Acceptability, deviation, and efficiency of automated artificial intelligence-based implant planning methods: A comparison with human intelligence.

To evaluate the feasibility of ultrasound-image-based computer-assisted implant planning and placement. Intraoral scans, cone-beam computerized tomography (CBCT), and ultrasound (US) scans with a custom positioning device were acquired in nine patients. Prosthetic-driven surgical guides were planned and fabricated based on ultrasound images and intraoral scans. Implants were then placed. Postoperative implant position was obtained intra-surgically by intraoral scan. Aside from the ultrasound-based plan, conventional implant planning was performed by the same operator on a pre-surgical CBCT for comparison. Linear deviations between ultrasound and CBCT-planned implant positions were measured and compared with the intra-surgical implant position, and the position deviations between two consecutive plannings were performed on the same CBCT by the same operator. The linear deviation between the 3D scan surface of the edentulous region and the ultrasonographic soft tissue profile segmentation was also assessed with reverse-engineering software. Means, standard deviations, and root mean square differences (RMSD) were calculated for every variable. All the ultrasound-planned implants were successfully placed, and no complications were recorded. The mean deviations in angles, shoulders, and apexes were 5.27 ± 1.75° (RMSD: 5.53°), 0.92 ± 0.26 mm (RMSD: 0.95 mm), and 1.41 ± 0.61 mm (RMSD: 1.53 mm), respectively, between the US and CBCT-planned implants; 2.63 ± 0.43° (RMSD: 2.66°), 1.16 ± 0.30 mm (RMSD: 1.19 mm), and 1.26 ± 0.27 mm (RMSD: 1.28 mm) between the planned implant and intra-surgically recorded positions; and 2.90 ± 1.36° (RMSD: 3.18°), 0.65 ± 0.27 mm (RMSD: 0.70 mm), and 0.99 ± 0.37 mm (RMSD: 1.05 mm) between two consecutive CBCTs planning performed by the same operator. The mean deviation between the 3D surfaces of model scans and ultrasound-derived soft tissue profile in the edentulous area was 0.19 ± 0.08 mm. Ultrasound-guided implant surgery represents a feasible non-ionizing alternative to conventional static guided implant surgical protocols for implant placement in sites with favorable characteristics.

Objective: To compare cone-beam CT (CBCT) and intraoral scanning (IOS) in evaluating dental implant placement accuracy. Methods: This prospective study included patients scheduled for single implant placement at the Department of Oral Implantology, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, from December 2024 to June 2025. Preoperative CBCT and IOS data were acquired, and implant positions were virtually planned following a prosthetically driven approach. Implants were placed freehand according to the planned positions. Postoperatively, CBCT and IOS datasets containing the actual implant positions were obtained. Three-dimensional deviations between the planned and actual implant positions were measured using both CBCT-and IOS-based methods, including apex deviation, platform deviation, angular deviation, as well as mesiodistal, buccolingual, and depth deviations at both apex and platform levels. The Wilcoxon test was used to compare differences between the two measurement methods. A linear mixed-effects model was employed to explore factors influencing the discrepancies between the two methods, including the presence of intraoral restorations, simultaneous bone grafting, CBCT image quality, and tooth region (anterior vs. posterior). Consistency was assessed using the intraclass correlation coefficient (ICC) and Bland-Altman analysis. Results: A total of 36 patients (17 males) with a age of (38.2±10.6) years were included. The median apex deviation, platform deviation, and angular deviation measured by CBCT were 1.4 (1.0) mm, 1.2 (0.8) mm, and 5.2° (4.1°), respectively; those measured by IOS were 1.3 (0.7) mm, 1.0 (0.6) mm, and 4.6° (4.3°), respectively. No statistically significant differences were observed between the two methods for any of the three-dimensional deviation parameters (all P>0.05). The ICCs between the two methods were greater than 0.90, indicating good overall consistency. Bland-Altman analysis revealed that the 95% limits of agreement (LoA) for the difference in apex linear deviation (IOS minus CBCT) between two methods ranged from -0.67 mm to 0.67 mm, and for the difference in angular deviation ranged from -2.34° to 2.64°. The mixed-effects model identified the presence of intraoral restorations as a significant factor affecting discrepancies between the two methods in platform depth, apex depth, and apex mesiodistal deviation. Conclusions: IOS and CBCT methods demonstrated comparable accuracy and relatively high consistency in measuring three-dimensional implant placement deviations. However, the 95% limits of agreement for the measurement discrepancies were relatively wide.

A double-blind randomized crossover trial comparing the esthetic outcomes of CAD-CAM provisional restorations fabricated using CBCT and IOS acquisition methods.

Accurately registering intraoral and cone beam computed tomography (CBCT) scans in patients with metal artifacts poses a significant challenge. Whether a cloud-based platform trained for artificial intelligence (AI)-driven segmentation can improve registration is unclear. The purpose of this clinical study was to validate a cloud-based platform trained for the AI-driven segmentation of prosthetic crowns on CBCT scans and subsequent multimodal intraoral scan-to-CBCT registration in the presence of high metal artifact expression. A dataset consisting of 30 time-matched maxillary and mandibular CBCT and intraoral scans, each containing at least 4 prosthetic crowns, was collected. CBCT acquisition involved placing cotton rolls between the cheeks and teeth to facilitate soft tissue delineation. Segmentation and registration were compared using either a semi-automated (SA) method or an AI-automated (AA). SA served as clinical reference, where prosthetic crowns and their radicular parts (natural roots or implants) were threshold-based segmented with point surface-based registration. The AA method included fully automated segmentation and registration based on AI algorithms. Quantitative assessment compared AA's median surface deviation (MSD) and root mean square (RMS) in crown segmentation and subsequent intraoral scan-to-CBCT registration with those of SA. Additionally, segmented crown STL files were voxel-wise analyzed for comparison between AA and SA. A qualitative assessment of AA-based crown segmentation evaluated the need for refinement, while the AA-based registration assessment scrutinized the alignment of the registered-intraoral scan with the CBCT teeth and soft tissue contours. Ultimately, the study compared the time efficiency and consistency of both methods. Quantitative outcomes were analyzed with the Kruskal-Wallis, Mann-Whitney, and Student t tests, and qualitative outcomes with the Wilcoxon test (all α=.05). Consistency was evaluated by using the intraclass correlation coefficient (ICC). Quantitatively, AA methods excelled with a 0.91 Dice Similarity Coefficient for crown segmentation and an MSD of 0.03 ±0.05 mm for intraoral scan-to-CBCT registration. Additionally, AA achieved 91% clinically acceptable matches of teeth and gingiva on CBCT scans, surpassing SA method's 80%. Furthermore, AA was significantly faster than SA (P<.05), being 200 times faster in segmentation and 4.5 times faster in registration. Both AA and SA exhibited excellent consistency in segmentation and registration, with ICC values of 0.99 and 1 for AA and 0.99 and 0.96 for SA, respectively. The novel cloud-based platform demonstrated accurate, consistent, and time-efficient prosthetic crown segmentation, as well as intraoral scan-to-CBCT registration in scenarios with high artifact expression.

BackgroundThis study highlights the need for precise and efficient methods to measure palatal mucosal thickness in the maxillary anterior teeth, particularly for soft tissue augmentation in the aesthetic zone. The research evaluates three digital imaging techniques, suggesting that Cone Beam Computed Tomography (CBCT) combined with intraoral scanners (IOS) is a promising approach for reliable clinical assessment.MethodsTen volunteers with healthy periodontium were selected, and three methods were employed: CBCT-based indirect gingival imaging, modified soft tissue CBCT (ST-CBCT), and CBCT combined with IOS. Measurements of palatal mucosal thickness were taken at multiple points along the palatal gingival margin. Statistical analysis included Bland-Altman plots for method agreement and intraclass Correlation Coefficient (ICC) analysis for reliability. All measurements were standardized, repeated for consistency, and accurate to 0.01 mm to ensure reliability.ResultsThe Bland-Altman plots showed that less than 5% of the points for palatal mucosal thickness differences measured by the gingival indirect radiographic method, modified ST-CBCT, and CBCT combined with IOS were located outside the 95% limits of agreement (LoA). The mean value of the differences was within 0.2 mm, indicating good clinical agreement among the three methods. The inter- and intra-study ICC values for palatal mucosal thickness measurements of the maxillary anterior teeth using the three CBCT methods were greater than 0.75 (P < 0.001), demonstrating reproducibility.ConclusionsBased on the evaluation of three digital imaging techniques, this study indicates that the combination of CBCT with IOS is a feasible method for measuring palatal mucosal thickness in the maxillary anterior teeth and demonstrates good reproducibility.

An alternative radiation-free method for assessing the accuracy of robotic computer-assisted implant surgery: a cross-sectional study.

PurposeA fully digital approach to oral prosthodontic rehabilitation requires the possibility of combining (i.e., registering) digital documentation from different sources. This becomes more complex in an edentulous jaw, as fixed dental markers to perform reliable registration are lacking. This validation study aimed to evaluate the reproducibility of 1) intraoral scanning and 2) soft tissue-based registration of an intraoral scan with a cone-beam computed tomography (CBCT) scan for a fully edentulous upper jaw.Materials and MethodsTwo observers independently performed intraoral scans of the upper jaw in 14 fully edentulous patients. The palatal vault of both surface models was aligned, and the inter-observer variability was assessed by calculating the mean inter-surface distance at the level of the alveolar crest. Additionally, a CBCT scan of all patients was obtained and a soft tissue surface model was generated using patient-specific gray values. This CBCT soft tissue model was registered with the intraoral scans of both observers, and the intraclass correlation coefficient (ICC) was calculated to evaluate the reproducibility of the registration method.ResultsThe mean inter-observer deviation when performing an intraoral scan of the fully edentulous upper jaw was 0.10 ± 0.09 mm. The inter-observer agreement for the soft tissue-based registration method was excellent (ICC=0.94; 95% confidence interval, 0.81–0.98).ConclusionEven when teeth are lacking, intraoral scanning of the jaw and soft tissue-based registration of an intraoral scan with a CBCT scan can be performed with a high degree of precision.

Improving interproximal surface reconstruction via artificial intelligence-based tooth segmentation with crown-root integrated models: A preliminary study.

BackgroundMiniscrews have been used to superimpose three-dimensional (3D) craniofacial images as well as explore stable structures in jaws. Our purpose was to evaluate the reliability and validity of linear and angular measurements made with miniscrews on a 3D cone-beam computed tomography (CBCT) at two voxel sizes and compared to models created by an intraoral scanner (IOS).MethodsAltogether, 64 miniscrews were placed in 12 goat jaws. The jaws were scanned by CBCT machine at 0.12 mm and 0.3 mm voxels and by the IOS. Linear and angular measurements between miniscrews on CBCT at the two voxel settings and the IOS were compared with actual measurements and with each other.ResultsAn intra-and inter-class correlation of 0.961–1.000 were obtained by each method. Linear measurements showed significant overestimations of 0.27 ± 0.24, 0.14 ± 0.22 and 0.15 ± 0.26 mm, and angular measurements showed non-significant differences of 0.11 ± 1.97°, 0.15 ± 2.79° and 0.41 ± 2.34° for the CBCT at 0.12-mm, 0.3-mm voxels and the IOS, respectively. Equal magnification of linear measurements was on homolateral and contralateral sides using CBCT, whereas significantly greater magnification on the homolateral side than on the opposite was observed using the IOS. There was no significant difference with angular measurements between digital CBCT models at two voxels and IOS. In addition, all angular measurements were comparable to actual measurement results.ConclusionsMiniscrews in CBCT and IOS are reliable and clinical valid when used as a reference measuring tooth movement. However, when miniscrews are involved in high precision measurement in CBCT or IOS image, systematic error should be taken into consideration. When comparing CBCT images, using the same voxel size is recommended for miniscrew related measurements to reduce error.

Positional trueness of abutments by using a digital die-merging protocol compared with complete arch direct digital scans and conventional dental impressions

To compare the three-dimensional (3D) linear displacements and the mesiodistal and buccolingual angulation changes after orthodontic treatment in digital dental models (DDMs) and 3D models derived from cone-beam computed tomography (CBCT). Digital dental model and CBCT scans were selected from 24 adults who had undergone orthodontic treatment for mandibular anterior crowding. 3D linear displacements and changes in angular measurements (mesiodistal and buccolingual angulation) were assessed in pre- and post-treatment DDM and CBCT images using the software ITK-snap and 3D SlicerCMF. Intra- and inter-rater agreement of measurements in DDM and CBCT were tested using the intraclass correlation coefficient (ICC). DDM and CBCT measurements were compared using the Wilcoxon test (P<.05), ICC and Bland-Altman plots. Intra- and inter-rater agreement varied from good (ICC>0.75) to excellent (ICC>0.90) for both DDM and CBCT measurements. Although no significant difference between DDM and CBCT methods was observed for linear measurements of tooth movement, the angular assessments were different for most measurements. The agreement between measurements from both assessments varied from poor to excellent. Longitudinal assessments of tooth movements including 3D linear displacements and mesiodistal and buccolingual angulation are reproducible when using both DDM and CBCT. Changes in angular measurements due to orthodontic treatment are discordant when measured in the digital models (clinical crown) and in the CBCT images (whole tooth).

To determine the accuracy of three-dimensional (3D) printed models fabricated from cone-beam computed tomography (CBCT) scans of human mandibular dry skulls in comparison with models derived from intraoral scanner (IOS) data. Six human mandibular dry skulls were scanned by IOS and CBCT. Digital models (DMs) constructed from the IOS and CBCT data were fabricated physically using a 3D printer. The width and thickness of individual teeth and intercanine and molar widths were measured using a digital caliper. The accuracy of the DMs was compared between IOS and CBCT. Paired t-tests were used for intergroup comparisons. All intraclass correlation coefficient values for the three measurements (mesial-distal, buccal-lingual, width) exceeded 0.9. For the mandibular teeth, there were significant discrepancies in model accuracy between the IOS (average discrepancies of 0.18 ± 0.08 mm and 0.16 ± 0.12 mm for width and thickness, respectively) and CBCT (0.28 ± 0.07 mm for width, 0.37 ± 0.2 mm for thickness; P &lt; .01). Intercanine (P = .38) and molar widths (P = .41) showed no significant difference between groups. There was a statistically significant difference in the accuracy of DMs obtained from CBCT and IOS; however, this did not seem to result in any important clinical difference. CBCT could be routinely used as an orthodontic diagnostic tool and for appliance construction.

Evaluation of root position during orthodontic treatment via multiple intraoral scans with automated registration technology

ObjectivesTo quantitatively assess periodontal soft tissue changes, including gingival thickness and keratinized gingiva width after periodontally accelerated osteogenic orthodontics (PAOO) surgery by digital measurements. MethodsThis study enrolled 15 maxillaries with 89 anterior teeth and 16 mandibles with 94 anterior teeth from Chinese adult patients with skeletal Angle Class III malocclusion for whom PAOO surgery was proposed during orthodontic treatment. Intraoral scanning and cone beam computed tomography (CBCT) examinations were performed before PAOO surgery and 6 months after the surgery. Keratinized gingiva width was measured on the digital model acquired by intraoral scanning. The gingival thickness was measured using a digital three-dimensional (3D) model based on the combination of digital intraoral scanning and CBCT data.ResultsThe mean gingival thickness before surgery was 0.91 ± 0.32 mm and 1.21 ± 0.38 mm at 6-month after PAOO. Patients showed periodontal soft tissue increase with a mean gingival tissue gain of 0.30 ± 0.33 mm. At 1 mm, 2 and 3 mm apical to cemento-enamel junction (CEJ) levels, the gingival thickness increase of the mandible was higher than that of the maxilla (0.38 ± 0.30 mm vs. 0.24 ± 0.31 mm, 0.43 ± 0.35 mm vs. 0.26 ± 0.41 mm, 0.36 ± 0.27 vs. 0.25 ± 0.32 mm, respectively, all P < 0.05). Moreover, the sites of gingival thickness ≤ 1 mm before surgery showed more tissue gain than the sites > 1 mm (0.36 ± 0.32 mm vs. 0.18 ± 0.31 mm, P < 0.001). The mean keratinized gingiva width at T0 was 3.88 ± 1.22 mm, and increased 1.05 ± 1.24 mm 6 months after PAOO surgery. Moreover, a digital 3D model for gingival thickness measurement based on the combination of digital intraoral scanning and CBCT displayed high reliability and accuracy with an intra-class correlation coefficient (ICC) of 0.897.ConclusionPAOO could improve an insufficient quantity of periodontal soft and hard tissues in patients with skeletal Angle Class III malocclusion, including the gingival thickness and keratinized gingiva width. A digital 3D model based on the combination of digital intraoral scanning and CBCT data could provide a new digital measurement of gingival thickness with high accuracy and reliability.

Accuracy and reliability of mandibular digital model registration with use of the mucogingival junction as the reference