Automatic segmentation and classification of frontal sinuses for sex determination from CBCT scans using a two-stage anatomy-guided attention network.

Sex determination is essential for identifying unidentified individuals, particularly in forensic contexts. Traditional methods for sex determination involve manual measurements of skeletal features on CBCT scans. However, these manual measurements are labor-intensive, time-consuming, and error-prone. The purpose of this study was to automatically and accurately determine sex on a CBCT scan using a two-stage anatomy-guided attention network (SDetNet). SDetNet consisted of a 2D frontal sinus segmentation network (FSNet) and a 3D anatomy-guided attention network (SDNet). FSNet segmented frontal sinus regions in the CBCT images and extracted regions of interest (ROIs) near them. Then, the ROIs were fed into SDNet to predict sex accurately. To improve sex determination performance, we proposed multi-channel inputs (MSIs) and an anatomy-guided attention module (AGAM), which encouraged SDetNet to learn differences in the anatomical context of the frontal sinus between males and females. SDetNet showed superior sex determination performance in the area under the receiver operating characteristic curve, accuracy, Brier score, and specificity compared with the other 3D CNNs. Moreover, the results of ablation studies showed a notable improvement in sex determination with the embedding of both MSI and AGAM. Consequently, SDetNet demonstrated automatic and accurate sex determination by learning the anatomical context information of the frontal sinus on CBCT scans.

Deep learning for sex determination: Analyzing over 200,000 panoramic radiographs.

The objective of this study is to assess the performance of an innovative AI-powered tool for sex determination using panoramic radiographs (PR) and to explore factors affecting the performance of the convolutional neural network (CNN). The study involved 207,946 panoramic dental X-rays and their corresponding reports from 15 clinical centers in São Paulo, Brazil. The PRs were acquired with four different devices, and 58% of the patients were female. Data preprocessing included anonymizing the exams, extracting pertinent information from the reports, such as sex, age, type of dentition, and number of missing teeth, and organizing the data into a PostgreSQL database. Two neural network architectures, a standard CNN and a ResNet, were utilized for sex classification, with both undergoing hyperparameter tuning and cross-validation to ensure optimal performance. The CNN model achieved 95.02% accuracy in sex estimation, with image resolution being a significant influencing factor. The ResNet model attained over 86% accuracy in subjects older than 6 years and over 96% in those over 16 years. The algorithm performed better on female images, and the area under the curve (AUC) exceeded 96% for most age groups, except the youngest. Accuracy values were also assessed for different dentition types (deciduous, mixed, and permanent) and missing teeth. This study demonstrates the effectiveness of an AI-driven tool for sex determination using PR and emphasizes the role of image resolution, age, and sex in determining the algorithm's performance.

Correlation among alveolar bone assessments provided by CBCT, micro-CT, and 14 T MRI.

OBJECTIVES: The aim of this study was to evaluate bone mineral adipose tissue (BMAT) volume in 21 alveolar bone specimens, as determined by 14 T MRI, and correlate them to the radiodensity values obtained pre-operatively of regions of interest (ROIs) by cone beam computed tomography (CBCT), and to the bone-volume-to-tissue-volume ratio values obtained by micro-CT, the gold-standard for morphometric data collection. METHODS: Partially edentulous patients were submitted to a CBCT scan, and the radiographic bone densities in each ROI were automatically calculated using coDiagnostiX software. Based on the CBCT surgical planning, a CAD/CAM stereolithographic surgical guide was fabricated to retrieve a bone biopsy from the same ROIs scanned preoperatively, and then to orientate the subsequent implant placement. The alveolar bone biopsies were then collected and scanned using the micro-CT and 14 T MRI techniques. Pearson's correlation test was performed to correlate the results obtained using the three different techniques. RESULTS: In the 21 eligible bone specimens (6 females, 15 males), age (mean age 52.9 years), micro-CT, and 14 T MRI variables were found to be normally distributed (p > 0.05). The strongest-and only statistically significant (p < 0.05)-correlation was found between micro-CT and 14 T MRI values (r = 0.943), and the weakest, between 14 T MRI and CBCT values (r = -0.068). CONCLUSIONS: The findings suggest that 14 T MRI can be used to evaluate BMAT as an indirect marker for bone volume, and that CBCT is not a reliable technique to provide accurate bone density values.

Influence of receiver bandwidth on MRI artifacts caused by orthodontic brackets composed of different alloys.

PURPOSE: The aim of this in vitro study was to assess the role of bandwidth on the area of magnetic resonance imaging (MRI) artifacts caused by orthodontic appliances composed of different alloys, using different pulse sequences in 1.5 T and 3.0 T magnetic fields. MATERIALS AND METHODS: Different phantoms containing orthodontic brackets (ceramic, ceramic bracket with a stainless-steel slot, and stainless steel) were immersed in agar gel and imaged in 1.5 T and 3.0 T MRI scanners. Pairs of gradient-echo (GE), spin-echo (SE), and ultrashort echo time (UTE) pulse sequences were used differing in bandwidth only. The area of artifacts from orthodontic devices was automatically estimated from pixel value thresholds within a region of interest (ROI). Mean values for similar pulse sequences differing in bandwidth were compared at 1.5 T and 3.0 T using analysis of variance. RESULTS: The comparison of groups revealed a significant inverse association between bandwidth values and artifact areas of the stainless-steel bracket and the self-ligating ceramic bracket with a stainless-steel slot (P<0.05). The areas of artifacts from the ceramic bracket were the smallest, but were not reduced significantly in pulse sequences with higher bandwidth values (P<0.05). Significant differences were also observed between 1.5 T and 3.0 T MRI using SE and UTE, but not using GE 2-dimensional or 3-dimensional pulse sequences. CONCLUSION: Higher receiver bandwidth might be indicated to prevent artifacts from orthodontic appliances in 1.5 T and 3.0 T MRI using SE and UTE pulse sequences.

Full Digital Workflow for Anterior Immediate Implants Using Custom Abutments.

The full digital workflow involves the combination of intraoral and cone beam computerized tomography scans. In the present case report, a second intraoral scan is performed after soft tissue management facilitated by the use of a 3-dimensional-printed interim implant restoration. The new STL file resulting from the second intraoral scan can be associated with the previous STL from the initial intraoral scan. The custom abutment was also digitally designed as an STL file, and no implant scan bodies were required for intraoral scanning.

Correlation between magnetic resonance imaging and cone-beam computed tomography for maxillary sinus graft assessment.

PURPOSE: Little is known regarding the accuracy of clinical magnetic resonance imaging (MRI) protocols with acceptable scan times in sinus graft assessment. The aim of this study was to evaluate the correlations between MRI and cone-beam computed tomographic (CBCT) measurements of maxillary sinus grafts using 2 different clinical MRI imaging protocols. MATERIALS AND METHODS: A total of 15 patients who underwent unilateral sinus lift surgery with biphasic calcium phosphate were included in this study. CBCT, T1-weighted MRI, and T2-weighted MRI scans were taken 6 months after sinus lift surgery. Linear measurements of the maximum height and buccolingual width in coronal images, as well as the maximum anteroposterior depth in sagittal images, were performed by 2 trained observers using CBCT and MRI Digital Imaging and Communication in Medicine files. Microcomputed tomography (micro-CT) was also performed to confirm the presence of bone tissue in the grafted area. Correlations between MRI and CBCT measurements were assessed with the Pearson test. RESULTS: Significant correlations between CBCT and MRI were found for sinus graft height (T1-weighted, r=0.711 and P<0.05; T2-weighted, r=0.713 and P<0.05), buccolingual width (T1-weighted, r=0.892 and P<0.05; T2-weighted, r=0.956 and P<0.05), and anteroposterior depth (T1-weighted, r=0.731 and P<0.05; T2-weighted, r=0.873 and P<0.05). The presence of bone tissue in the grafted areas was confirmed via micro-CT. CONCLUSION: Both MRI pulse sequences tested can be used for sinus graft measurements, as strong correlations with CBCT were found. However, correlations between T2-weighted MRI and CBCT were slightly higher than those between T1-weighted MRI and CBCT.

Comparison between different cone-beam computed tomography devices in the detection of mechanically simulated peri-implant bone defects.

PURPOSE: This study compared 2 cone-beam computed tomography (CBCT) systems in the detection of mechanically simulated peri-implant buccal bone defects in dry human mandibles. MATERIALS AND METHODS: Twenty-four implants were placed in 7 dry human mandibles. Peri-implant bone defects were created in the buccal plates of 16 implants using spherical burs. All mandibles were scanned using 2 CBCT systems with their commonly used acquisition protocols: i-CAT Gendex CB-500 (Imaging Sciences, Hatfield, PA, USA; field of view [FOV], 8 cm×8 cm; voxel size, 0.125 mm; 120 kVp; 5 mA; 23 s) and Orthopantomograph OP300 (Intrumentarium, Tuusula, Finland; FOV, 6 cm×8 cm; voxel size, 0.085 mm; 90 kVp; 6.3 mA; 13 s). Two oral and maxillofacial radiologists assessed the CBCT images for the presence of a defect and measured the depth of the bone defects. Diagnostic performance was compared in terms of the area under the curve (AUC), accuracy, sensitivity, specificity, and intraclass correlation coefficient. RESULTS: High intraobserver and interobserver agreement was found (P<0.05). The OP300 showed slightly better diagnostic performance and higher detection rates than the CB-500 (AUC, 0.56±0.03), with a mean accuracy of 75.0%, sensitivity of 81.2%, and specificity of 62.5%. Higher contrast was observed with the CB-500, whereas the OP300 formed more artifacts. CONCLUSION: Within the limitations of this study, the present results suggest that the choice of CBCT systems with their respective commonly used acquisition protocols does not significantly affect diagnostic performance in detecting and measuring buccal peri-implant bone loss.

Comparison of the diagnostic performance of panoramic and occlusal radiographs in detecting submandibular sialoliths.

PURPOSE: The aim of this study was to assess and compare the diagnostic performance of panoramic and occlusal radiographs in detecting submandibular sialoliths. MATERIALS AND METHODS: A total of 40 patients (20 cases and 20 controls) were included in this retrospective study. Cases were defined as subjects with a submandibular sialolith confirmed by computed tomography (CT), whereas controls did not have any submandibular calcifications. Three observers with different expertise levels assessed panoramic and occlusal radiographs of all subjects for the presence of sialoliths. Intraobserver and interobserver agreement were assessed using the kappa test. Sensitivity, specificity, accuracy, positive and negative predictive values, and the diagnostic odds ratio of panoramic and occlusal radiographs in screening for submandibular sialoliths were calculated for each observer. RESULTS: The sensitivity and specificity values for occlusal and panoramic radiographs all ranged from 80% to 100%. The lowest values of sensitivity and specificity observed among the observers were 82.6% and 80%, respectively (P=0.001). Intraobserver and interobserver agreement were higher for occlusal radiographs than for panoramic radiographs, although panoramic radiographs demonstrated a higher overall accuracy. CONCLUSION: Both panoramic and occlusal radiographic techniques displayed satisfactory diagnostic performance and should be considered before using a CT scan to detect submandibular sialoliths.