No abstract

Objective To qualitatively and quantitatively assess integrated segmentation of three convolutional neural network (CNN) models for the creation of a maxillary virtual patient (MVP) from cone-beam computed tomography (CBCT) images. Materials and methods A dataset of 40 CBCT scans acquired with different scanning parameters was selected. Three previously validated individual CNN models were integrated to achieve a combined segmentation of maxillary complex, maxillary sinuses, and upper dentition. Two experts performed a qualitative assessment, scoring-integrated segmentations from 0 to 10 based on the number of required refinements. Furthermore, experts executed refinements, allowing performance comparison between integrated automated segmentation (AS) and refined segmentation (RS) models. Inter-observer consistency of the refinements and the time needed to create a full-resolution automatic segmentation were calculated. Results From the dataset, 85% scored 7–10, and 15% were within 3–6. The average time required for automated segmentation was 1.7 min. Performance metrics indicated an excellent overlap between automatic and refined segmentation with a dice similarity coefficient (DSC) of 99.3%. High inter-observer consistency of refinements was observed, with a 95% Hausdorff distance (HD) of 0.045 mm. Conclusion The integrated CNN models proved to be fast, accurate, and consistent along with a strong interobserver consistency in creating the MVP. Clinical relevance The automated segmentation of these structures simultaneously could act as a valuable tool in clinical orthodontics, implant rehabilitation, and any oral or maxillofacial surgical procedures, where visualization of MVP and its relationship with surrounding structures is a necessity for reaching an accurate diagnosis and patient-specific treatment planning.

No abstract

No abstract

No abstract

Accurate mandibular canal (MC) detection is crucial to avoid nerve injury during surgical procedures. Moreover, the anatomic complexity of the interforaminal region requires a precise delineation of anatomical variations such as the anterior loop (AL). Therefore, CBCT-based presurgical planning is recommended, even though anatomical variations and lack of MC cortication make canal delineation challenging. To overcome these limitations, artificial intelligence (AI) may aid presurgical MC delineation. In the present study, we aim to train and validate an AI-driven tool capable of performing accurate segmentation of the MC even in the presence of anatomical variation such as AL. Results achieved high accuracy metrics, with 0.997 of global accuracy for both MC with and without AL. The anterior and middle sections of the MC, where most surgical interventions are performed, presented the most accurate segmentation compared to the posterior section. The AI-driven tool provided accurate segmentation of the mandibular canal, even in the presence of anatomical variation such as an anterior loop. Thus, the presently validated dedicated AI tool may aid clinicians in automating the segmentation of neurovascular canals and their anatomical variations. It may significantly contribute to presurgical planning for dental implant placement, especially in the interforaminal region.

AimTo assess the influence of artefacts generated by metal posts on the detection of simulated internal root resorption (IRR) in adjacent teeth using cone‐beam computed tomography (CBCT) and to verify the impact of metal artefact reduction (MAR) on these cases.MethodologyCBCT images of 14 premolar teeth were acquired before and after IRR simulation using chemical and mechanical procedures, in an OP300 Maxio unit, with and without MAR. Each tooth was placed in the socket of a human mandible and scanned under three different conditions: (i) without adjacent teeth – control group; (ii) distal adjacent tooth restored with metal post; and (iii) with both adjacent teeth restored with metal post. Five oral radiologists scored the IRR detection using a 5‐point scale. Diagnostic values were obtained for the tested groups and compared using two‐way analysis of variance (α = 0.05).ResultsThe presence of a single adjacent tooth restored with metal post did not significantly influence the diagnostic values for IRR detection (P > 0.05). The presence of both adjacent teeth with metal posts, without MAR application, was associated with a significantly lower area under the ROC curve (Az) compared to the control (P = 0.0182). In this case, the application of MAR increased Az, leading to nonsignificant differences from the control group and the group with one adjacent restored tooth (P > 0.05). Sensitivity decreased significantly when two adjacent restored teeth were present, regardless of MAR application (P = 0.0379). Specificity was not affected by the conditions tested (P > 0.05).ConclusionCBCT detection of IRR was impaired by artefacts only when both adjacent teeth restored with metal posts were present. In such cases, activation of MAR improved the performance on this diagnostic task.

Objectives: To evaluate the influence of the level of three micro-CT reconstruction tools: beam-hardening correction (BHC), smoothing filter (SF), and ring artefact correction (RAC) on the fractal dimension (FD) analysis of trabecular bone. Methods: Five Wistar rats’ maxillae were individually scanned in a SkyScan 1174 micro-CT device, under the following settings: 50 kV, 800 µA, 10.2 µm voxel size, 0.5 mm Al filter, rotation step 0.5°, two frames average, 180° rotation and scan time of 35 min. The raw images were reconstructed under the standard protocol (SP) recommended by the manufacturer, a protocol without any artefact correction tools (P0) and 35 additional protocols with different combinations of SF, RAC and BHC levels. The same volume of interest was established in all reconstructions for each maxilla and the FD was calculated using the Kolmogorov (box counting) method. One-way ANOVA with Dunnet’s post-hoc test was used to compare the FD of each reconstruction protocol (P0–P35) with the SP (α = 5%). Multiple linear regression verified the dependency of reconstruction tools in FD. Results: Overall, FD values are not dependent on RAC (p = 0.965), but increased significantly when the level of BHC and SF increased (p < 0.001). FD values from protocols with BHC at 45% combined with SF of 2, and BHC at 30% combined with SF of 4 or 6 had no statistical difference compared to SP. Conclusions: BHC and SF tools affect the FD values of micro-CT images of the trabecular bone. Therefore, these reconstruction parameters should be standardized when the FD is analyzed.