Abstract

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.

Clinical Implications

The AI-driven segmentation of prosthetic crowns on CBCT scans can diminish the impact of artifacts on the resulting 3-dimensional (3D) cast, thus enhancing the accuracy of the AI algorithms used for automated surface-based intraoral scan-to-CBCT registration. This functionality renders it a valuable tool for generating accurate 3D casts of both soft and hard tissues in preoperative digital dental implant planning.

The implementation of digital tools in implant dentistry has enhanced the prediction and accuracy of both dental implant planning and its guided placement.1, 2 Cone beam computed tomography (CBCT) has become an indispensable tool in implant dentistry, providing detailed 3-dimensional (3D) imaging for precise diagnosis, treatment planning, and surgical guidance.3, 4, 5 However, relying solely on CBCT assessment is insufficient to capture all patient information because of its limitations in depicting soft tissue and detailed dental anatomy.⁶ Therefore, an intraoral scan (IOS) must be registered with the CBCT scan to ensure visualization of both hard and soft tissues.7, 8, 9

The segmentation of CBCT with prominent metal artifact expression poses considerable challenges. Artifacts can originate from sources that include prosthetic crowns, dental implants, dental restorations, and orthodontic brackets10, 11 and may obscure the true dental anatomy, resulting in segmented crown anatomy from an CBCT scan that may not accurately reflect those observed in IOSs.12, 13 Consequently, the IOS-to-CBCT registration process typically entails identifying common points within segmented natural tooth crowns or prosthetic crowns derived from CBCT scans, as well as the crowns captured by IOSs. Nevertheless, when the CBCT scans exhibit artifacts, locating these shared points between the 2 distinct 3D datasets becomes challenging.14, 15, 16, 17

Artificial intelligence (AI) has recently been incorporated into CBCT segmentation, demonstrating its ability to produce high-quality segmentations of CBCT scans even when dealing with prominent artifacts from sources such as dental devices.11, 18, 19, 20, 21, 22, 23 Additionally, AI has been implemented in the IOS-to-CBCT registration process, autonomously performing this task without human intervention.9, 24, 25, 26, 27

As efforts to integrate AI-based solutions into digital workflows, there remains a lack of evidence concerning the implementation and evaluation of clinically applicable AI-driven tools for accurately segmenting prosthetic crowns on CBCT and registering IOSs with CBCT scans, especially in scenarios with high metal artifact expression.²⁸ The aim of this study was to validate an AI-based tool for prosthetic crown segmentation on CBCT scans and IOS-to-CBCT registration in scenarios with significant artifact expression (containing at least 4 prosthetic crowns) by comparing its performance with a semi-automated approach (reference group) regarding accuracy, time efficiency, and consistency. The null hypothesis was that an AI-based approach to prosthetic crown segmentation and subsequent IOS-to-CBCT registration would have the same accuracy, time efficiency, and consistency as the semi-automated approach.

‍