and more precise diagnosis of complex periapical pathoses. The main advantage of MRI is its ability to image soft tissues usingnonionizing radiation, and the main disadvantage in the case of CBCT is overdiagnosis of the lesion.

Conclusion

MRI has various advantages over CBCT with similar diagnostic utility. When diagnosing periapical pathogens, both MRI and CBCT are needed for an accurate diagnosis.

Detection of Dental Apical Lesions Using CNNs on Periapical Radiograph

Apical lesions, the general term for chronic infectious diseases, are very common dental diseases in modern life, and are caused by various factors. The current prevailing endodontic treatment makes use of X-ray photography taken from patients where the lesion area is marked manually, which is therefore time consuming. Additionally, for some images the significant details might not be recognizable due to the different shooting angles or doses. To make the diagnosis process shorter and efficient, repetitive tasks should be performed automatically to allow the dentists to focus more on the technical and medical diagnosis, such as treatment, tooth cleaning, or medical communication. To realize the automatic diagnosis, this article proposes and establishes a lesion area analysis model based on convolutional neural networks (CNN). For establishing a standardized database for clinical application, the Institutional Review Board (IRB) with application number 202002030B0 has been approved with the database established by dentists who provided the practical clinical data. In this study, the image data is preprocessed by a Gaussian high-pass filter. Then, an iterative thresholding is applied to slice the X-ray image into several individual tooth sample images. The collection of individual tooth images that comprises the image database are used as input into the CNN migration learning model for training. Seventy percent (70%) of the image database is used for training and validating the model while the remaining 30% is used for testing and estimating the accuracy of the model. The practical diagnosis accuracy of the proposed CNN model is 92.5%. The proposed model successfully facilitated the automatic diagnosis of the apical lesion.

Association between Pulpal-Periapical Pathology and Autoimmune Diseases: A Systematic Review

Several studies have linked apical periodontitis and systemic diseases. The aim of this study is to present a systematic review of the available literature investigating whether there is an association between pulpal-periapical pathology and autoimmune disease. The review was conducted following the PRISMA statement. A literature search was performed in five databases. Studies involving patients with pulpal-periapical pathology and autoimmune diseases were included in the review. Based on the PICO model, the research question aimed to assess whether there is an increased risk of developing pulpal-periapical pathology in patients with autoimmune disease. Article selection, data extraction, and quality assessment were performed using an adapted version of the STROBE guidelines. A total of seven studies were included in our review. The types of articles were five case-control and two cross-sectional studies. Periapical pathologies were associated to three autoimmune diseases (diabetes mellitus I, rheumatoid arthritis, and inflammatory bowel disease). Among the included studies, four show a low risk of bias, while three present a moderate risk. There could be an association between apical periodontitis and autoimmune diseases, although most studies report statistically non-significant associations.

Possible Causes for Failure of Endodontic Surgery - A Retrospective Series of 20 Resurgery Cases

OBJECTIVE

This study aimed to evaluate unsuccessful endodontic surgery cases for possible causes for treatment failure and evaluate if a nonsurgical retreatment (NSRTX) approach could have been a better alternative to resurgery.

METHODS

Analyses of clinical and cone-beam computed tomography (CBCT) images, periapical radiographs, and chart documentation determined study parameters. Preoperative factors were age, sex, tooth type, signs and/or symptoms, presence of periapical radiolucency, previous root canal treatment, timeline since previous endodontic surgery, presence of posts, cores, and restorations. The intra-operative factors were microsurgical classification, previous techniques, and current techniques utilized. Postoperative factors were signs and/or symptoms, time to follow-up, and healing status. The accessibility of the root canal system and the quality of the existing root filling were used to evaluate NSRTX as an alternative to resurgery.

RESULTS

A total of 1073 surgical cases from 2011-2019 were reviewed. In 14 patients, 20 cases matched the inclusion criteria and allowed for data extraction. The mean time since the previous surgery was 2.9+-2.1 years, with a mean follow-up of 9.1+-5.8 months after the resurgery. Possible reasons for failure identified were: insufficient root-end filling (leaking, off-axis preparation, lack of depth, overfill) n=12/20, 60.0%; missed anatomy (main and lateral canals, isthmus) n=9/20, 45.0%; incomplete resection n=6/20, 30.0%. In 18/20 cases (90.0%), resurgery appeared to be indicated for 2/20 cases (10.0%). Therefore, NSRTX may have been a potential alternative.

CONCLUSION

Further evidence for possible causes of failure of endodontic surgery was provided, which were primarily iatrogenic. The evaluation of CBCT and high magnification intra-operative images proved beneficial for identifying critical issues for all investigated cases.

[Interpretation of periapical healing in radiological images. A review]

Interpretation of the state of healing of chronic apical periodontitis or apical curettage with apicoectomy in radiological images is based on the analysis of changes in the appearance of the periapical area and in the bone structure adjacent to the site of inflammation or surgical intervention, which are projected onto normal bone structures. However, distortion of structures or the superposition of anatomical images should be considered when interpreting radiographs. We compared conventional studies of evaluation of the periapical area following treatment, together with 2D images, with the periapical index and the criteria of evaluation in both successful and unsuccessful cases of endodontic surgical treatment. Some studies have reported that the radiographic appearance of the tooth crown and root may facilitate interpretation of the periapical area. In addition, cone-beam computed tomography can show the relationship between injured and repairing tissue using buccal and lingual tables to measure the periphery in transverse reconstruction. Indeed, complex biological events and mechanisms can occur during the healing process of periapical and root tissues. Knowledge of the diversity of tissues is essential to identify the dynamics of the signs of regeneration or the presence of healing due to repair. Hence, the aim of this article was to identify the criteria used to interpret periapical healing in two-dimensional or three-dimensional images and their relationship with diagnosis and treatment according to the literature currently available.

A Deep Learning Approach to Segment and Classify C-Shaped Canal Morphologies in Mandibular Second Molars Using Cone-beam Computed Tomography

INTRODUCTION

The identification of C-shaped root canal anatomy on radiographic images affects clinical decision making and treatment. The aims of this study were to develop a deep learning (DL) model to classify C-shaped canal anatomy in mandibular second molars from cone-beam computed tomographic (CBCT) volumes and to compare the performance of 3 different architectures.

METHODS

U-Net, residual U-Net, and Xception U-Net architectures were used for image segmentation and classification of C-shaped anatomies. Model training and validation were performed on 100 of a total of 135 available limited field of view CBCT images containing mandibular molars with C-shaped anatomy. Thirty-five CBCT images were used for testing. Voxel-matching accuracy of the automated labeling of the C-shaped anatomy was assessed with the Dice index. The mean sensitivity of predicting the correct C-shape subcategory was calculated based on detection accuracy. One-way analysis of variance and post hoc Tukey honestly significant difference tests were used for statistical evaluation.

RESULTS

The mean Dice coefficients were 0.768 ± 0.0349 for Xception U-Net, 0.736 ± 0.0297 for residual U-Net, and 0.660 ± 0.0354 for U-Net on the test data set. The performance of the 3 models was significantly different overall (analysis of variance, P = .000779). Both Xception U-Net (Q = 7.23, P = .00070) and residual U-Net (Q = 5.09, P = .00951) performed significantly better than U-Net (post hoc Tukey honestly significant difference test). The mean sensitivity values were 0.786 ± 0.0378 for Xception U-Net, 0.746 ± 0.0391 for residual U-Net, and 0.720 ± 0.0495 for U-Net. The mean positive predictive values were 77.6% ± 0.1998% for U-Net, 78.2% ± 0.0.1971% for residual U-Net, and 80.0% ± 0.1098% for Xception U-Net. The addition of contrast-limited adaptive histogram equalization had improved overall architecture efficacy by a mean of 4.6% (P < .0001).

CONCLUSIONS

DL may aid in the detection and classification of C-shaped canal anatomy.

A retrospective study of endodontic microsurgery about 302 patients

OBJECTIVES

To investigate the outcome of endodontic microsurgery and analyze the potential prognostic factors, and to evaluate the value of surgical classification by Kim and Kratchman.

METHODS

Collecting clinical examination and radiographical examination of endodontic microsurgery cases (which were followed up at least 1 year), which were classified according to Kim and Kratchman, and we analyzed the outcome of endodontic microsurgery and its potential prognostic factors.

RESULTS

302 patients (400 teeth) who received endodontic microsurgery were included. The one year success rate of endodontic microsurgery was 94.25%. Different classification had significant influences on the outcome of endodontic microsurgery (P<0.05), and the success rate of class B and C were better than those of class D, E, and F. The position of teeth had significant influences on the outcome of endodontic microsurgery (P<0.05). The success rate of maxillary teeth was higher than that of mandibular teeth. The success rate of anterior teeth was higher than that of posterior teeth (P<0.05). The quality of root end filling and first or second surgery had no effect on the outcome (P>0.05).

CONCLUSIONS

Endodontic microsurgery is an effective treatment method for saving affected teeth, and it can get a good result. Tooth position and classification are the potential prognostic factors. The surgical classification of Kim and Kratchman can help to predict the outcome of endodontic microsurgery.

Interexaminer Agreement in the Radiologic Identification of Apical Periodontitis/Rarefying Osteitis in the National Dental Practice-Based Research Network PREDICT Endodontic Study

INTRODUCTION

Periapical images are routinely made in endodontics to support diagnosis and treatment decisions, but conventional imaging may not readily demonstrate inflammatory changes. This study aims to quantify disagreement in the radiologic interpretation of apical periodontitis/rarefying osteitis between 2 expert examiners and to determine if differences exist based on anatomic location.

METHODS

We used 1717 pretreatment periapical images made before orthograde endodontic treatment as part of the Predicting Outcomes of Root Canal Treatment (PREDICT) study conducted within the National Dental Practice-Based Research Network. Periapical changes were assessed independently by 2 board-certified specialists, an oral and maxillofacial radiologist and an endodontist, blinded to other clinical information. If the examiners disagreed about whether a diagnosis of apical periodontitis/rarefying osteitis was justified, an adjudication was made by a third examiner.

RESULTS

The overall prevalence of this radiologic diagnosis in the periapical images was 55%, and interexaminer agreement measured with the Cohen kappa statistic was calculated to be 0.56 (95% confidence interval, 0.52-0.60). Diagnostic disagreements between the 2 examiners occurred for 377 teeth (22%), with disagreements more frequent for jaw location (P = .038) and tooth type (P = .021). Differences between root number (P = .058) and jaw location and tooth groups (P = .069) were found not to be statistically significant.

CONCLUSIONS

The variability of diagnostic disagreements across anatomic location and tooth type may reflect the inability of periapical images to reveal bone changes masked by the complexity and density of overlying anatomic structures, a limitation that could potentially be overcome with the use of 3-dimensional imaging.

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.

Deep learning for categorization of endodontic lesion based on radiographic periapical index scoring system

OBJECTIVE

The study aimed to apply convolutional neural network (CNN) to score periapical lesion on an intraoral periapical radiograph (IOPAR) based on the periapical index (PAI) scoring system.

MATERIALS AND METHODS

A total of 3000 periapical root areas (PRA) on 1950 digital IOPAR were pre-scored by three endodontists. This data was used to train the CNN model-"YOLO version 3." A total of 450 PRA was used for validation of the model. Data augmentation techniques and model optimization were applied. A total of 540 PRA on 250 digital IOPAR was used to test the performance of the CNN model.

RESULTS

A total of 303 PRA (56.11%) exhibited true prediction. PAI score 1 showed the highest true prediction (90.9%). PAI scores 2 and 5 exhibited the least true prediction (30% each). PAI scores 3 and 4 had a true prediction of 60% and 71%, respectively. When the scores were dichotomized as healthy (PAI scores 1 and 2) and diseased (PAI score 3, 4, and 5), the model achieved a true prediction of 76.6% and 92%, respectively. The model exhibited a 92.1% sensitivity/recall, 76% specificity, 86.4% positive predictive value/precision, and 86.1% negative predictive value. The accuracy, F1 score, and Matthews correlation coefficient were 86.3%, 0.89, and 0.71, respectively.

CONCLUSION

The CNN model trained on a limited amount of IOPAR data showed potential for PAI scoring of the periapical lesion on digital IOPAR.

CLINICAL RELEVANCE

An automated system for PAI scoring is developed that would potentially benefit clinician and researchers.

Evaluation of the accuracy values of cone-beam CT regarding apical periodontitis: a systematic review and meta-analysis

Specialists need to know how accurate and effective each radiographic procedure is, and which ones can provide better images for bone resorption around the apical periodontitis. Therefore, the researcher decided to conduct the present study with the aim of evaluate the accuracy values of cone-beam CT regarding apical periodontitis. The PubMed, Embase, ISI, Scopus, and Medicine have been used to search articles over the last 15 years between 2005 and December 2020. Meta-analysis data with 95% confidence interval (CI), Random effect model, and restricted maximum-likelihood methods were calculated. Random effects were used to deal with potential heterogeneity and I² showed heterogeneity. I² values above 50% signified moderate-to-high heterogeneity. The meta-analysis has been evaluated with the statistical software Stata/MP v.16 (The fastest version of Stata). One hundred and fifty-eight studies were selected to review the abstracts, six papers met these crucial criteria to do a systematic review and meta-analysis. Sensitivity and specificity of digital periapical radiography was 50% (ES 0.50; 95% CI 0.05, 0.95) and 83% (ES 0.83; 95% CI 0.52, 1.15), respectively. Sensitivity and specificity of cone-beam computed tomographic was 95% (ES 0.95; 95% CI 0.80, 1.00) and 90% (ES 0.90; 95% CI 0.78, 1.03), respectively. In conclusion, CBCT imaging reports values with excellent accuracy vs digital periapical radiography.

Artificial Intelligence in Endodontics: Current Applications and Future Directions

INTRODUCTION

Artificial intelligence (AI) has the potential to replicate human intelligence to perform prediction and complex decision making in health care and has significantly increased its presence and relevance in various tasks and applications in dentistry, especially endodontics. The aim of this review was to discuss the current endodontic applications of AI and potential future directions.

METHODS

Articles that have addressed the applications of AI in endodontics were evaluated for information pertinent to include in this narrative review.

RESULTS

AI models (eg, convolutional neural networks and/or artificial neural networks) have demonstrated various applications in endodontics such as studying root canal system anatomy, detecting periapical lesions and root fractures, determining working length measurements, predicting the viability of dental pulp stem cells, and predicting the success of retreatment procedures. The future of this technology was discussed in light of helping with scheduling, treating patients, drug-drug interactions, diagnosis with prognostic values, and robotic-assisted endodontic surgery.

CONCLUSIONS

AI demonstrated accuracy and precision in terms of detection, determination, and disease prediction in endodontics. AI can contribute to the improvement of diagnosis and treatment that can lead to an increase in the success of endodontic treatment outcomes. However, it is still necessary to further verify the reliability, applicability, and cost-effectiveness of AI models before transferring these models into day-to-day clinical practice.