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.

Variations and thicknesses of anterior belly of the digastric muscle: an ultrasonographic study.

PURPOSE: This study aims to evaluate the anatomy and anatomical variations of the anterior belly of the digastric muscle. METHODS: Hundred and fifty one ultrasonographic images of the digastric muscle pairs were evaluated in Near East University Faculty of Dentistry Department of Dentomaxillofacial Radiology. Morphological variations were recorded using the classification of the digastric muscle into 12 types by Kim et al. For the analysis, the Mann-Whitney U test and Chi-square test were used, and for the correlational analysis, Spearman's rho test was applied. P < 0.05 was considered statistically significant in all tests. RESULTS: Seventy female and 81 male patients aged 19-60 years were evaluated. Type 1 digastric muscle was observed in 145 of 151 patients, Type 2 in 3 patients, and Type 7 in 3 patients. The thicknesses of the right and left digastric muscles were measured, and a statistically significant difference was observed between the groups when the genders were compared. It was observed that both right and left digastric muscle thicknesses were higher in males than females. There was a statistically significant positive high correlation between right and left digastric muscle thicknesses (p = 0.000; r = 0.736). No statistically significant difference was found between genders (p = 0.596) in terms of anatomical variations. CONCLUSION: Considering that the variations of the digastric muscle may have a clinical significance role, the normal anatomy and variations of this muscle should be well known by maxillofacial surgeons and radiologists.

Influence of voxel size and filter type on detecting vertical root fracture using cone-beam computed tomography.

Vertical root fractures (VRFs) can start at any level of the root and progress longitudinally to the coronal attachment. This study aimed to investigate the effects of different exposure parameters used when obtaining CBCT scans in detecting simulated VRFs. Hence, 80 intact human mandibular single-rooted pre-molar teeth without root fractures were included in the study. No statistically significant difference was found between the filters in terms of VRF detection in the group with the roots with only root canal filling (Groups 1 and 5); however, 100 voxels were found to be more successful in terms of VRF detection than other voxel sizes. Results of this study suggest that using lower voxel sizes leads to an accurate diagnosis of vertical root fracture, in addition, our results revealed that using AR filters did not improve the diagnostic accuracy in detecting VRFs.

Retrospective evaluation of the morpometric and morphological anatomy of the occipital condyle, hypoglossal canal and foramen magnum in Turkish populaton with CBCT.

PURPOSE: The aim of this study is to morphometrically and morphologically examine the occipital condyle, which is an important anatomical region in terms of surgery and forensic medicine, and its surrounding structures, to evaluate the change in mean values according to gender and age, and to evaluate the correlation of the measurements obtained. METHODS: 180 (90 men, 90 women) CBCT images selected from the archive of Ankara University Faculty of Dentistry. Occipital Condyle length and width, Hypoglossal Canal-Basion distance, Hypoglossal Canal-Opistion distance, Hypoglossal Canal-Occipital Condyle anterior and posterior border distance, Occipital Condyle thickness, Hypoglossal Canal length, the widest diameter of Hypoglossal Canal, the narrowest diameter of the Hypoglossal Canal, the length of the Jugular Tubercle, the width of the Jugular Tubercle, the anterior intercondylar distance, the posterior intercondylar distance, and the Foramen Magnum index were measured. At the same time, the presence of septum or spicule in the hypoglossal canal and protrusion of the occipital condyle were evaluated. The relationship of age, gender, anterior and posterior intercondylar distance, and foramen magnum index measurements with all measurements were examined. RESULTS: In our study, all measurements were repeated 1 month after the first measurements to evaluate the intra-observer agreement, and the agreement between the obtained measurements and the first measurements was evaluated by calculating the intraclass correlation coefficient and 95% confidence intervals. Men's measurements were found to be significantly higher than women's measurements. When the coefficients of concordance in all measurements were examined, it was observed that there was a perfect concordance. CONCLUSION: When the results of the study are evaluated, it is seen that the values ​​obtained are generally close to the studies related to CT. Considering this, an idea can be gained as to whether CBCT, which has a lower dose and less cost, can be used as an alternative to CT in studies to be conducted with more comprehensive and different methods in skull base surgical planning.

Development and validation of intraoral periapical radiography-based machine learning model for periodontal defect diagnosis.

Radiographic determination of the bone level is useful in the diagnosis and determination of the severity of the periodontal disease. Various two- and three-dimensional imaging modalities offer choices for imaging pathologic processes that affect the periodontium. In recent years, innovative computer techniques, especially artificial intelligence (AI), have begun to be used in many areas of dentistry and are helping increase treatment and diagnostic performance. This study was aimed at developing a machine-learning (ML) model and assessing the extent to which it was capable of classifying periodontal defects on 2D periapical images. Eighty-seven periapical images were examined as part of this research. The existence or absence of periodontal defects in the aforementioned images were evaluated by a human observer. The evaluations were subsequently repeated using a radiomics platform. A comparison was made of all data acquired through human observation and ML techniques by SVM analysis. According to the study findings the ability of human observers and the ML model to detect periodontal defects was significantly different in comparison to the gold standard. However, ML and human observers performed similarly for the detection of periodontal defects without a significant difference. This study reveals that the prediction of periodontal defects can be achieved by combining particular radiomic features with image variables. The proposed machine leaning model can be utilized for supporting clinical practitioners and eventually substitute evaluations conducted by human observers while enhancing future levels of performance.

Deep-Learning-Based Automatic Segmentation of Parotid Gland on Computed Tomography Images.

This study aims to develop an algorithm for the automatic segmentation of the parotid gland on CT images of the head and neck using U-Net architecture and to evaluate the model's performance. In this retrospective study, a total of 30 anonymized CT volumes of the head and neck were sliced into 931 axial images of the parotid glands. Ground truth labeling was performed with the CranioCatch Annotation Tool (CranioCatch, Eskisehir, Turkey) by two oral and maxillofacial radiologists. The images were resized to 512 × 512 and split into training (80%), validation (10%), and testing (10%) subgroups. A deep convolutional neural network model was developed using U-net architecture. The automatic segmentation performance was evaluated in terms of the F1-score, precision, sensitivity, and the Area Under Curve (AUC) statistics. The threshold for a successful segmentation was determined by the intersection of over 50% of the pixels with the ground truth. The F1-score, precision, and sensitivity of the AI model in segmenting the parotid glands in the axial CT slices were found to be 1. The AUC value was 0.96. This study has shown that it is possible to use AI models based on deep learning to automatically segment the parotid gland on axial CT images.

Comparative evaluation of trabecular bone structures of bruxist and non-bruxist individuals with bone apposition in the mandible angle region by fractal analysis.

OBJECTIVE: This study aimed to compare the trabecular internal structure of different regions of the mandible according to the grades of appositional classification in the mandible angle region in probable bruxist individuals and non-bruxist G0(Convex course of the basal cortex, no directional change, no bone apposition) individuals by measuring fractal dimension (FD) on panoramic radiographs. METHODS: 200 sample jaws, bilaterally, of 80 probable bruxists and 20 non-bruxist G0 individuals were included in the study. According to the classification in the literature, each mandible angle apposition severity was classified as G0-G1-G2-G3. FD was calculated by selecting the region of interest (ROI) area of 7 regions from each sample. Gender differences in changes between ROIs in radiographs and independent samples t-test were evaluated. Relation between categorical variables was determined by chi-square test (p < .05). RESULTS: In the comparison of the probable bruxist and non-bruxist G0 groups, FD was found to be statistically significantly higher in the mandible angle (p = 0.013) and cortical bone (p = 0.000) regions in the probable bruxist group than in the non-bruxist G0 group. There is a statistically significant difference between probable bruxist G0 and non-bruxist G0 grades in terms of FD averages in cortical bone (p < 0.001). A statistically significant difference was found in the relationship of ROIs with gender in canine apex (p = 0.021) and canine distal (p = 0.041) regions. CONCLUSION: FD was found to be higher in the mandibular angle region and cortical bone in probable bruxist individuals than in non-bruxist G0 individuals. Morphological changes seen in the mandible angulus region may be a finding that may raise suspicion for bruxism for clinicians.

Evaluation of single session physical therapy methods in bruxism patients using shear wave ultrasonography.

OBJECTIVE: To compare the immediate effects of a single session of manual therapy (MT) or Kinesio taping following MT (KTMT) in patients with bruxism using shear wave ultrasonography. METHODS: Twenty patients were included in the MT group (mean age 27.3 ± 4.8), and 19 patients were included in the KTMT group (age mean 26.2 ± 5.4), randomly. Muscle thickness and stiffness were assessed via shear wave ultrasonography, and pain pressure threshold was assessed with an algometer before and after one session of MT or KTMT. RESULTS: Significant decreases were found in muscle thickness and stiffness of the bilateral masseter (p < 0.05). Significant decrease in pain was seen in the masseter and temporalis muscle PPT measurements in the KTMT group (p < 0.05) only. CONCLUSION: Kinesio taping in addition to MT is recommended in the immediate physiotherapy treatment of bruxism for acute pain.

Evaluation of a metal artifact reduction algorithm and an adaptive image noise optimization filter in the estimation of peri-implant fenestration defects using cone beam computed tomography: an in-vitro study.

OBJECTIVE: The aim of this study is to assess the effects of metal artifact reduction (MAR) and adaptive image noise enhancer (AINO) in CBCT imaging on the detection accuracy of artificially created fenestration defects in proximity to titanium and zirconium implants in sheep jaw. METHODS: Six zirconium and 10 titanium implants were planted on mandibular jaws of three sheep, and artificial defects were created. All images were obtained with a standard voxel size (0.150 mm3) and with 4 scan modes: (1) without MAR/without AINO; (2) with MAR/without AINO; (3) without MAR/with AINO; and (4) with MAR/with AINO during CBCT scanning. A total of 60 CBCT scans were produced. RESULTS: For all types of implants, intra- and inter-observer kappa values were the highest for MAR filter. The scan mode of with MAR filter was found to have the highest area under the curve (AUC), whereas the scan mode of without both MAR and AINO filters was found to have the lowest AUC values with statistical significance (p ≤ 0.05). Titanium implants were found to have higher AUC values than zirconium (p ≤ 0.05). CONCLUSION: Both MAR module and AINO filters enhance the accuracy of the detection of peri-implant fenestrations; however, the use of MAR filter solely can be recommended for detection of peri-implant fenestrations.

Comparison of Kinesio Taping and manual therapy in the treatment of patients with bruxism using shear-wave elastography-A randomised clinical trial.

BACKGROUND: Bruxism is significantly associated with craniofacial pain, feeling of stiffness or fatigue of the jaw and neck pain. Various physiotherapeutic strategies are used in the treatment of bruxism; however, it is not clear which method leads to greater decrease in pain. OBJECTIVE: The aim of this study is to compare the effects of two physiotherapy methods (manual therapy [MT] and Kinesio taping with manual therapy [KTMT]) in patients with bruxism. METHODS: Patients were randomised into MT or KTMT groups. Evaluations were performed at baseline and following 4 weeks of physiotherapy. Muscle thickness and stiffness were assessed via shear wave elastography; pain thresholds were evaluated using algometer. Sleep quality was assessed using Pittsburgh Sleep Quality Index, and quality of life was assessed with Likert scales regarding the associated symptoms. RESULTS: Significant decreases were found in muscle stiffness, pain threshold, sleep quality and quality of life (P < .05) in both MT and KTMT groups. Pain in bilateral temporalis and right occipital region of the trapezius muscle decreased more in the KTMT group compared with the MT group (P < .05). No significant differences in muscle thickness (P > .05) were found in either of the groups. CONCLUSION: Both MT and KTMT methods were effective in the treatment of bruxism. Kinesio Tape used in conjunction with MT has additionally decreased jaw pain and temporal region pain compared with MT intervention only. Therefore, if jaw pain is the primary complaint of a patient, our results recommend including Kinesio Tape application in the physiotherapeutic treatment program.

Comparison of the different voxel sizes in the estimation of peri-implant fenestration defects using cone beam computed tomography: an ex vivo study.

BACKGROUND: To examine the influence of voxel sizes to detect of peri-implant fenestration defects on cone beam computed tomography (CBCT) images. MATERIALS AND METHODS: This study performed with three sheep heads both maxilla and mandible and two types of dental implant type 1 zirconium implant (Zr40) (n = 6) and type 2 titanium implant (Ti22) (n = 10). A total of 14 peri-implant fenestrations (8 buccal surfaces, 6 palatal/lingual surface) were created while 18 surfaces (8 buccal, 10 palatal/lingual) were free of fenestrations. Three observers have evaluated the images of fenestration at each site. Images obtained with 0.75 mm3, 0.100 mm3, 0.150 mm3, 0.200 mm3, and 0.400 mm3 voxel sizes. For intra- and inter-observer agreements for each voxel size, Kappa coefficients were calculated. RESULTS: Intra- and inter-observer kappa values were the highest for 0.150 mm3, and the lowest in 0.75 mm3 and 0.400 mm3 voxel sizes for all types of implants. The highest area under the curve (AUC) values were found higher for the scan mode of 0.150 mm3, whereas lower AUC values were found for the voxel size for 0.400 mm3. Titanium implants had higher AUC values than zirconium with the statistical significance for all voxel sizes (p ≤ 0.05). CONCLUSION: A voxel size of 0.150 mm3 can be used to detect peri-implant fenestration bone defects. CBCT is the most reliable diagnostic tool for peri-implant fenestration bone defects.