The aim of this study was to evaluate the validity of the bone density value of potential implant sites in HU obtained by a specific cone-beam computed tomography (CBCT) device. In this study, the HU values obtained using a MSCT scanner were used as the gold standard. Twenty mandibles (40 potential implant sites) were scanned using an MSCT scanner (Somatom Sensation 40) and a CBCT scanner (i-CAT). The MSCT images were evaluated using the Syngo CT Workplace software and the CBCT images, using the XoranCat software. The images were evaluated twice by three oral radiologists, at 60 day intervals. The trabecular bone density of the same area was evaluated on both images. Intraclass coefficients (ICC) were calculated to examine the agreement between the examiners and between the two periods of evaluation. The bone density and area of the ROI were compared by the Student t test and Bland-Altman analysis. ICCs were excellent. The mean HU value obtained using CBCT (418.06) was higher than that obtained using MSCT (313.13), with a statistically significant difference (p < 0.0001). In addition, Bland-Altman analysis showed that the HU measures were not equivalent. In conclusion, the bone density in HU with CBCT images obtained using the device studied proved unreliable, since it was higher than that obtained using MSCT.
Objectives: To develop and assess the performance of a novel artificial intelligence (AI)‐driven convolutional neural network (CNN)‐based tool for automated three‐dimensional (3D) maxillary alveolar bone segmentation on cone‐beam computed tomography (CBCT) images.Materials and Methods: A total of 141 CBCT scans were collected for performing training (n = 99), validation (n = 12), and testing (n = 30) of the CNN model for automated segmentation of the maxillary alveolar bone and its crestal contour. Following automated segmentation, the 3D models with under‐ or overestimated segmentations were refined by an expert for generating a refined‐AI (R‐AI) segmentation. The overall performance of CNN model was assessed. Also, 30% of the testing sample was randomly selected and manually segmented to compare the accuracy of AI and manual segmentation. Additionally, the time required to generate a 3D model was recorded in seconds (s).Results: The accuracy metrics of automated segmentation showed an excellent range of values for all accuracy metrics. However, the manual method (95% HD: 0.20 ± 0.05 mm; IoU: 95% ± 3.0; DSC: 97% ± 2.0) showed slightly better performance than the AI segmentation (95% HD: 0.27 ± 0.03 mm; IoU: 92% ± 1.0; DSC: 96% ± 1.0). There was a statistically significant difference of the time‐consumed among the segmentation methods (p < .001). The AI‐driven segmentation (51.5 ± 10.9 s) was 116 times faster than the manual segmentation (5973.3 ± 623.6 s). The R‐AI method showed intermediate time‐consumed (1666.7 ± 588.5 s).Conclusion: Although the manual segmentation showed slightly better performance, the novel CNN‐based tool also provided a highly accurate segmentation of the maxillary alveolar bone and its crestal contour consuming 116 times less than the manual approach.
Objectives
The aim of this study was to assess the reliability of four panoramic radiographic findings, both individually and in association, in predicting the absence of corticalization between the mandibular canal and the third molar on cone beam CT (CBCT) images.
Methods
The sample consisted of 72 individuals (142 mandibular third molars) who underwent pre-operative radiographic evaluation before extraction of impacted mandibular third molars. On panoramic radiographs, the most common signs of corticalization (darkening of roots, diversion of mandibular canal, narrowing of mandibular canal and interruption of white line) and the presence or absence of corticalization between the mandibular third molar and the mandibular canal on CBCT images were evaluated.
Results
Darkening of roots and interruption of white line associated with the absence of corticalization between the mandibular third molar and the mandibular canal on CBCT images were statistically significant, both as isolated findings (p = 0.0001 and p = 0.0006, respectively) and in association (p = 0.002). No statistically significant association was observed for the other panoramic radiographic findings, either individually or in association (p > 0.05).
Conclusion
Darkening of roots and interruption of white line observed on panoramic radiographs, both as isolated findings and in association, were effective in determining the risk relationship between the tooth roots and the mandibular canal, requiring three-dimensional evaluation of the case.