scholarly journals A Deep Learning Approach For Dental Implant Planning On Cone-Beam Computed Tomography Images

2021 ◽  
Author(s):  
Sevda Kurt Bayrakdar ◽  
Kaan Orhan ◽  
Ibrahim Sevki Bayrakdar ◽  
Elif Bilgir ◽  
Matvey Ezhov ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Cone Beam Computed Tomography ◽  
Cone Beam ◽  
Rank Test ◽  
Human Observer ◽  
Manual Segmentation ◽  
Support Mechanism ◽  
Computed Tomography Images ◽  
Bone Height ◽  
Missing Tooth

Abstract Background: The aim of this study was to evaluate the success of the artificial intelligence (AI) system in implant planning using three-dimensional cone-beam computed tomography (CBCT) images.Methods: Seventy-five CBCT images were included in this study. In these images, bone height and thickness in 508 regions where implants were required were measured by a human observer with manual segmentation method using InvivoDental 6.0 (Anatomage Inc. San Jose, CA, USA). Also, canals/sinuses/fossae associated with alveolar bones and missing tooth regions were detected. After all of this evaluations were repeated using the deep convolutional neural network (Diagnocat, Inc.) The jaws were separated as mandible/maxilla and each jaw was grouped as anterior/premolar/molar teeth region. The data obtained from manual segmentation and AI methods were compared using Bland-Altman analysis and Wilcoxon signed rank test.Results: In the bone height measurements, there were no statistically significant differences between AI and manual measurements in the premolar region of mandible and the premolar and molar regions of the maxilla (p>0.05). In the bone thickness measurements, there were statistically significant differences between AI and manual measurements in all regions of maxilla and mandible (p<0.001). Also, the percentage of right detection was 72.2% for canals, 66.4% for sinuses/fossae and 95.3% for missing tooth regions.Conclusions: Development of AI systems and their using in future for implant planning will both facilitate the work of physicians and will be a support mechanism in implantology practice to physicians.

scholarly journals A deep learning approach for dental implant planning in cone-beam computed tomography images

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Sevda Kurt Bayrakdar ◽  
Kaan Orhan ◽  
Ibrahim Sevki Bayrakdar ◽  
Elif Bilgir ◽  
Matvey Ezhov ◽  
...  
Keyword(s):  
Computed Tomography ◽  
San Francisco ◽  
Cone Beam Computed Tomography ◽  
Assessment Method ◽  
Cone Beam ◽  
Rank Test ◽  
Human Observer ◽  
Computed Tomography Images ◽  
Bone Height ◽  
Missing Tooth

Abstract Background The aim of this study was to evaluate the success of the artificial intelligence (AI) system in implant planning using three-dimensional cone-beam computed tomography (CBCT) images. Methods Seventy-five CBCT images were included in this study. In these images, bone height and thickness in 508 regions where implants were required were measured by a human observer with manual assessment method using InvivoDental 6.0 (Anatomage Inc. San Jose, CA, USA). Also, canals/sinuses/fossae associated with alveolar bones and missing tooth regions were detected. Following, all evaluations were repeated using the deep convolutional neural network (Diagnocat, Inc., San Francisco, USA) The jaws were separated as mandible/maxilla and each jaw was grouped as anterior/premolar/molar teeth region. The data obtained from manual assessment and AI methods were compared using Bland–Altman analysis and Wilcoxon signed rank test. Results In the bone height measurements, there were no statistically significant differences between AI and manual measurements in the premolar region of mandible and the premolar and molar regions of the maxilla (p > 0.05). In the bone thickness measurements, there were statistically significant differences between AI and manual measurements in all regions of maxilla and mandible (p < 0.001). Also, the percentage of right detection was 72.2% for canals, 66.4% for sinuses/fossae and 95.3% for missing tooth regions. Conclusions Development of AI systems and their using in future for implant planning will both facilitate the work of physicians and will be a support mechanism in implantology practice to physicians.

scholarly journals Does Alt-RAMEC protocol and facemask treatment affect dentoalveolar structures?

2021 ◽  
Author(s):  
Elvan Önem Özbilen ◽  
Hanife Nuray Yılmaz ◽  
Yasemin Bahar Acar
Keyword(s):  
Computed Tomography ◽  
Cone Beam Computed Tomography ◽  
Alveolar Bone ◽  
Cone Beam ◽  
Distributed Data ◽  
Bone Thickness ◽  
Total Reduction ◽  
Computed Tomography Images ◽  
Significant Change ◽  
Bone Height

ABSTRACT Objectives To evaluate dentoalveolar changes immediately after the alternate rapid maxillary expansion and constriction (Alt-RAMEC) protocol and facemask (FM) treatment using cone-beam computed tomography images. Materials and Methods Cone-beam computed tomography images of 20 patients (mean age = 9.64 ± 1.3 years) who received the Alt-RAMEC protocol before FM treatment were retrieved in this retrospective study. Dental and alveolar inclinations, buccal and palatal alveolar bone thickness, and buccal and palatal alveolar bone height changes were measured before treatment (T0), after the Alt-RAMEC protocol (T1), and after FM treatment (T2). Measurements for right and left molars were performed separately. The Shapiro-Wilks test was used to assess the conformity of the parameters to the normal distribution. The paired t-test and repeated measures analysis of variance were used for normally distributed data. The Wilcoxon signed-rank test and Friedman test were used for non-normally distributed data. The Bonferroni correction was used to reduce the chances of obtaining false-positive results. Statistical significance was set at P &lt; .05. Results Buccal alveolar bone thickness and alveolar bone inclinations decreased significantly from T1 to T0 and showed no significant change from T2 to T1. The total reduction T2-T0 was statistically significant. The change in palatal alveolar bone thickness was not significant T1-T0 but increased significantly for T2-T1 and T2-T0. Buccal alveolar bone height, palatal alveolar bone height, and molar inclinations increased significantly T1-T0, but there was no significant change T2-T1. The total reduction at T2-T0 was statistically significant. Conclusions The results of this study revealed that the effects of the Alt-RAMEC protocol on dentoalveolar tissues were similar to the changes reported in the literature after rapid palatal expansion.

scholarly journals Alveolar bone heights of maxillary central incisors in unilateral cleft lip and palate patients using cone-beam computed tomography evaluation

2021 ◽  
Author(s):  
Marcin Stasiak ◽  
Anna Wojtaszek-Słomińska ◽  
Bogna Racka-Pilszak
Keyword(s):  
Computed Tomography ◽  
Cone Beam Computed Tomography ◽  
Cleft Lip ◽  
Cleft Lip And Palate ◽  
Alveolar Bone ◽  
Contralateral Side ◽  
Cone Beam ◽  
Rank Test ◽  
Cross Sectional ◽  
Alveolar Bone Grafting

Abstract Purpose The aims of this retrospective cross-sectional study were to measure and compare labial and palatal alveolar bone heights of maxillary central incisors in unilateral cleft lip and palate patients, following STROBE (Strengthening the Reporting of Observational Studies in Epidemiology) guidelines. Patients and methods The study group consisted of 21 patients with a mean age of 16 years. High-resolution cone-beam computed tomography was performed at least one year after secondary alveolar bone grafting. The experimental side was the cleft side and the contralateral side without congenital cleft was the control. Measurements were performed on incisors’ midsagittal cross-sections. The Wilcoxon signed-rank test was used for intergroup comparisons. Results The labial and palatal distances between alveolar bone crests and cementoenamel junctions were significantly greater on the cleft side than on the noncleft side. Mean differences were 0.75 and 1.41 mm, respectively. The prevalence of dehiscences at the cleft side maxillary central incisors was 52% on the labial surface and 43% on the palatal surface. In the controls, it was 19% and 14%, respectively. Conclusion The cleft-adjacent maxillary central incisors had more apically displaced alveolar bone crests on the labial and palatal sides of the roots than the controls. Higher prevalence of dehiscences was found on the cleft side. Bone margin differences predispose to gingival height differences of the central incisors. These differences could increase the demands of patients to obtain more esthetic treatment results with orthodontic extrusion and periodontal intervention on the cleft side.

Sign in / Sign up

Export Citation Format

Share Document