Deep learning for determining the difficulty of endodontic treatment: a pilot study.

BACKGROUND: To develop and validate a deep learning model for automated assessment of endodontic case difficulty from periapical radiographs. METHODS: A dataset of 1,386 periapical radiographs was compiled from two clinical sites. Two dentists and two endodontists annotated the radiographs for difficulty using the "simple assessment" criteria from the American Association of Endodontists' case difficulty assessment form in the Endocase application. A classification task labeled cases as "easy" or "hard", while regression predicted overall difficulty scores. Convolutional neural networks (i.e. VGG16, ResNet18, ResNet50, ResNext50, and Inception v2) were used, with a baseline model trained via transfer learning from ImageNet weights. Other models was pre-trained using self-supervised contrastive learning (i.e. BYOL, SimCLR, MoCo, and DINO) on 20,295 unlabeled dental radiographs to learn representation without manual labels. Both models were evaluated using 10-fold cross-validation, with performance compared to seven human examiners (three general dentists and four endodontists) on a hold-out test set. RESULTS: The baseline VGG16 model attained 87.62% accuracy in classifying difficulty. Self-supervised pretraining did not improve performance. Regression predicted scores with ± 3.21 score error. All models outperformed human raters, with poor inter-examiner reliability. CONCLUSION: This pilot study demonstrated the feasibility of automated endodontic difficulty assessment via deep learning models.

Deep learning for tooth identification and numbering on dental radiography: a systematic review and meta-analysis.

OBJECTIVES: Improved tools based on deep learning can be used to accurately number and identify teeth. This study aims to review the use of deep learning in tooth numbering and identification. METHODS: An electronic search was performed through October 2023 on PubMed, Scopus, Cochrane, Google Scholar, IEEE, arXiv, and medRxiv. Studies that used deep learning models with segmentation, object detection, or classification tasks for teeth identification and numbering of human dental radiographs were included. For risk of bias assessment, included studies were critically analysed using quality assessment of diagnostic accuracy studies (QUADAS-2). To generate plots for meta-analysis, MetaDiSc and STATA 17 (StataCorp LP, College Station, TX, USA) were used. Pooled outcome diagnostic odds ratios (DORs) were determined through calculation. RESULTS: The initial search yielded 1618 studies, of which 29 were eligible based on the inclusion criteria. Five studies were found to have low bias across all domains of the QUADAS-2 tool. Deep learning has been reported to have an accuracy range of 81.8%-99% in tooth identification and numbering and a precision range of 84.5%-99.94%. Furthermore, sensitivity was reported as 82.7%-98% and F1-scores ranged from 87% to 98%. Sensitivity was 75.5%-98% and specificity was 79.9%-99%. Only 6 studies found the deep learning model to be less than 90% accurate. The average DOR of the pooled data set was 1612, the sensitivity was 89%, the specificity was 99%, and the area under the curve was 96%. CONCLUSION: Deep learning models successfully can detect, identify, and number teeth on dental radiographs. Deep learning-powered tooth numbering systems can enhance complex automated processes, such as accurately reporting which teeth have caries, thus aiding clinicians in making informed decisions during clinical practice.

Comparison between combination of tamsulosin and Pentoxifylline versus tamsulosin alone in the treatment of lower urinary tract symptoms due to benign prostate hyperplasia: A preliminary study.

BACKGROUND: In older adults, bladder outlet obstruction (BOO) is prevalent, primarily due to benign prostatic hyperplasia (BPH). These patients' lower urinary tract symptoms can be treated surgically and with medical therapy. Compared to standard treatment with tamsulosin, Pentoxifylline, a phosphodiesterase inhibitor, could benefit patients with BOO due to its properties on microcirculatory blood flow and oxygenation of ischemic tissues. Hence, this trial intended to study the efficacy of Pentoxifylline combined with tamsulosin in treating BOO patients. MATERIALS AND METHODS: This randomized, double-blind clinical trial recruited 60 patients with BPH from a single center in 2022. Upon consent of patients meeting the eligibility criteria, they were randomly allocated to intervention (Pentoxifylline + tamsulosin) and control (placebo + tamsulosin) groups. The patients were evaluated for international prostate symptom score (IPSS), quality of life (QoL), maximum urinary flow rate (Qmax ) by uroflowmetry, and post-void residual volume (PVR) by abdominal sonography at the onset of the study and after the 12th week. RESULTS: Patients who used the combination therapy had significantly better results of prostate symptoms and quality of life improvement (IPSS: -36.6%, QoL: -45.3%) compared to patients who received tamsulosin alone (IPSS: -21.2%, QoL: -27.7%) (p < .001). Also, this study shows that the improvement in maximum urinary flow rate and residual volume by combination therapy is significantly higher (Qmax : +42.5%, PVR: -42.6%) compared to monotherapy (Qmax : +25.1%, PVR: -26.1%) (p < .001). CONCLUSION: When combined with tamsulosin, Pentoxifylline could significantly improve the lower urinary symptoms of BPH patients. It is well tolerated, and the treatment outcomes are better in patients who receive the combination of Pentoxifylline and tamsulosin than those who only receive tamsulosin.

The effect of low-dose aspirin on aspirin triggered lipoxin, interleukin 1 beta, and prostaglandin E2 levels in periapical fluid: a double-blind randomized clinical trial.

BACKGROUND: The role of pro-resolving mediators in inflammation is a new concern in research. The effect of low-dose aspirin on production of a special kind of these mediators named aspirin triggered lipoxin (ATL) has been studied on different tissues. This randomized clinical trial evaluated the effect of low-dose aspirin on ATL and pro-inflammatory mediators' level in periapical fluid of necrotic teeth with large lesions. METHODS: Twenty-four patients with necrotic pulp and periapical lesion were randomly assigned to low-dose aspirin and placebo groups. In the first appointment, canals were shaped up to F3 size and #40 K-file and cleaned with 10 milliliters 2.5% sodium hypochlorite and 17% Ethylenediaminetetraacetic acid. Periapical fluid was sampled by a paper cone. The tooth was temporized without any intracanal medication. Tablets were administered for 7 days, then the teeth were re-opened and the sampling were repeated. Interleukin-1 beta (IL-1ß), prostaglandin E2 (PGE2) and ATL were analyzed by enzyme-linked immunosorbent assay. Data were analyzed with paired t-test using SPSS statistical software, version 21 (α = 0.05). RESULTS: A significant reduction in PGE2 and IL-1ß was noted in the aspirin-treated group while an increase in ATL was observed (P < 0.001). There was no significant difference in the mediator scores before and after in the placebo-treated group (P > 0.05). CONCLUSION: Low-dose aspirin can influence the inflammatory process by reducing pro-inflammatory mediators such as PGE2 and IL-1ß, as well as increasing the pro-resolving mediators such as ATL. TRIAL REGISTRATION: IRCT20191211045702N1.

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.

Deep learning for tooth identification and enumeration in panoramic radiographs.

Background: Dentists begin the diagnosis by identifying and enumerating teeth. Panoramic radiographs are widely used for tooth identification due to their large field of view and low exposure dose. The automatic numbering of teeth in panoramic radiographs can assist clinicians in avoiding errors. Deep learning has emerged as a promising tool for automating tasks. Our goal is to evaluate the accuracy of a two-step deep learning method for tooth identification and enumeration in panoramic radiographs. Materials and Methods: In this retrospective observational study, 1007 panoramic radiographs were labeled by three experienced dentists. It involved drawing bounding boxes in two distinct ways: one for teeth and one for quadrants. All images were preprocessed using the contrast-limited adaptive histogram equalization method. First, panoramic images were allocated to a quadrant detection model, and the outputs of this model were provided to the tooth numbering models. A faster region-based convolutional neural network model was used in each step. Results: Average precision (AP) was calculated in different intersection-over-union thresholds. The AP50 of quadrant detection and tooth enumeration was 100% and 95%, respectively. Conclusion: We have obtained promising results with a high level of AP using our two-step deep learning framework for automatic tooth enumeration on panoramic radiographs. Further research should be conducted on diverse datasets and real-life situations.

Dahaan: a framework for delivering evidence-informed dentistry recommendations and dental public health advocacy in Iran.

Although health is mostly determined by socio-political factors, the need for providing reliable health recommendations to the public should not be neglected. There has been a considerable void in delivering evidence-informed oral health recommendations in Iran; whilst there is a significant gap in oral health knowledge among socioeconomic classes, recommendations are neither fully compatible with each other nor up-to-date. To fill in this void, we started Dahaan (meaning "mouth" in Persian) with the aim of providing the latest easily accessed evidence-informed dentistry recommendations and advocating dental public health in the Iranian community. In this paper, we as the authors present the performance and achievements of this group, which is a member of the NCD Alliance and the Informed Health Choices project with a reasonable number of readers across the country, and illustrate the way ahead towards our goals.

Drug-related Dysgeusia: A Systematic Review.

PURPOSE: Dysgeusia is an unpleasant alteration in taste. It can affect the nutritional and psychological status and decrease the quality of life of patients. It may be caused by nerve injury, head and neck trauma or surgery, infections, radiotherapy and drugs, but certain aetiological factors have not yet been identified. Understanding dysgeusia as a drug side effect is important for practitioners. The aim of this systematic review was to provide detailed information about dysgeusia in patients receiving different common medications. MATERIALS AND METHODS: An electronic search was conducted in MEDLINE, Google Scholar and Scopus databases, and studies were selected according to our inclusion criteria. We included studies on human subjects that reported dysgeusia as a drug side effect. RESULTS: Thirty-four eligible studies were included in the systematic review. Thirty-five drugs were found in the literature to be correlated to dysgeusia. The most commonly reported offending drugs were from keratolytic agents, chemotherapeutic and cancer medication, antihistamine, antibiotics and angiotensin-converting enzyme inhibitors. CONCLUSION: The quality of evidence was low in most reviewed studies. More studies with standard methodology are needed in this field. However, physicians and dental practitioners must consider the probability of dysgeusia as an adverse side effect when prescribing certain medications.