Gender-Based Variation in Alveolar Bone Thickness of Maxillary Incisor Teeth: A CBCT Retrospective Study.

BACKGROUND This retrospective study from a single center in Cyprus aimed to assess labial (buccal) and palatal bone thickness in 6 anterior maxillary teeth of 120 adults using cone-beam computed tomography (CBCT). MATERIAL AND METHODS The CBCT scans of 120 patients (720 teeth) were examined, with scanning parameters of 90 kvP, 24 s, 4 mA, voxel size 0.3 mm, and field of view of 10×6 cm. All maxillary incisors were categorized into 3 distinct points in terms of buccal (B) and palatal (P) points, with points B1 (buccal) and P1 (palatal) 4 mm below the cementoenamel junction; points B2 and P2 at the midpoint between the labial and palatal alveolar crest plane extending to the root apex; and points B3 and P3 at the root apex. Evaluation was done by measuring the distance from these points to the labial and palatal alveolar bone. RESULTS When the thicknesses were measured between all 6 points and labial and palatal bone, the thickness of point B3 of tooth 13 in men was significantly higher than that in women. At points P1, P2, and P3 for teeth 11 and 13, the palatal bone thickness of men was significantly higher than that of women. At points P2 and P3 of tooth 12, the palatal bone thickness of men was significantly higher than that of women. CONCLUSIONS The study found a correlation between alveolar bone thickness and patient sex in the North Cyprus population. Alveolar bone thickness in the anterior maxillary should be considered in implant treatment and orthodontic techniques.

Comparison of Three Commercially Available, AI-Driven Cephalometric Analysis Tools in Orthodontics.

Background: Cephalometric analysis (CA) is an indispensable diagnostic tool in orthodontics for treatment planning and outcome assessment. Manual CA is time-consuming and prone to variability. Methods: This study aims to compare the accuracy and repeatability of CA results among three commercial AI-driven programs: CephX, WebCeph, and AudaxCeph. This study involved a retrospective analysis of lateral cephalograms from a single orthodontic center. Automated CA was performed using the AI programs, focusing on common parameters defined by Downs, Ricketts, and Steiner. Repeatability was tested through 50 randomly reanalyzed cases by each software. Statistical analyses included intraclass correlation coefficients (ICC3) for agreement and the Friedman test for concordance. Results: One hundred twenty-four cephalograms were analyzed. High agreement between the AI systems was noted for most parameters (ICC3 > 0.9). Notable differences were found in the measurements of angle convexity and the occlusal plane, where discrepancies suggested different methodologies among the programs. Some analyses presented high variability in the results, indicating errors. Repeatability analysis revealed perfect agreement within each program. Conclusions: AI-driven cephalometric analysis tools demonstrate a high potential for reliable and efficient orthodontic assessments, with substantial agreement in repeated analyses. Despite this, the observed discrepancies and high variability in part of analyses underscore the need for standardization across AI platforms and the critical evaluation of automated results by clinicians, particularly in parameters with significant treatment implications.

A Deep Learning Approach to Automatic Tooth Caries Segmentation in Panoramic Radiographs of Children in Primary Dentition, Mixed Dentition, and Permanent Dentition.

OBJECTIVES: The purpose of this study was to evaluate the effectiveness of dental caries segmentation on the panoramic radiographs taken from children in primary dentition, mixed dentition, and permanent dentition with Artificial Intelligence (AI) models developed using the deep learning method. METHODS: This study used 6075 panoramic radiographs taken from children aged between 4 and 14 to develop the AI model. The radiographs included in the study were divided into three groups: primary dentition (n: 1857), mixed dentition (n: 1406), and permanent dentition (n: 2812). The U-Net model implemented with PyTorch library was used for the segmentation of caries lesions. A confusion matrix was used to evaluate model performance. RESULTS: In the primary dentition group, the sensitivity, precision, and F1 scores calculated using the confusion matrix were found to be 0.8525, 0.9128, and 0.8816, respectively. In the mixed dentition group, the sensitivity, precision, and F1 scores calculated using the confusion matrix were found to be 0.7377, 0.9192, and 0.8185, respectively. In the permanent dentition group, the sensitivity, precision, and F1 scores calculated using the confusion matrix were found to be 0.8271, 0.9125, and 0.8677, respectively. In the total group including primary, mixed, and permanent dentition, the sensitivity, precision, and F1 scores calculated using the confusion matrix were 0.8269, 0.9123, and 0.8675, respectively. CONCLUSIONS: Deep learning-based AI models are promising tools for the detection and diagnosis of caries in panoramic radiographs taken from children with different dentition.

Retrospective evaluation of ponticulus posticus prevalence, sella turcica types, and stylohyoid complex calcifications in a group of Turkish population.

The aim of this retrospective analysis was to assess the incidence of ponticulus posticus and stylohyoid ligament calcification and to evaluate the morphological variations of the sella turcica within the Turkish demographic using CBCT scans. Involving a retrospective review of 460 CBCT scans and utilizing the NewTom 3G system, the study analyzed high-quality CBCT images to investigate ponticulus posticus, stylohyoid ligament calcifications, and sella turcica morphology. The ponticulus posticus was examined for complete or partial formations, while the stylohyoid ligament was classified according to its elongation and calcification patterns. The sella turcica was categorized into six distinct morphological types, enhancing the understanding of structural variations in the context of the Turkish population. The calcification patterns of the styloid processes were examined on both sides of 380 individuals, revealing the highest prevalence in the 'd' and 'e' categories on the right, and similar findings on the left among 373 individuals. Symmetric calcification patterns were more common, with 68.4% symmetry observed. For the sella turcica, category 'a' was the most frequent among 363 individuals. Analysis of ponticulus posticus absence and presence showed a majority lacking this feature on both sides, with complete and partial forms less common. The study highlights the anatomical variability and bilateral symmetry of the styloid processes, sella turcica, and ponticulus posticus, illustrating that these structures do not significantly vary with gender or age. These results hold clinical significance for the diagnosis and treatment of related conditions, prompting further investigation into their impact on patient care.

Classification of Periapical and Bitewing Radiographs as Periodontally Healthy or Diseased by Deep Learning Algorithms.

Objectives The aim of this artificial intelligence (AI) study was to develop a deep learning algorithm capable of automatically classifying periapical and bitewing radiography images as either periodontally healthy or unhealthy and to assess the algorithm's diagnostic success. Materials and methods The sample of the study consisted of 1120 periapical radiographs (560 periodontally healthy, 560 periodontally unhealthy) and 1498 bitewing radiographs (749 periodontally healthy, 749 periodontally ill). From the main datasets of both radiography types, three sub-datasets were randomly created: a training set (80%), a validation set (10%), and a test set (10%). Using these sub-datasets, a deep learning algorithm was developed with the YOLOv8-cls model (Ultralytics, Los Angeles, California, United States) and trained over 300 epochs. The success of the developed algorithm was evaluated using the confusion matrix method. Results The AI algorithm achieved classification accuracies of 75% or higher for both radiograph types. For bitewing radiographs, the sensitivity, specificity, precision, accuracy, and F1 score values were 0.8243, 0.7162, 0.7439, 0.7703, and 0.7821, respectively. For periapical radiographs, the sensitivity, specificity, precision, accuracy, and F1 score were 0.7500, 0.7500, 0.7500, 0.7500, and 0.7500, respectively. Conclusion The AI models developed in this study demonstrated considerable success in classifying periodontal disease. Future applications may involve employing AI algorithms for assessing periodontal status across various types of radiography images and for automated disease detection.

Morphological Variations of the Nasopalatine Canal in the North Cyprus Population: A Cone Beam Computed Tomography Study.

BACKGROUND This study aimed to evaluate the morphological characteristics of the anterior maxillary nasopalatine canal and the width of the buccal bone using cone-beam computed tomography (CBCT) in 150 adults in Northern Cyprus. MATERIAL AND METHODS The study included 150 participants, and their anterior maxillary morphometric measurements (eg, length of the nasopalatine canal and anteroposterior diameter of the nasal foramen) were taken using CBCT with the scanning parameters of 90 kvP, 24 s, 4 mA, voxel size 0.3 mm, and field of view 10×6 cm. The shapes of the nasopalatine canal (NPC) were categorized into 4 types: cylindrical, hourglass, funnel-shaped, and banana (54%, 20.6%, 18.6%, and 4%, respectively). RESULTS The findings showed a clear link between the shape of the NPC and the horizontal dimensions of the anterior maxilla's morphometric properties. In general, decreased horizontal bone dimensions were found in the premaxilla at the banana- and funnel-shaped type for the nasopalatine canal. Also, the anteroposterior diameter of a nasal foramen in the hourglass shape was significantly larger in diameter than all other shapes. Additionally, the morphology of the nasopalatine canal is influenced by its shape. The sagittal cross-section has shown significant correlations with the sizes of the incisive foramen, nasal foramen, and the length of the nasopalatine canal. CONCLUSIONS The study found a correlation between the shape of the NPC and the horizontal dimensions of the anterior maxilla's anatomy. The measurements of NPC in a North Cyprus population slightly differ from the established standards found in the existing literature. Conducting more extensive studies with a larger number of CBCT images will offer additional insights.

MgCa-Based Alloys Modified with Zn- and Ga-Doped CaP Coatings Lead to Controlled Degradation and Enhanced Bone Formation in a Sheep Cranium Defect Model.

Mg-based biodegradable metallic implants are gaining increased attraction for applications in orthopedics and dentistry. However, their current applications are hampered by their high rate of corrosion, degradation, and rapid release of ions and gas bubbles into the physiological medium. The aim of the present study is to investigate the osteogenic and angiogenic potential of coated Mg-based implants in a sheep cranial defect model. Although their osteogenic potential was studied to some extent, their potential to regenerate vascularized bone formation was not studied in detail. We have studied the potential of magnesium-calcium (MgCa)-based alloys modified with zinc (Zn)- or gallium (Ga)-doped calcium phosphate (CaP) coatings as a strategy to control their degradation rate while enhancing bone regeneration capacity. MgCa and its implants with CaP coatings (MgCa/CaP) as undoped or as doped with Zn or Ga (MgCa/CaP + Zn and MgCa/CaP + Ga, respectively) were implanted in bone defects created in the sheep cranium. MgCa implants degraded faster than the others at 4 weeks postop and the weight loss was ca. 50%, while it was ca. 15% for MgCa/CaP and <10% in the presence of Zn and Ga with CaP coating. Scanning electron microscopy (SEM) analysis of the implant surfaces also revealed that the MgCa implants had the largest degree of structural breakdown of all the groups. Radiological evaluation revealed that surface modification with CaP to the MgCa implants induced better bone regeneration within the defects as well as the enhancement of bone-implant surface integration. Bone volume (%) within the defect was ca. 25% in the case of MgCa/CaP + Ga, while it was around 15% for undoped MgCa group upon micro-CT evaluation. This >1.5-fold increase in bone regeneration for MgCa/CaP + Ga implant was also observed in the histopathological examination of the H&E- and Masson's trichrome-stained sections. Immunohistochemical analysis of the bone regeneration (antiosteopontin) and neovascularization (anti-CD31) at the defect sites revealed >2-fold increase in the expression of the markers in both Ga- and Zn-doped, CaP-coated implants. Zn-doped implants further presented low inflammatory reaction, notable bone regeneration, and neovascularization among all the implant groups. These findings indicated that Ga- and Zn-doped CaP coating is an important strategy to control the degradation rate as well as to achieve enhanced bone regeneration capacity of the implants made of Mg-based alloys.

Development and Validation of an Ultrasonography-Based Machine Learning Model for Predicting Outcomes of Bruxism Treatments.

BACKGROUND AND OBJECTIVES: We aimed to develop a predictive model for the outcome of bruxism treatments using ultrasonography (USG)-based machine learning (ML) techniques. This study is a quantitative research study (predictive modeling study) in which different treatment methods applied to bruxism patients are evaluated through artificial intelligence. MATERIALS AND METHODS: The study population comprised 102 participants with bruxism in three treatment groups: Manual therapy, Manual therapy and Kinesio Tape or Botulinum Toxin-A injection. USG imaging was performed on the masseter muscle to calculate muscle thickness, and pain thresholds were evaluated using an algometer. A radiomics platform was utilized to handle imaging and clinical data, as well as to perform a subsequent radiomics statistical analysis. RESULTS: The area under the curve (AUC) values of all machine learning methods ranged from 0.772 to 0.986 for the training data and from 0.394 to 0.848 for the test data. The Support Vector Machine (SVM) led to excellent discrimination between bruxism and normal patients from USG images. Radiomics characteristics in pre-treatment ultrasound scans of patients, showing coarse and nonuniform muscles, were associated with a greater chance of less effective pain reduction outcomes. CONCLUSIONS: This study has introduced a machine learning model using SVM analysis on ultrasound (USG) images for bruxism patients, which can detect masseter muscle changes on USG. Support Vector Machine regression analysis showed the combined ML models can also predict the outcome of the pain reduction.

The Detection of Pulp Stones with Automatic Deep Learning in Panoramic Radiographies: An AI Pilot Study.

This study aims to evaluate the effectiveness of employing a deep learning approach for the automated detection of pulp stones in panoramic imaging. A comprehensive dataset comprising 2409 panoramic radiography images (7564 labels) underwent labeling using the CranioCatch labeling program, developed in Eskisehir, Turkey. The dataset was stratified into three distinct subsets: training (n = 1929, 80% of the total), validation (n = 240, 10% of the total), and test (n = 240, 10% of the total) sets. To optimize the visual clarity of labeled regions, a 3 × 3 clash operation was applied to the images. The YOLOv5 architecture was employed for artificial intelligence modeling, yielding F1, sensitivity, and precision metrics of 0.7892, 0.8026, and 0.7762, respectively, during the evaluation of the test dataset. Among deep learning-based artificial intelligence algorithms applied to panoramic radiographs, the use of numerical identification for the detection of pulp stones has achieved remarkable success. It is expected that the success rates of training models will increase by using datasets consisting of a larger number of images. The use of artificial intelligence-supported clinical decision support system software has the potential to increase the efficiency and effectiveness of dentists.

Relationships between Interleukin 18 -607 C/A and -137 G/C, Osteopontin -9250 C/T Genetic Polymorphisms and Systemic Inflammatory Response Syndrome in Coronary Artery Bypass Graft Surgery.

Background and Objectives: Systemic inflammatory response syndrome (SIRS) is one of the most significant complications after on-pump heart surgery procedures. High cytokine levels have been shown after open-heart surgeries and a genetic predisposition seems to be an important underlying modulatory characteristic for SIRS. To investigate the association between interleukin 18 -607 C/A, interleukin 18 -137 G/C and osteopontin 9250 C/T genetic polymorphisms and SIRS in on-pump CABG patients. Materials and Methods: Two hundred consecutive elective on-pump CABG patients were recruited prospectively to the study. Genomic DNA was extracted from whole blood and genotyping was determined by sequence specific PCR or PCR-RFLP methods for related polymorphisms. Results: SIRS incidence was 60.2%, 38.1%, 18.9% on postoperative day 1, 2 and 3, respectively, in the whole study population. The SIRS rate on the second postoperative day was 13% and 43.4%, respectively, in osteopontin 9250 C/T T allele non-carriers and carriers (p = 0.004). WBC (White Blood Cell) counts were higher on day 2 and 3 in osteopontin 9250 C/T T allele carriers compared to non-carriers (day 2; 12.7 ± 4 vs. 10.5 ± 2.4 (p = 0.015), day 3; 11.8 ± 4 vs. 9.1 ± 4.7 (p = 0.035)). The average ICU stay was 3.1 ± 7.4, 1.28 ± 0.97 for IL 18-137 G/C C allele carriers and non-carriers, respectively (p = 0.003), and in the IL 18-137 G/C C allele carriers, SIRS developed in 42.2% by the second postoperative day whereas the rate was 57.8% in non-carriers (p = 0.025). Conclusions: The current research revealed a possible link between osteopontin 9250 C/T and IL18-137 G/C genetic polymorphism and SIRS and morbidity in on-pump CABG patients.

Maxillary Canine Impaction: Assessing the Influence of Maxillary Anatomy Using Cone Beam Computed Tomography.

BACKGROUND The purpose of this study was to evaluate the anatomical characteristics of patients with unilateral impacted canine teeth compared to a control group. Cone beam computed tomography (CBCT) records were retrospectively analyzed. MATERIAL AND METHODS CBCT records of 64 patients with unilateral impacted canine teeth (57.8% female and 42.2% male) and 64 controls (59.4% female and 40.6% male) were retrospectively analyzed. On the CBCT images, intermolar width, arch length, arch perimeter, palatal width in the molar region at cementoenamel junction, palatal width in the molar region at the crest, palatal width in the molar region measured from mid-root level, nasal cavity width, and palatal depth were evaluated. RESULTS In the palatal width measurement from the mid-root variable, the measurement of labially positioned canines was significantly lower than the control group (P<0.05). In terms of intermolar width, the labial positioned impacted canines' values were lower than in the control group. There was a significant difference in terms of the perimeter variable and both palatinally and labially positioned impacted canines were significantly lower than in the control group (P<0.05). All parameters were compared according to sex, and measurements of male patients were significantly higher than in female patients (P<0.05). CONCLUSIONS A labially impacted canine was strongly linked to a decrease in mid-root palatal and intermolar widths. Additionally, impacted canines positioned both palatally and labially were found to result in a reduced arch perimeter. Moreover, male patients with impacted canines exhibited notably greater anatomical measurements compared to female patients.

Validation of artificial intelligence application for dental caries diagnosis on intraoral bitewing and periapical radiographs.

OBJECTIVES: This study aimed to assess the reliability of AI-based system that assists the healthcare processes in the diagnosis of caries on intraoral radiographs. METHODS: The proximal surfaces of the 323 selected teeth on the intraoral radiographs were evaluated by two independent observers using an AI-based (Diagnocat) system. The presence or absence of carious lesions was recorded during Phase 1. After 4 months, the AI-aided human observers evaluated the same radiographs (Phase 2), and the advanced convolutional neural network (CNN) reassessed the radiographic data (Phase 3). Subsequently, data reflecting human disagreements were excluded (Phase 4). For each phase, the Cohen and Fleiss kappa values, as well as the sensitivity, specificity, positive and negative predictive values, and diagnostic accuracy of Diagnocat, were calculated. RESULTS: During the four phases, the range of Cohen kappa values between the human observers and Diagnocat were κ=0.66-1, κ=0.58-0.7, and κ=0.49-0.7. The Fleiss kappa values were κ=0.57-0.8. The sensitivity, specificity and diagnostic accuracy values ranged between 0.51-0.76, 0.88-0.97 and 0.76-0.86, respectively. CONCLUSIONS: The Diagnocat CNN supports the evaluation of intraoral radiographs for caries diagnosis, as determined by consensus between human and AI system observers. CLINICAL SIGNIFICANCE: Our study may aid in the understanding of deep learning-based systems developed for dental imaging modalities for dentists and contribute to expanding the body of results in the field of AI-supported dental radiology..

Progress of Artificial Intelligence-Driven Solutions for Automated Segmentation of Dental Pulp Space on Cone-Beam Computed Tomography Images. A Systematic Review.

INTRODUCTION: Automated segmentation of 3-dimensional pulp space on cone-beam computed tomography images presents a significant opportunity for enhancing diagnosis, treatment planning, and clinical education in endodontics. The aim of this systematic review was to investigate the performance of artificial intelligence-driven automated pulp space segmentation on cone-beam computed tomography images. METHODS: A comprehensive electronic search was performed using PubMed, Web of Science, and Cochrane databases, up until February 2024. Two independent reviewers participated in the selection of studies, data extraction, and evaluation of the included studies. Any disagreements were resolved by a third reviewer. The Quality Assessment of Diagnostic Accuracy Studies-2 tool was used to assess the risk of bias. RESULTS: Thirteen studies that met the eligibility criteria were included. Most studies demonstrated high accuracy in their respective segmentation methods, although there was some variation across different structures (pulp chamber, root canal) and tooth types (single-rooted, multirooted). Automated segmentation showed slightly superior performance for segmenting the pulp chamber compared to the root canal and single-rooted teeth compared to multi-rooted ones. Furthermore, the second mesiobuccal (MB2) canalsegmentation also demonstrated high performance. In terms of time efficiency, the minimum time required for segmentation was 13 seconds. CONCLUSION: Artificial intelligence-driven models demonstrated outstanding performance in pulp space segmentation. Nevertheless, these findings warrant careful interpretation, and their generalizability is limited due to the potential risk and low evidence level arising from inadequately detailed methodologies and inconsistent assessment techniques. In addition, there is room for further improvement, specifically for root canal segmentation and testing of artificial intelligence performance in artifact-induced images.

Microcomputed tomography as a diagnostic tool for detection of lymph node metastasis in non-small cell lung cancer: A decision-support approach for pathological examination "A pilot study for method validation".

Background: Non-small cell lung cancer (NSCLC) patients without lymph node (LN) metastases (pN0) may exhibit different survival rates, even when their T stage is similar. This divergence could be attributed to the current pathology practice, wherein LNs are examined solely in two-dimensional (2D). Unfortunately, adhering to the protocols of 2D pathological examination does not ensure the exhaustive sampling of all excised LNs, thereby leaving room for undetected metastatic foci in the unexplored depths of tissues. The employment of micro-computed tomography (micro-CT) facilitates a three-dimensional (3D) evaluation of all LNs without compromising sample integrity. In our study, we utilized quantitative micro-CT parameters to appraise the metastatic status of formalin-fixed paraffin-embedded (FFPE) LNs. Methods: Micro-CT scans were conducted on 12 FFPEs obtained from 8 NSCLC patients with histologically confirmed mediastinal LN metastases. Simultaneously, whole-slide images from these FFPEs underwent scanning, and 47 regions of interest (ROIs) (17 metastatic foci, 11 normal lymphoid tissues, 10 adipose tissues, and 9 anthracofibrosis) were marked on scanned images. Quantitative structural variables obtained via micro-CT analysis from tumoral and non-tumoral ROIs, were analyzed. Result: Significant distinctions were observed in linear density, connectivity, connectivity density, and closed porosity between tumoral and non-tumoral ROIs, as indicated by kappa coefficients of 1, 0.90, 1, and 1, respectively. Receiver operating characteristic analysis substantiated the differentiation between tumoral and non-tumoral ROIs based on thickness, linear density, connectivity, connectivity density, and the percentage of closed porosity. Conclusions: Quantitative micro-CT parameters demonstrate the ability to distinguish between tumoral and non-tumoral regions of LNs in FFPEs. The discriminatory characteristics of these quantitative micro-CT parameters imply their potential usefulness in developing an artificial intelligence algorithm specifically designed for the 3D identification of LN metastases while preserving the FFPE tissue.

Tooth numbering and classification on bitewing radiographs: an artificial intelligence pilot study.

OBJECTIVE: The aim of this study is to assess the efficacy of employing a deep learning methodology for the automated identification and enumeration of permanent teeth in bitewing radiographs. The experimental procedures and techniques employed in this study are described in the following section. STUDY DESIGN: A total of 1248 bitewing radiography images were annotated using the CranioCatch labeling program, developed in Eskisehir, Turkey. The dataset has been partitioned into 3 subsets: training (n = 1000, 80% of the total), validation (n = 124, 10% of the total), and test (n = 124, 10% of the total) sets. The images were subjected to a 3 × 3 clash operation in order to enhance the clarity of the labeled regions. RESULTS: The F1, sensitivity and precision results of the artificial intelligence model obtained using the Yolov5 architecture in the test dataset were found to be 0.9913, 0.9954, and 0.9873, respectively. CONCLUSION: The utilization of numerical identification for teeth within deep learning-based artificial intelligence algorithms applied to bitewing radiographs has demonstrated notable efficacy. The utilization of clinical decision support system software, which is augmented by artificial intelligence, has the potential to enhance the efficiency and effectiveness of dental practitioners.

The utilization of decision trees on orthopantomographic and lateral panoramic graphs for the diagnosis of unilateral anterior disc displacement of the temporomandibular joint.

BACKGROUND: Investigation is to utilize decision trees in conjunction with orthopantomography (OPT) and lateral panoramic graphy (LPG) to diagnose unilateral anterior disc displacement (ADD) of the temporomandibular joint. METHODS: In this study, 161 patients with images obtained through all three imaging methods, MRI, OPT, and LPG, were selected from the archives. The participants were categorized into two groups: the study group, comprising 89 patients with unilateral anterior disc displacement, and the control group, consisting of 72 healthy individuals. Measurements, including 2 angles (antero-posterior angle and superior-inferior angle) and 3 distance parameters (anterior joint space distance, superior joint space distance, and posterior joint space distance), were conducted on each imaging modality dataset. To assess the obtained measurement data within each patient, the differences from each measurement were calculated. Statistical analysis of the measurement differences between the control and study groups was carried out with independent t test, and decision trees were generated using the SPSS 25 decision tree module 5.0. RESULTS: In ADD patients, it was statistically significantly found that the APA increased while the SIA decreased for angle measurements. But for linear measurements, AS increased while the SS and PS decreased in MRI, OPT, and LPG. CONCLUSION: ADD can be diagnosed in OPT and LPG. The identification of the specific type of ADD that occurs in the temporomandibular joint is not feasible.

Artificial intelligence system for automatic maxillary sinus segmentation on cone beam computed tomography images.

OBJECTIVES: The study aims to develop an artificial intelligence (AI) model based on nnU-Net v2 for automatic maxillary sinus (MS) segmentation in cone beam computed tomography (CBCT) volumes and to evaluate the performance of this model. METHODS: In 101 CBCT scans, MS were annotated using the CranioCatch labelling software (Eskisehir, Turkey) The dataset was divided into 3 parts: 80 CBCT scans for training the model, 11 CBCT scans for model validation, and 10 CBCT scans for testing the model. The model training was conducted using the nnU-Net v2 deep learning model with a learning rate of 0.00001 for 1000 epochs. The performance of the model to automatically segment the MS on CBCT scans was assessed by several parameters, including F1-score, accuracy, sensitivity, precision, area under curve (AUC), Dice coefficient (DC), 95% Hausdorff distance (95% HD), and Intersection over Union (IoU) values. RESULTS: F1-score, accuracy, sensitivity, precision values were found to be 0.96, 0.99, 0.96, 0.96, respectively for the successful segmentation of maxillary sinus in CBCT images. AUC, DC, 95% HD, IoU values were 0.97, 0.96, 1.19, 0.93, respectively. CONCLUSIONS: Models based on nnU-Net v2 demonstrate the ability to segment the MS autonomously and accurately in CBCT images.

A potential novel technique for measurement of pulp volume on periapical radiography: A pilot study.

Pulp volume can be assessed during dental treatment. Three-dimensional imaging techniques are not routinely used for this purpose because of high radiation doses. This study aimed to develop a novel method to measure pulp volume using periapical radiography. In this study, cone-beam computed tomography (CBCT) was used as a reference method. Periapical radiography and CBCTs obtained from the same patients (n = 32) were recorded. Pulp volume was determined by observing the density differences between the pulp and peripheral structures using ImageJ. A method of graph and volume calculation was developed for each tooth. The Shapiro-Wilk test and Mann-Whitney U test were used to show normality and non-normal distributions. The Bland-Altman plot was used to show the scattering of the mean versus difference values of the measurements of the two methods used to calculate the pulp volume. Normality was evaluated using the Shapiro-Wilk test. CBCT measurements are normally distributed (p = 0.307), while ImageJ is not normally distributed (p = 0.027). Therefore, the mean difference between the two groups was analyzed using the nonparametric Mann-Whitney U test. There was a statistically significant difference between the CBCT and ImageJ measurements (p = 0.01). According to Spearman's correlation analysis, the results obtained from the novel method were moderately correlated with those obtained from the reference method (r = 0.444). The results of this study indicated that a novel method-based Java software can be used to calculate pulp volume using low-dose radiation containing periapical radiography.

Prediction of extraction difficulty for impacted maxillary third molars with deep learning approach.

OBJECTIVE: The aim of this study is to determine if a deep learning (DL) model can predict the surgical difficulty for impacted maxillary third molar tooth using panoramic images before surgery. MATERIALS AND METHODS: The dataset consists of 708 panoramic radiographs of the patients who applied to the Oral and Maxillofacial Surgery Clinic for various reasons. Each maxillary third molar difficulty was scored based on dept (V), angulation (H), relation with maxillary sinus (S), and relation with ramus (R) on panoramic images. The YoloV5x architecture was used to perform automatic segmentation and classification. To prevent re-testing of images, participate in the training, the data set was subdivided as: 80 % training, 10 % validation, and 10 % test group. RESULTS: Impacted Upper Third Molar Segmentation model showed best success on sensitivity, precision and F1 score with 0,9705, 0,9428 and 0,9565, respectively. S-model had a lesser sensitivity, precision and F1 score than the other models with 0,8974, 0,6194, 0,7329, respectively. CONCLUSION: The results showed that the proposed DL model could be effective for predicting the surgical difficulty of an impacted maxillary third molar tooth using panoramic radiographs and this approach might help as a decision support mechanism for the clinicians in peri­surgical period.