Oral Radiology最新文献

Objectives: Periodontitis is one of the most common chronic inflammatory diseases. It causes changes in the biting abilities of individuals. However, periodontal treatment has positive effects on masticatory function. The aim of this study is to determine the effect of periodontitis and periodontal treatment on masticatory abilities by measuring masseter and temporal muscle thicknesses with ultrasonography before and after periodontal treatment in chronic periodontitis patients.

Methods: The patients included in the study were determined by clinical and radiological examination. The thickness of the masseter and temporal muscles of the patients were measured by ultrasonography. Periodontal measurements and treatments of the patients were completed by a single physician. IBM SPSS 20.0 (IBM Corp., Armonk, NY) statistical program was used for statistical analysis.

Results: A statistically significant difference was found between the values of periodontal measurements before and after treatment (p<0.05). In the ultrasonography measurements of the thickness of masseter and anterior temporal muscles, a statistically significant increase was observed in both rest and contraction values at all time intervals (p<0.05). Muscle thicknesses of male patients were higher than female patients.

Conclusions: Periodontitis negatively affects the masticatory performance of individuals. Chronic periodontitis patients should be referred for periodontal treatment without wasting time.

Objectives: The aim of this study was to develop an assessment tool for automatic detection of dental caries in periapical radiographs using convolutional neural network (CNN) architecture.

Methods: A novel diagnostic model named ResNet + SAM was established using numerous periapical radiographs (4278 images) annotated by medical experts to automatically detect dental caries. The performance of the model was compared to the traditional CNNs (VGG19, ResNet-50), and the dentists. The Gradient-weighted Class Activation Mapping (Grad-CAM) technique shows the region of interest in the image for the CNNs.

Results: ResNet + SAM demonstrated significantly improved performance compared to the modified ResNet-50 model, with an average F1 score of 0.886 (95% CI 0.855-0.918), accuracy of 0.885 (95% CI 0.862-0.901) and AUC of 0.954 (95% CI 0.924-0.980). The comparison between the performance of the model and the dentists revealed that the model achieved higher accuracy than that of the junior dentists. With the assist of the tool, the dentists achieved superior metrics with a mean F1 score of 0.827 and the interobserver agreement for dental caries is enhanced from 0.592/0.610 to 0.706/0.723.

Conclusions: According to the results obtained from the experiments, the automatic assessment tool using the ResNet + SAM model shows remarkable performance and has excellent possibilities in identifying dental caries. The use of the assessment tool in clinical practice can be of great benefit as a clinical decision-making support in dentistry and reduce the workload of dentists.

Objectives: We aim to develop a deep learning model based on a convolutional neural network (CNN) combined with a classification algorithm (CA) to assist dentists in quickly and accurately diagnosing the stage of periodontitis.

Materials and methods: Periapical radiographs (PERs) and clinical data were collected. The CNNs including Alexnet, VGG16, and ResNet18 were trained on PER to establish the PER-CNN models for no periodontal bone loss (PBL) and PBL. The CAs including random forest (RF), support vector machine (SVM), naive Bayes (NB), logistic regression (LR), and k-nearest neighbor (KNN) were added to the PER-CNN model for control, stage I, stage II and stage III/IV periodontitis. Heat map was produced using a gradient-weighted class activation mapping method to visualize the regions of interest of the PER-Alexnet model. Clustering analysis was performed based on the ten PER-CNN scores and the clinical characteristics.

Results: The accuracy of the PER-Alexnet and PER-VGG16 models with the higher performance was 0.872 and 0.853, respectively. The accuracy of the PER-Alexnet + RF model with the highest performance for control, stage I, stage II and stage III/IV was 0.968, 0.960, 0.835 and 0.842, respectively. Heat map showed that the regions of interest predicted by the model were periodontitis bone lesions. We found that age and smoking were significantly related to periodontitis based on the PER-Alexnet scores.

Conclusion: The PER-Alexnet + RF model has reached high performance for whole-case periodontal diagnosis. The CNN models combined with CA can assist dentists in quickly and accurately diagnosing the stage of periodontitis.

Introduction: The mandibular nerve and the mental foramen have occasionally shown variations in its anatomy. This report aims to present a case of lingual mental foramen recognised on three-dimensional cone beam computed tomographic imaging (CBCT).

Case report: Routine Orthopantomogram (OPG) and CBCT images were evaluated to assess the status of impact third molars in a 31-year-old female who had visited the dental clinics in our institution. The OPG image failed to reveal any anatomic variation in the position of the mental foramen. On tracing the course of the mandibular canal in CBCT images, two foramina were traced at the region of premolar. One opened towards the buccal cortical plate at the normal position of the mental foramen and an accessory lingual mental foramen had an opening on the lingual cortical bone at the same level as the mental foramen.

Conclusion: Understanding variations of the mental foramen is extremely essential in dentistry to carry out successful anaesthetic or surgical interventions and to avoid complications such as nerve damage or excessive bleeding.

Objectives: This study assessed the incidence of postfracture radiological temporomandibular joint (TMJ) degeneration in patients with different types of mandibular fractures, focusing on the impact of condylar fractures.

Methods: This retrospective review included patients diagnosed as having mandibular fractures from 2016 to 2020 who had undergone initial computed tomography (CT) and a follow-up CT scan at least 1-month postfracture. Patient demographics, fracture details, treatment methods, and radiological signs of TMJ degeneration on CT were analyzed to identify risk factors for postfracture TMJ degeneration, with a focus on condylar head fracture and non-head (condylar neck or base) fractures.

Results: The study included 85 patients (mean age: 38.95 ± 17.64 years). The per-patient analysis indicated that the incidence of new radiologic TMJ degeneration on CT was significantly the highest (p < 0.001) in patients with condylar head fractures (90.91%), followed by those with non-head condylar fractures (57.14%), and those without condylar involvement (24.49%). The per-joint analysis indicated nearly inevitable degeneration (93.94%) in 33 TMJs with ipsilateral condylar head fractures. For the remaining 137 TMJs, multivariate logistic regression revealed that other patterns (ipsilateral non-head, contralateral, or both) of condylar fractures (odds ratio (OR) = 3.811, p = 0.007) and the need for open reduction and internal fixation (OR = 5.804, p = 0.005) significantly increased the risk of TMJ degeneration.

Conclusions: Ipsilateral non-head condylar fractures and contralateral condylar fractures are associated with a high risk of postfracture TMJ degeneration. Indirect trauma plays a vital role in postfracture TMJ degeneration.

Background: The recent impact of artificial intelligence in diagnostic services has been enormous. Machine learning tools offer an innovative alternative to diagnose cysts and tumors radiographically that pose certain challenges due to the near similar presentation, anatomical variations, and superimposition. It is crucial that the performance of these models is evaluated for their clinical applicability in diagnosing cysts and tumors.

Methods: A comprehensive literature search was carried out on eminent databases for published studies between January 2015 and December 2022. Studies utilizing machine learning models in the diagnosis of odontogenic cysts or tumors using Orthopantomograms (OPG) or Cone Beam Computed Tomographic images (CBCT) were included. QUADAS-2 tool was used for the assessment of the risk of bias and applicability concerns. Meta-analysis was performed for studies reporting sufficient performance metrics, separately for OPG and CBCT.

Results: 16 studies were included for qualitative synthesis including a total of 10,872 odontogenic cysts and tumors. The sensitivity and specificity of machine learning in diagnosing cysts and tumors through OPG were 0.83 (95% CI 0.81-0.85) and 0.82 (95% CI 0.81-0.83) respectively. Studies utilizing CBCT noted a sensitivity of 0.88 (95% CI 0.87-0.88) and specificity of 0.88 (95% CI 0.87-0.89). Highest classification accuracy was 100%, noted for Support Vector Machine classifier.

Conclusion: The results from the present review favoured machine learning models to be used as a clinical adjunct in the radiographic diagnosis of odontogenic cysts and tumors, provided they undergo robust training with a huge dataset. However, the arduous process, investment, and certain ethical concerns associated with the total dependence on technology must be taken into account. Standardized reporting of outcomes for diagnostic studies utilizing machine learning methods is recommended to ensure homogeneity in assessment criteria, facilitate comparison between different studies, and promote transparency in research findings.

Objectives

Bitewing radiography is considered to be of high diagnostic value in caries detection, but owing to projections, lesions may remain undetected. The novel bitewing plus (BW +) technology enables scrolling through radiographs in different directions and angles. The present study aimed at comparing BW + with other 2D and 3D imaging methods in terms of sensitivity, specificity, and user reliability.

Materials and methods

Five human cadavers were used in this study. In three cadavers, natural teeth were transplanted post-mortem. BW + , two-dimensional (digital sensors, imaging plates, 2D and 3D bitewing radiographs) and 3D methods (high and low dose CBCT) were taken. Carious lesions were evaluated on 96 teeth at three positions (mesial, distal, and occlusal) and scored according to their level of demineralization by ten observers, resulting in 35,799 possible lesions across all observers and settings. For reference, µCT scans of all teeth were performed.

Results

Overall, radiographic evaluations showed a high rate of false-negative diagnoses, with around 70% of lesions remaining undetected, especially enamel lesions. BW + showed the highest sensitivity for dentinal caries and had comparatively high specificity overall.

Conclusions

Within the limits of the study, BW + showed great potential for added diagnostic value, especially for dentinal caries. However, the tradeoff of diagnostic benefit and radiation exposure must be considered according to each patient’s age and risk.

Stafne bone defect (SBD) is a rare developmental bone defect characterized by an asymptomatic focal concavity of the cortical bone, typically on the lingual aspect of the mandibular body, which generally contains salivary gland tissue. It can be detected during routine dental examinations and typically appears as an ovoid, well-defined, well-corticated, radiolucent depression in the posterior mandibular region below the inferior alveolar nerve (IAN) (in: Neville et al, Oral and maxillofacial pathology, Elsevier, Inc, St. Louis, MO, 2016).

An 80-year-old male presented to our clinic for a routine dental examination. Panoramic radiography and cone-beam computed tomography (CBCT) displayed two well-defined, well-corticated, ovoid radiolucencies inferior to the IAN canal on the left mandibular molar region. The working diagnosis was SBD, and the patient was informed of the findings. Irregular margins on the superior aspect of the anterior defect were noted on CBCT imaging; therefore, follow-up with panoramic images at 6 months, 1 and 5 years was recommended.

Objective

This study aimed to evaluate the usability of morphometric features obtained from mandibular panoramic radiographs in gender determination using machine learning algorithms.

Materials and methods

High-resolution radiographs of 200 patients aged 20–77 (41.0 ± 12.7) were included in the study. Twelve different morphometric measurements were extracted from each digital panoramic radiography included in the study. These measurements were used as features in the machine learning phase in which six different machine learning algorithms were used (k-nearest neighbor, decision trees, support vector machines, naive Bayes, linear discrimination analysis, and neural networks). To evaluate the reliability, we have performed tenfold cross-validation and we repeated this 10 times for every classification process. This process enhances the reliability of the results for other datasets.

Results

When all 12 features are used together, the accuracy rate is found to be 82.6 ± 0.5%. The classification accuracies are also compared using each feature alone. Three features that give the highest accuracy are coronoid height (80.9 ± 0.9%), condyle height (78.2 ± 0.5%), and ramus height (77.2 ± 0.4%), respectively. When compared to the classification algorithms, the highest accuracy was obtained with the naive Bayes algorithm with a rate of 84.0 ± 0.4%.

Conclusion

Machine learning techniques can accurately determine gender by analyzing mandibular morphometric structures from digital panoramic radiographs. The most precise results are achieved by evaluating the structures in combination, using attributes obtained from applying the MRMR algorithm to all features.