A Novel Digital Implant Planning Workflow in Patients with Preexisting Metal Restorations: A Technical Report

An AI-based tool for prosthetic crown segmentation serving automated intraoral scan-to-CBCT registration in challenging high artifact scenarios

STATEMENT OF PROBLEM

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.

PURPOSE

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.

MATERIAL AND METHODS

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).

RESULTS

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.

CONCLUSIONS

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.

Single scanning of CBCT and intraoral scanning for guided implantation in terminal dentitions with multi-unit metal restorations: technical note

When anatomical landmarks are missing or obstructed by metal artefacts, it is challenging to accurately merge cone beam computed tomography (CBCT) and intraoral scanning (IOS) information, and the accuracy of the implant surgical guides would be compromised. This article describes a novel technical note using oral wound dressings and flowable resin as additional new radiopaque fiducial landmarks to design surgical guides for full-arch immediate implant placement. This technical note provided an accurate, convenient, and cost-effective option for the clinician.

The in-vitro accuracy of fiducial marker-based versus markerless registration of an intraoral scan with a cone-beam computed tomography scan in the presence of restoration artifact

OBJECTIVES

To determine the effect of restoration artifact ('metal artifact') on registration accuracy of an intraoral scan and cone-beam computed tomography (CBCT) scan, comparing fiducial marker-based registration with markerless registration.

MATERIALS AND METHODS

A maxillary model was fitted with multiple configurations of zirconia crowns to simulate various states of oral rehabilitation. Intraoral scans and CBCT scans (half and full rotation) were acquired. Registration was performed using markerless (point-based registration with surface-based refinement) and fiducial marker-based registration. Each experimental condition was repeated 10 times (n = 320). The absolute deviation was measured at the canines and first molars, and the average and maximum values were analysed using multiple linear regression.

RESULTS

R2 was 0.874 for average error and 0.858 for maximum error. For markerless registration, there were 0.041 mm (p < .001) and 0.045 mm (p < .001) increases in average and maximum error per crown, respectively. For fiducial marker-based registration, the effect of additional crowns was not statistically significant for average (p = .067) or maximum (p = .438) error. For a full arch of crowns, the regression model predicted average and maximum errors of 0.581 and 0.697 mm for the markerless technique, and 0.185 and 0.210 mm for the fiducial marker-based technique. Overall, the fiducial marker-based technique was more accurate for four or more crowns. The half rotation scan increased average error by 0.021 mm (p = .001) and maximum error by 0.029 mm (p < .001).

CONCLUSIONS

Under the present study's experimental conditions, the fiducial marker-based technique should be considered if four or more full-coverage highly radiopaque restorations are present.

Comparative Analysis between 3D-Printed Models Designed with Generic and Dental-Specific Software

With the great demand in the market for new dental software, the need has been seen to carry out a precision study for applications in digital dentistry, for which there is no comparative study, and there is a general ignorance regarding their applications. The purpose of this study was to investigate the accuracy differences between digital impressions obtained using generic G-CAD (general CAD) and D-CAD (CAD dental) software. Today, there is a difference between the design software used in dentistry and these in common use. Thus, it is necessary to make a comparison of precision software for specific and generic dental use. We hypothesized that there is no significant difference between the software for specific and general dental use.

METHODS

A typodont was digitized with an intraoral scanner and the models obtained were exported in STL format to four different softwares (Autodesk MeshMixer 3.5, Exocad Dental, Blender for dental, and InLAB). The STL files obtained by each software were materialized using a 3D printer. The printed models were scanned and exported in STL files, with which six pairs of groups were formed. The groups were compared using analysis software (3D Geomagic Control X) by superimposing them in the initial alignment order and using the best fit method.

RESULTS

There were no significant differences between the four analyzed software types; however, group 4, composed of the combination of D-CAD (Blender-InLAB), obtained the highest average (-0.0324 SD = 0.0456), with a higher accuracy compared to the group with the lowest average (group 5, composed of the combination of the Meshmixer and Blender models), a generic software and a specific software (0.1024 SD = 0.0819).

CONCLUSION

Although no evidence of significant difference was found regarding the accuracy of 3D models produced by G-CAD and D-CAD, combinations of groups where specific dental design software was present showed higher accuracy (precision and trueness). The comparison of the 3D graphics obtained with the superimposition of the digital meshes of the printed models performed with the help of the analysis software using the best fit method, replicating the same five reference points for the six groups formed, evidenced a greater tolerance in the groups using D-CAD.