口内扫描数据伪影自动去除研究

Cone-beam computed tomography (CBCT) plays a crucial role in dental clinical applications, but metal implants often cause severe artifacts, challenging accurate diagnosis. Most deep learning-based methods attempt to achieve metal artifact reduction (MAR) by training neural networks on paired simulated data. However, they often struggle to preserve anatomical structures around metal implants, and fail to bridge the domain gap between real-world and simulated data, leading to suboptimal performance in practice. To address these issues, we propose a two-stage diffusion framework with a strong emphasis on structure preservation and domain generalization. In Stage I, a structure-aware diffusion model is trained to extract artifact-free clean edge maps from artifact-affected CBCT images. This training is supervised by the tooth contours derived from the fusion of intraoral scan (IOS) data and CBCT images to improve generalization to real-world data. In Stage II, these extracted clean edge maps serve as structural priors to guide the MAR process. Additionally, we introduce a segmentation-guided sampling (SGS) strategy in this stage to further enhance structure preservation during inference. Experiments on both simulated and real-world data demonstrate that our method achieves superior artifact reduction and better preservation of dental structures compared to competing approaches.

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.

Low-dose dental cone beam computed tomography (CBCT) has been increasingly used for maxillofacial modeling. However, the presence of metallic inserts, such as implants, crowns, and dental filling, causes severe streaking and shading artifacts in a CBCT image and loss of the morphological structures of the teeth, which consequently prevents accurate segmentation of bones. A two-stage metal artifact reduction method is proposed for accurate 3D low-dose maxillofacial CBCT modeling, where a key idea is to utilize explicit tooth shape prior information from intra-oral scan data whose acquisition does not require any extra radiation exposure. In the first stage, an image-to-image deep learning network is employed to mitigate metal-related artifacts. To improve the learning ability, the proposed network is designed to take advantage of the intra-oral scan data as side-inputs and perform multi-task learning of auxiliary tooth segmentation. In the second stage, a 3D maxillofacial model is constructed by segmenting the bones from the dental CBCT image corrected in the first stage. For accurate bone segmentation, weighted thresholding is applied, wherein the weighting region is determined depending on the geometry of the intra-oral scan data. Because acquiring a paired training dataset of metal-artifact-free and metal artifact-affected dental CBCT images is challenging in clinical practice, an automatic method of generating a realistic dataset according to the CBCT physics model is introduced. Numerical simulations and clinical experiments show the feasibility of the proposed method, which takes advantage of tooth surface information from intra-oral scan data in 3D low dose maxillofacial CBCT modeling.

Reliable 3D-2D alignment between intraoral scan (IOS) models and lateral cephalometric radiographs is critical for orthodontic diagnosis, yet conventional intensity-driven registration methods struggle under real clinical conditions, where cephalograms exhibit magnification, distortion, low-contrast dental crowns, and acquisition-dependent variation. These factors hinder the stability of appearance-based metrics and often lead to convergence failures or anatomically implausible alignments. To address these limitations, we propose DentalSCR, named for its silhouette-to-contour registration scheme, a pose-stable and contour-guided framework for accurate and interpretable alignment that achieves state-of-the-art performance. Our method constructs a U-Midline Dental Axis (UMDA) to establish a unified cross-arch anatomical coordinate system, stabilizing initialization and standardizing projection geometry across cases. Using this reference frame, we generate radiograph-like projections via a surface-based DRR (Digitally Reconstructed Radiograph) formulation with coronal-axis perspective and Gaussian splatting, which preserves clinically accurate magnification and emphasizes external silhouettes. Registration is formulated as a 2D similarity transform optimized with a symmetric bidirectional Chamfer distance under a hierarchical coarse-to-fine schedule, enabling both large capture range and subpixel-level contour agreement. We evaluate DentalSCR on 34 expert-annotated cases. Results demonstrate substantial reductions in landmark error, particularly at posterior teeth, tighter lower-jaw dispersion, and low Chamfer and controlled Hausdorff distances. These findings indicate that DentalSCR robustly handles real-world cephalograms and delivers high-fidelity, clinically inspectable 3D-2D alignment, consistently outperforming baselines and establishing a new state-of-the-art.

Metal implants introduce severe artifacts in CT images, compromising diagnostic reliability. Supervised metal artifact reduction (MAR) models trained on simulated data are effective but often fail due to domain gaps when applied to real clinical data. Unsupervised methods trained on real images avoid such gaps but suffer from weak artifact suppression and training instability. To address these challenges, we propose d-MAR, a novel MAR framework that performs diffusion-driven domain transformations between simulated and real image domains. Specifically, real image domain (RID) data is transformed into the simulated image domain (SID), processed by a MAR model trained on simulation-paired data, and transformed back into RID. We harness diffusion models as a transformation bridge and introduce two targeted conditional sampling techniques-conditional input and sampling enhancement-based on Fourier-extracted low-frequency image components. This enables domain alignment without random generation, ensuring consistent anatomical fidelity. The proposed d-MAR can reduce real metal artifacts originating from different scanning protocols and devices with a MAR model trained with simulated paired data. Evaluations on Clinical Head, Clinical Body, and dental CBCT datasets show that d-MAR consistently outperforms conventional MAR methods in both quantitative metrics and visual quality, demonstrating strong generalization capability. The d-MAR code is publicly available at https://github.com/guoyii/d-MAR.

Cone beam computed tomography (CBCT) is widely used in dental treatment due to its low radiation dose and cost. However, it has lower image quality compared to Multi Detector Computed Tomography (MDCT), limiting its use in precision medical examinations. Recent research has focused on using generative models, particularly Cycle-GAN, to transform low-resolution CBCT images into high-resolution MDCT-like images. Although Cycle-GAN has shown promising results, it often produces shading artifacts that compromise image quality. In this paper, we propose a fine-tuning method that integrates human feedback with style transfer techniques to effectively address this issue, thereby improving the model’s adaptability and performance. Our method involves re-training the Cycle-GAN generator to learn and replicate the feature distribution of clean MDCT images, significantly reducing shading artifacts and preserving morphological structures. Experimental results demonstrate that our proposed fine-tuning method effectively reduces artifacts and enhances image quality. Additionally, our selective training technique ensures the preservation of local morphological structures, leading to better outcomes compared to non-selective training methods. This approach provides a reliable and efficient solution for generating high-resolution, artifact-free MDCT-like images from cost-effective CBCT scans, with the potential to greatly benefit clinical diagnostics and patient outcomes.

High cone-angle artifacts (HCAAs) appear frequently in circular cone-beam computed tomography (CBCT) images and can heavily affect diagnosis and treatment planning. To reduce HCAAs in CBCT scans, we propose a novel deep learning approach that reduces the three-dimensional (3D) nature of HCAAs to two-dimensional (2D) problems in an efficient way. Specifically, we exploit the relationship between HCAAs and the rotational scanning geometry by training a convolutional neural network (CNN) using image slices that were radially sampled from CBCT scans. We evaluated this novel approach using a dataset of input CBCT scans affected by HCAAs and high-quality artifact-free target CBCT scans. Two different CNN architectures were employed, namely U-Net and a mixed-scale dense CNN (MS-D Net). The artifact reduction performance of the proposed approach was compared to that of a Cartesian slice-based artifact reduction deep learning approach in which a CNN was trained to remove the HCAAs from Cartesian slices. In addition, all processed CBCT scans were segmented to investigate the impact of HCAAs reduction on the quality of CBCT image segmentation. We demonstrate that the proposed deep learning approach with geometry-aware dimension reduction greatly reduces HCAAs in CBCT scans and outperforms the Cartesian slice-based deep learning approach. Moreover, the proposed artifact reduction approach markedly improves the accuracy of the subsequent segmentation task compared to the Cartesian slice-based workflow.

Motion artifacts are a major factor that can degrade the diagnostic performance of computed tomography (CT) images. In particular, the motion artifacts become considerably more severe when an imaging system requires a long scan time such as in dental CT or cone-beam CT (CBCT) applications, where patients generate rigid and non-rigid motions. To address this problem, we proposed a new real-time technique for motion artifacts reduction that utilizes a deep residual network with an attention module. Our attention module was designed to increase the model capacity by amplifying or attenuating the residual features according to their importance. We trained and evaluated the network by creating four benchmark datasets with rigid motions or with both rigid and non-rigid motions under a step-and-shoot fan-beam CT (FBCT) or a CBCT. Each dataset provided a set of motion-corrupted CT images and their ground-truth CT image pairs. The strong modeling power of the proposed network model allowed us to successfully handle motion artifacts from the two CT systems under various motion scenarios in real-time. As a result, the proposed model demonstrated clear performance benefits. In addition, we compared our model with Wasserstein generative adversarial network (WGAN)-based models and a deep residual network (DRN)-based model, which are one of the most powerful techniques for CT denoising and natural RGB image deblurring, respectively. Based on the extensive analysis and comparisons using four benchmark datasets, we confirmed that our model outperformed the aforementioned competitors. Our benchmark datasets and implementation code are available at https://github.com/youngjun-ko/ct_mar_attention.

Providing patients a functional and aesthetic dentition traditionally entails a labor-intensive process and numerous appointments are required to successfully complete these preliminary steps prior to delivering the final restorations. Advancements in dental technology have substantially simplified this arborous process by streamlining workflow thus reducing patient in-office time, and allowing patients the ability to view the result before committing to a treatment plan. This case report described a digital workflow including use of an intraoral scanner, a 3dimensional (3-D) face-scan application on smartphone, and a digital design software to achieve the patient’s desired smile transformation. A 30-year-old female presented to the clinic with a chief complaint of dissatisfaction with her current smile. Clinical examination revealed asymmetrical central incisors, peglateral incisors, and extrinsic staining. After multiple treatment options were discussed, she opted for six maxillary all-ceramic veneers. The preliminary steps included digital photographs and intraoral scans (Trios 3, 3 Shape, Copenhagen, Denmark) of the patient’s current dentition (Fig. 1A and B). To obtain the face scan, a 3-D face scanning application (Bellus3D Inc., Campbell, CA, USA) on a smartphone (iPhone 12, Apple Inc., Cupertino, CA, USA) was used. For face scanning procedure, the patient centered her face on the screen of the smartphone and then turned her head to

In dental cone-beam computed tomography (CBCT), metal implants can cause metal artifacts, affecting image quality and the final medical diagnosis. To reduce the impact of metal artifacts, our proposed metal artifacts reduction (MAR) method takes a novel approach by integrating CBCT data with intraoral optical scanning data, utilizing information from these two different modalities to correct metal artifacts in the projection domain using a guided-diffusion model. The intraoral optical scanning data provides a more accurate generation domain for the diffusion model. We have proposed a multi-channel generation method in the training and generation stage of the diffusion model, considering the physical mechanism of CBCT, to ensure the consistency of the diffusion model generation. In this paper, we present experimental results that convincingly demonstrate the feasibility and efficacy of our approach, which introduces intraoral optical scanning data into the analysis and processing of projection domain data using the diffusion model for the first time, and modifies the diffusion model to better adapt to the physical model of CBCT.

Summary High-fidelity three-dimensional (3D) models of tooth-bone structures are valuable for virtual dental treatment planning; however, they require integrating data from cone-beam computed tomography (CBCT) and intraoral scans (IOS) using methods that are either error-prone or time-consuming. Hence, this study presents Deep Dental Multimodal Fusion (DDMF), an automatic multimodal framework that reconstructs 3D tooth-bone structures using CBCT and IOS. Specifically, the DDMF framework comprises CBCT and IOS segmentation modules as well as a multimodal reconstruction module with novel pixel representation learning architectures, prior knowledge-guided losses, and geometry-based 3D fusion techniques. Experiments on real-world large-scale datasets revealed that DDMF achieved superior segmentation performance on CBCT and IOS, achieving a 0.17 mm average symmetric surface distance (ASSD) for 3D fusion with a substantial processing time reduction. Additionally, clinical applicability studies have demonstrated DDMF’s potential for accurately simulating tooth-bone structures throughout the orthodontic treatment process.

No abstract available

Dentocraniofacial hard tissue defects profoundly affect patients'physiological functions, facial aesthetics, and psychological well-being, posing significant challenges for precise reconstruction. Current deep learning models are limited to single-tissue scenarios and modality-specific imaging inputs, resulting in poor generalizability and trade-offs between anatomical fidelity, computational efficiency, and cross-tissue adaptability. Here we introduce UniDCF, a unified framework capable of reconstructing multiple dentocraniofacial hard tissues through multimodal fusion encoding of point clouds and multi-view images. By leveraging the complementary strengths of each modality and incorporating a score-based denoising module to refine surface smoothness, UniDCF overcomes the limitations of prior single-modality approaches. We curated the largest multimodal dataset, comprising intraoral scans, CBCT, and CT from 6,609 patients, resulting in 54,555 annotated instances. Evaluations demonstrate that UniDCF outperforms existing state-of-the-art methods in terms of geometric precision, structural completeness, and spatial accuracy. Clinical simulations indicate UniDCF reduces reconstruction design time by 99% and achieves clinician-rated acceptability exceeding 94%. Overall, UniDCF enables rapid, automated, and high-fidelity reconstruction, supporting personalized and precise restorative treatments, streamlining clinical workflows, and enhancing patient outcomes.

INTRODUCTION In the treatment of malocclusion, continuous monitoring of the three-dimensional relationship between dental roots and the surrounding alveolar bone is essential for preventing complications from orthodontic procedures. Cone-beam computed tomography (CBCT) provides detailed root and bone data, but its high radiation dose limits its frequent use, consequently necessitating an alternative for ongoing monitoring. OBJECTIVES We aimed to develop a deep learning-based cross-temporal multimodal image fusion system for acquiring root and jawbone information without additional radiation, enhancing the ability of orthodontists to monitor risk. METHODS Utilizing CBCT and intraoral scans (IOSs) as cross-temporal modalities, we integrated deep learning with multimodal fusion technologies to develop a system that includes a CBCT segmentation model for teeth and jawbones. This model incorporates a dynamic kernel prior model, resolution restoration, and an IOS segmentation network optimized for dense point clouds. Additionally, a coarse-to-fine registration module was developed. This system facilitates the integration of IOS and CBCT images across varying spatial and temporal dimensions, enabling the comprehensive reconstruction of root and jawbone information throughout the orthodontic treatment process. RESULTS The experimental results demonstrate that our system not only maintains the original high resolution but also delivers outstanding segmentation performance on external testing datasets for CBCT and IOSs. CBCT achieved Dice coefficients of 94.1 % and 94.4 % for teeth and jawbones, respectively, and it achieved a Dice coefficient of 91.7 % for the IOSs. Additionally, in the context of real-world registration processes, the system achieved an average distance error (ADE) of 0.43 mm for teeth and 0.52 mm for jawbones, significantly reducing the processing time. CONCLUSION We developed the first deep learning-based cross-temporal multimodal fusion system, addressing the critical challenge of continuous risk monitoring in orthodontic treatments without additional radiation exposure. We hope that this study will catalyze transformative advancements in risk management strategies and treatment modalities, fundamentally reshaping the landscape of future orthodontic practice.

A critical step in virtual dental treatment planning is to accurately delineate all tooth-bone structures from CBCT with high fidelity and accurate anatomical information. Previous studies have established several methods for CBCT segmentation using deep learning. However, the inherent resolution discrepancy of CBCT and the loss of occlusal and dentition information largely limited its clinical applicability. Here, we present a Deep Dental Multimodal Analysis (DDMA) framework consisting of a CBCT segmentation model, an intraoral scan (IOS) segmentation model (the most accurate digital dental model), and a fusion model to generate 3D fused crown-root-bone structures with high fidelity and accurate occlusal and dentition information. Our model was trained with a large-scale dataset with 503 CBCT and 28,559 IOS meshes manually annotated by experienced human experts. For CBCT segmentation, we use a five-fold cross validation test, each with 50 CBCT, and our model achieves an average Dice coefficient and IoU of 93.99% and 88.68%, respectively, significantly outperforming the baselines. For IOS segmentations, our model achieves an mIoU of 93.07% and 95.70% on the maxillary and mandible on a test set of 200 IOS meshes, which are 1.77% and 3.52% higher than the state-of-art method. Our DDMA framework takes about 20 to 25 minutes to generate the fused 3D mesh model following the sequential processing order, compared to over 5 hours by human experts. Notably, our framework has been incorporated into a software by a clear aligner manufacturer, and real-world clinical cases demonstrate that our model can visualize crown-root-bone structures during the entire orthodontic treatment and can predict risks like dehiscence and fenestration. These findings demonstrate the potential of multi-modal deep learning to improve the quality of digital dental models and help dentists make better clinical decisions.

No abstract available

In contemporary practice, intraoral scans and cone-beam computed tomography (CBCT) are widely adopted techniques for tooth localization and the acquisition of comprehensive three-dimensional models. Despite their utility, each dataset presents inherent merits and limitations, prompting the pursuit of an amalgamated solution for optimization. Thus, this research introduces a novel 3D registration approach aimed at harmonizing these distinct datasets to offer a holistic perspective. In the pre-processing phase, a retrained Mask-RCNN is deployed on both sagittal and panoramic projections to partition upper and lower teeth from the encompassing CBCT raw data. Simultaneously, a chromatic classification model is proposed for segregating gingival tissue from tooth structures in intraoral scan data. Subsequently, the segregated datasets are aligned based on dental crowns, employing the robust RANSAC and ICP algorithms. To assess the proposed methodology’s efficacy, the Euclidean distance between corresponding points is statistically evaluated. Additionally, dental experts, including two orthodontists and an experienced general dentist, evaluate the clinical potential by measuring distances between landmarks on tooth surfaces. The computed error in corresponding point distances between intraoral scan data and CBCT data in the automatically registered datasets utilizing the proposed technique is quantified at 0.234 ± 0.019 mm, which is significantly below the 0.3 mm CBCT voxel size. Moreover, the average measurement discrepancy among expert-identified landmarks ranges from 0.368 to 1.079 mm, underscoring the promise of the proposed method.

High-fidelity 3D tooth models are essential for digital dentistry, but must capture both the detailed crown and the complete root. Clinical imaging modalities are limited: Cone-Beam Computed Tomography (CBCT) captures the root but has a noisy, low-resolution crown, while Intraoral Scanners (IOS) provide a high-fidelity crown but no root information. A naive fusion of these sources results in unnatural seams and artifacts. We propose a novel, fully-automated pipeline that fuses CBCT and IOS data using a deep implicit representation. Our method first segments and robustly registers the tooth instances, then creates a hybrid proxy mesh combining the IOS crown and the CBCT root. The core of our approach is to use this noisy proxy to guide a class-specific DeepSDF network. This optimization process projects the input onto a learned manifold of ideal tooth shapes, generating a seamless, watertight, and anatomically coherent model. Qualitative and quantitative evaluations show our method uniquely preserves both the high-fidelity crown from IOS and the patient-specific root morphology from CBCT, overcoming the limitations of each modality and naive stitching.

We present a fully automated method of integrating intraoral scan (IOS) and dental cone-beam computerized tomography (CBCT) images into one image by complementing each image's weaknesses. Dental CBCT alone may not be able to delineate precise details of the tooth surface due to limited image resolution and various CBCT artifacts, including metal-induced artifacts. IOS is very accurate for the scanning of narrow areas, but it produces cumulative stitching errors during full-arch scanning. The proposed method is intended not only to compensate the low-quality of CBCT-derived tooth surfaces with IOS, but also to correct the cumulative stitching errors of IOS across the entire dental arch. Moreover, the integration provides both gingival structure of IOS and tooth roots of CBCT in one image. The proposed fully automated method consists of four parts; (i) individual tooth segmentation and identification module for IOS data (TSIM-IOS); (ii) individual tooth segmentation and identification module for CBCT data (TSIM-CBCT); (iii) global-to-local tooth registration between IOS and CBCT; and (iv) stitching error correction for full-arch IOS. The experimental results show that the proposed method achieved landmark and surface distance errors of 112.4μm and 301.7μm, respectively.

OBJECTIVES To evaluate the feasibility of utilising artificial intelligence (AI)-based segmentation of cone-beam computed tomography (CBCT) images in the generation of three-dimensional virtual patients, particularly in contexts complicated by the presence of metallic artefacts. METHODS Crown preparations were performed on the mandibular second premolars of a validated human head phantom, followed by intraoral scanning with a TRIOS scanner. Custom zirconia crowns were digitally designed and milled. The phantom was scanned using two CBCT units under four conditions simulating different crown placements. CBCT datasets were processed using an AI-driven platform for automatic segmentation of mandibular teeth, mandible, and zirconia crowns. Segmentation accuracy was evaluated by registering intraoral scan, crown design, CBCT without zirconia crowns, and AI-segmented models, followed by quantitative surface comparison using root mean square (RMS) and median surface deviation (MSD). RESULTS AI-based segmentation was generally accurate across all experimental conditions and CBCT units, with complete 3D models showing RMS values of 0.17-0.30 mm and near-zero MSD values, indicating minimal spatial misalignment. Segmentation accuracy was highest for mandibular teeth and mandible (RMS: 0.03-0.34 mm), while zirconia crowns exhibited greater deviations (RMS: 0.66-0.95 mm), likely due to metallic artefacts. CONCLUSION AI-based CBCT segmentation for generating 3D virtual patients is feasible, even in cases complicated by metallic artefacts. Zirconia crowns had minimal impact on segmentation accuracy for mandibular teeth and the mandible, though zirconia crown segmentation was more affected. Expert clinical supervision remains essential to ensure the reliability and accuracy of these virtual models. CLINICAL SIGNIFICANCE AI-based CBCT segmentation can reliably generate 3D models of the mandible and teeth, even in the presence of zirconia crowns. This suggests a promising alternative to intraoral scanning in specific clinical scenarios, provided that expert validation is ensured.

Virtual simulation has advanced in dental healthcare, but the impact of different tomographic techniques on virtual patient (VP) creation remains unclear. This study primarily aimed to automatically create VP from facial scans (FS), intraoral scans (IOS), multislice (MSCT), and cone beam computed tomography (CBCT); Secondarily, to quantitatively compare artificial intelligence (AI)-driven, AI-refined and semi automatically registered (SAR) VP creation from MSCT and CBCT and to compare the effect of soft tissue on the registration with MSCT and CBCT. A dataset of 20 FS, IOS, and (MS/CB)CT scans was imported into the Virtual Patient Creator platform to generate automated VPs. The accuracy (percentage of corrections required), consistency, and time efficiency of the AI-driven VP registration were then compared to those of the AI-refined and SAR (clinical reference) using Mimics software. The surface distance between the registered FS and the (MS/CB)CT surface rendering using SAR and AI-driven methods was measured to assess the effect of soft tissue on registration. All three registration methods achieved 100% accuracy for VP creation with both MSCT and CBCT (p > 0.999), with no significant differences between tomographic techniques either (p > 0.999). Perfect consistency (1.00) was obtained with AI-driven and AI-refined methods, and slightly lower for SAR (0.977 for MSCT and 0.895 for CBCT). Average registration times were 24.9 and 28.5 s for AI-driven and AI-refined, and 242.3 and 275.7 s for SAR with MSCT and CBCT respectively. The total time was significantly shorter for MSCT (313.7 s) compared to CBCT (850.3 s) (p < 0.001). While the average surface distance between MSCT- and CBCT-based VP showed no significant difference (p > 0.05), AI-driven resulted in a smaller surface distance than SAR (p < 0.05). AI enables fast, accurate, and consistent VP creation using FS, IOS, and (MS/CB)CT data. AI-driven, AI-refined, and semi-automated methods all achieve good accuracy. Additionally, soft tissue registration shows no significant difference between MSCT and CBCT.

Digital dentistry represents a transformative shift in modern dental practice. The foundational step in this transformation is the accurate digital representation of the patient's dentition, which is obtained from segmented Cone-Beam Computed Tomography (CBCT) and Intraoral Scans (IOS). Despite the growing interest in digital dental technologies, existing segmentation methodologies frequently lack rigorous validation and demonstrate limited performance and clinical applicability. To the best of our knowledge, this is the first work to introduce a multimodal pretraining framework for tooth segmentation. We present ToothMCL, a Tooth Multimodal Contrastive Learning for pretraining that integrates volumetric (CBCT) and surface-based (IOS) modalities. By capturing modality-invariant representations through multimodal contrastive learning, our approach effectively models fine-grained anatomical features, enabling precise multi-class segmentation and accurate identification of F\'ed\'eration Dentaire Internationale (FDI) tooth numbering. Along with the framework, we curated CBCT-IOS3.8K, the largest paired CBCT and IOS dataset to date, comprising 3,867 patients. We then evaluated ToothMCL on a comprehensive collection of independent datasets, representing the largest and most diverse evaluation to date. Our method achieves state-of-the-art performance in both internal and external testing, with an increase of 12\% for CBCT segmentation and 8\% for IOS segmentation in the Dice Similarity Coefficient (DSC). Furthermore, ToothMCL consistently surpasses existing approaches in tooth groups and demonstrates robust generalizability across varying imaging conditions and clinical scenarios.

Cone-Beam Computed Tomography (CBCT) and Intraoral Scanning (IOS) are essential for digital dentistry, but annotated data scarcity limits automated solutions for pulp canal segmentation and cross-modal registration. To benchmark semi-supervised learning (SSL) in this domain, we organized the STSR 2025 Challenge at MICCAI 2025, featuring two tasks: (1) semi-supervised segmentation of teeth and pulp canals in CBCT, and (2) semi-supervised rigid registration of CBCT and IOS. We provided 60 labeled and 640 unlabeled IOS samples, plus 30 labeled and 250 unlabeled CBCT scans with varying resolutions and fields of view. The challenge attracted strong community participation, with top teams submitting open-source deep learning-based SSL solutions. For segmentation, leading methods used nnU-Net and Mamba-like State Space Models with pseudo-labeling and consistency regularization, achieving a Dice score of 0.967 and Instance Affinity of 0.738 on the hidden test set. For registration, effective approaches combined PointNetLK with differentiable SVD and geometric augmentation to handle modality gaps; hybrid neural-classical refinement enabled accurate alignment despite limited labels. All data and code are publicly available at https://github.com/ricoleehduu/STS-Challenge-2025 to ensure reproducibility.

The precise diagnosis and treatment planning of oral diseases are increasingly dependent on digital technologies. Oromaxillofacial Cone-Beam Computed Tomography (CBCT) provides comprehensive information about tooth roots and internal structures, yet it is constrained by limited spatial resolution and data redundancy. In contrast, Intraoral Scanning (IOS) captures high-resolution surface data of the tooth crowns. By registering and fusing CBCT and IOS point cloud data, it is possible to achieve rapid, comprehensive, and highly accurate 3D reconstructions of dental anatomy, thereby significantly improving the efficiency and precision of dental treatment. However, conventional registration methodologies in this domain typically exhibit limited generalization and are highly sensitive to noise, and research on the application of existing learning-based end-to-end registration models remains relatively scarce. To address these challenges, this study formulates point cloud registration as a Reinforcement Learning (RL) problem. Our proposed model first leverages a Graph Neural Network (GNN) to extract structural features from the point clouds and obtain effective feature descriptors. Subsequently, the model employs Imitation Learning (IL) to acquire an expert registration policy, which is further refined through policy optimization guided by a registration-based reward mechanism. To enable adaptive step refinement and eliminate quantization errors, we introduce a hybrid discrete-continuous action space that applies a continuous scaling factor to the discrete step size, resulting in superior final registration accuracy.

Computer-Assisted Interventions enable clinicians to perform precise, minimally invasive procedures, often relying on advanced imaging methods. Cone-beam computed tomography (CBCT) can be used to facilitate computer-assisted interventions, despite often suffering from artifacts that pose challenges for accurate interpretation. While the degraded image quality can affect image analysis, the availability of high quality, preoperative scans offers potential for improvements. Here we consider a setting where preoperative CT and intraoperative CBCT scans are available, however, the alignment (registration) between the scans is imperfect to simulate a real world scenario. We propose a multimodal learning method that fuses roughly aligned CBCT and CT scans and investigate the effect on segmentation performance. For this experiment we use synthetically generated data containing real CT and synthetic CBCT volumes with corresponding voxel annotations. We show that this fusion setup improves segmentation performance in $18$ out of $20$ investigated setups.

In dental applications, information of the soft-and-hard tissues’ surfaces from an intraoral scan or a dental cast helps a user to enhance visualization of anatomical structures in cone-beam computed tomography (CBCT) images. This paper presents a combination process based on the Visualization Toolkit (VTK) library. The proposed process consisted of three main steps: landmark identification, 3D surface registration, and visualization of alignment’s quality. In experiments, the tissue’s surfaces were acquired from intraoral scans and dental casts, and these surfaces were combined with several CBCT data. The results showed that all three parts of the proposed process performed smoothly. A combination of CBCT data and tissue’s surfaces obviously presented good quality of alignment and improved visualization of anatomical structures although qualities of CBCT data were dropped by image noises and some artifacts.

Dual-energy cone-beam computed tomography (DE-CBCT) is a promising imaging technique with foreseeable clinical applications. DE-CBCT images acquired with two different spectra can provide material-specific information. Meanwhile, the anatomical consistency and energy-domain correlation result in significant information redundancy, which could be exploited to improve image quality. In this context, this paper develops the Transformer-Integrated Multi-Encoder Network (TIME-Net) for DE-CBCT to remove the limited-angle artifacts. TIME-Net comprises three encoders (image encoder, prior encoder, and transformer encoder), two decoders (low- and high-energy decoders), and one feature fusion module. Three encoders extract various features for image restoration. The feature fusion module compresses these features into more compact shared features and feeds them to the decoders. Two decoders perform differential learning for DE-CBCT images. By design, TIME-Net could obtain high-quality DE-CBCT images using two complementary quarter-scans, holding great potential to reduce radiation dose and shorten the acquisition time. Qualitative and quantitative analyses based on simulated data and real rat data have demonstrated the promising performance of TIME-Net in artifact removal, subtle structure restoration, and reconstruction accuracy preservation. Two clinical applications, virtual non-contrast (VNC) imaging and iodine quantification, have proved the potential utility of the DE-CBCT images provided by TIME-Net.

Purpose The purpose of this study was to evaluate the clinical accuracy of the fusion of intra-oral scans in cone-beam computed tomography (CBCT) scans using two commercially available software packages. Materials and methods Ten dry human skulls were subjected to structured light scanning, CBCT scanning, and intra-oral scanning. Two commercially available software packages were used to perform fusion of the intra-oral scans in the CBCT scan to create an accurate virtual head model: IPS CaseDesigner® and OrthoAnalyzer™. The structured light scanner was used as a gold standard and was superimposed on the virtual head models, created by IPS CaseDesigner® and OrthoAnalyzer™, using an Iterative Closest Point algorithm. Differences between the positions of the intra-oral scans obtained with the software packages were recorded and expressed in six degrees of freedom as well as the inter- and intra-observer intra-class correlation coefficient. Results The tested software packages, IPS CaseDesigner® and OrthoAnalyzer™, showed a high level of accuracy compared to the gold standard. The accuracy was calculated for all six degrees of freedom. It was noticeable that the accuracy in the cranial/caudal direction was the lowest for IPS CaseDesigner® and OrthoAnalyzer™ in both the maxilla and mandible. The inter- and intra-observer intra-class correlation coefficient showed a high level of agreement between the observers. Clinical relevance IPS CaseDesigner® and OrthoAnalyzer™ are reliable software packages providing an accurate fusion of the intra-oral scan in the CBCT. Both software packages can be used as an accurate fusion tool of the intra-oral scan in the CBCT which provides an accurate basis for 3D virtual planning.

INTRODUCTION The purpose of this study was to investigate the registration accuracy between intraoral-scanned crowns and cone-beam computed tomography (CBCT)-scanned crowns in various registration methods. METHODS The samples consisted of 18 Korean adult patients, whose pretreatment intraoral scans and CBCT images were available. A 3-dimensional (3D) dental model was fabricated using a TRIOS intraoral scanner (3Shape, Copenhagen, Denmark) and the OrthoAnalyzer program (version 1.7.1.4; 3Shape). After the CBCT image was taken, 3D volume rendering was performed to fabricate a 3D dental model using InVivo5 software (version 5.1; Anatomage, San Jose, Calif). Registration of the 3D dental crowns made from intraoral- and CBCT-scanned images was performed with Rapidform 2006 software (Inus Technology, Seoul, Korea) by a single operator. According to registration methods, 3 groups were established: individual-arch-total-registration group, individual-arch-segment-registration group, and bimaxillary-arch-centric-occlusion-registration group (n = 18 per group). After the amounts of shell/shell deviation were obtained, the mixed model analysis of variance and Bonferroni correction were performed. RESULTS Although there was no significant difference in the registration accuracy between the individual-arch-total-registration group and individual-arch-segment-registration group, the bimaxillary-arch-centric-occlusion-registration group exhibited the lowest registration accuracy (maxillary and mandibular teeth, all 0.21 mm in the individual-arch-total-registration group; all 0.20 mm in the individual-arch-segment-registration group vs 0.26 mm and 0.25 mm in the bimaxillary-arch-centric-occlusion-registration group; P <0.001). Color-coded visualization charts exhibited that most red spots were localized on the occlusal surface of the posterior teeth in all 3 groups. CONCLUSIONS When considering the registration accuracy and convenience of the process, the individual-arch-total-registration method can be regarded as an efficient tool when integrating CBCT-scanned crown and intraoral-scanned crown.

BACKGROUND Static computer-assisted implant surgery (s-CAIS) utilizes 3D imaging data to guide implant placement with high precision. Accurate segmentation of CBCT and intraoral scan data is crucial to creating reliable anatomical models. While AI-driven segmentation has emerged as a promising solution to reduce manual workload, its performance is hindered by technical and algorithmic limitations. OBJECTIVE To evaluate the accuracy and limitations of AI-based segmentation in dental implant planning software and to identify common sources of segmentation errors, their clinical implications, and strategies for mitigation. METHODS This work is framed as a narrative literature review and educational practice overview. Observations on software functionality were based on direct use and exploration of varying implant planning software programs. This was conducted to qualitatively describe common segmentation error patterns (boundary errors, over-/under-segmentation, misidentification, and partial volume effects), and demonstrate editing functionalities across four implant planning systems (coDiagnostiX, BlueSkyPlan, Atomica, and Relu). These demonstrations are intended for illustrative purposes and do not constitute a formal, reproducible performance comparison. RESULTS AI-based segmentation frequently encounters errors due to imaging artifacts, motion blur, anatomical variability, and algorithmic biases. These errors can lead to inaccurate implant positioning, compromised surgical guide designs, and clinical complications. While advanced methods such as U-Net, GANs, and SISTR improve segmentation quality, manual intervention remains essential. The effectiveness of AI tools varies significantly across platforms, and limited editing capabilities often hinder error correction. CONCLUSION Despite advances in AI, segmentation errors remain a critical barrier in s-CAIS workflows. Enhanced imaging protocols, algorithmic refinement, clinician oversight, and regulatory transparency are essential to improve segmentation accuracy and ensure safe, effective digital implant planning.

No abstract available

The present study presents an AI-based platform that is aimed at enhancing the accuracy and flexibility of dental implant procedures. The system combines anatomical analysis, which is generated with the help of deep learning, and real-time surgery navigation, which considers both the preoperative Cone Beam Computed Tomography (CBCT) and intraoral scan data to assist in the implant placement. The system makes use of Convolutional Neural Networks (CNN) to perform 3D segmentation and landmark detection, which is then followed by planning the path of the implant and realtime surgical feedback. It is much better than the oldfashioned methods of statical guides and hand-drawn methods, as it is more accurate and quicker to react. The AI system helps to minimize the deviations at the time the implant is placed, the operational latency is minimized, and the safety of the patient is enhanced because there is no risk of critical structures. The outcomes of experimental trials indicate that the accuracy is being continuously enhanced, and the ultimate accuracy is 95.6 percent, as opposed to manual procedures, and fixed guides. This research identifies the possibility of AI to transform dental implantology, providing a smarter, more accurate and efficient way of conducting surgeries.

CT metal artefact reduction (MAR) methods based on supervised deep learning are often troubled by domain gap between simulated training dataset and real-application dataset, i.e., methods trained on simulation cannot generalize well to practical data. Unsupervised MAR methods can be trained directly on practical data, but they learn MAR with indirect metrics and often perform unsatisfactorily. To tackle the domain gap problem, we propose a novel MAR method called UDAMAR based on unsupervised domain adaptation (UDA). Specifically, we introduce a UDA regularization loss into a typical image-domain supervised MAR method, which mitigates the domain discrepancy between simulated and practical artefacts by feature-space alignment. Our adversarial-based UDA focuses on a low-level feature space where the domain difference of metal artefacts mainly lies. UDAMAR can simultaneously learn MAR from simulated data with known labels and extract critical information from unlabeled practical data. Experiments on both clinical dental and torso datasets show the superiority of UDAMAR by outperforming its supervised backbone and two state-of-the-art unsupervised methods. We carefully analyze UDAMAR by both experiments on simulated metal artefacts and various ablation studies. On simulation, its close performance to the supervised methods and advantages over the unsupervised methods justify its efficacy. Ablation studies on the influence from the weight of UDA regularization loss, UDA feature layers, and the amount of practical data used for training further demonstrate the robustness of UDAMAR. UDAMAR provides a simple and clean design and is easy to implement. These advantages make it a very feasible solution for practical CT MAR.

Digital orthodontics leverages 3D intraoral scanning and computational analysis to enable precise diagnosis, treatment planning, and outcome evaluation in a data-driven workflow. A structured understanding of intraoral 3D scans is essential for digital orthodontics. Such structured understanding converts raw geometric data into clinically interpretable representations, forming the foundation for reliable automated analysis throughout the orthodontic pipeline. However, existing deep-learning approaches rely heavily on modality-specific training, large annotated datasets, and controlled scanning conditions, which limit generalization across devices and hinder deployment in real clinical workflows. Moreover, raw intraoral meshes exhibit substantial variation in arch pose, incomplete geometry caused by occlusion or tooth contact, and a lack of texture cues, making unified semantic interpretation highly challenging. To address these limitations, we propose ArchMap, a training-free and knowledge-guided framework for robust structured dental understanding. ArchMap first introduces a geometry-aware archflattening module that standardizes raw 3D meshes into spatially aligned, continuity-preserving multi-view projections. We then construct a Dental Knowledge Base (DKB) encoding hierarchical tooth ontology, dentition-stage policies, and clinical semantics to constrain the symbolic reasoning space. Leveraging on this ontology, a schema-constrained vision-language inference pipeline transforms general-purpose VLMs into deterministic, contractcompliant structured predictors. We validate ArchMap on 1060 pre-/post-orthodontic cases, demonstrating robust performance in tooth counting, anatomical partitioning, dentition-stage classification, and the identification of clinical conditions such as crowding, missing teeth, prosthetics, and caries. Compared with supervised pipelines and prompted VLM baselines, ArchMap achieves higher accuracy, reduced semantic drift, and superior stability under sparse or artifact-prone conditions. As a fully training-free system, ArchMap demonstrates that combining geometric normalization with ontology-guided multimodal reasoning offers a practical and scalable solution for the structured analysis of 3D intraoral scans in modern digital orthodontics.

In the digitalization of modern dentistry, 3D tooth segmentation serves as a critical prerequisite for various clinical applications. However, existing deep learning segmentation approaches often encounter the problem of boundary ambiguity between adjacent teeth due to the high similarity in their geometric and semantic features. To address this issue, we propose a novel 3D tooth instance segmentation method that leverages the chain-like distribution property of tooth categories. Built upon a DGCNN backbone, the method employs a multi-branch architecture comprising multi-class segmentation, tooth-gingiva binary classification, and a skip mask binary classification network. Furthermore, we design a binary cross entropy loss function associated with skip mask that exploits the linear progression inherent in tooth category distribution, thereby enhancing feature learning in critical regions to improve boundary delineation. By integrating multiple task-specific supervision signals into a unified loss function, our framework supports end-to-end joint training. Public dataset experiments show the proposed method outperforms mainstream approaches across segmentation metrics, with more precise adjacent tooth discrimination, mitigated boundary ambiguity.

When planning guided implant surgery, highly radiopaque materials such as metals or zirconia produce streaking artifacts ('metal artifact') on cone-beam computed tomography scans, which can impair registration of the intraoral scan. This study aimed to determine the effect of metal artifact reduction on the trueness of registration in the presence of multiple full-coverage zirconia crowns. A 3D-printed maxillary study model was restored with 12 full-coverage zirconia crowns and scanned with an intraoral scanner. Cone-beam computed tomography scans of the study model were acquired, with and without activation of the metal artifact reduction algorithm. Registration of the optical scans was performed using initial point-based registration with surface-based refinement, and the deviation was measured at four pre-defined dental landmarks. Welch's t-test was used to compare the registration error for the metal artifact reduction group with the control group. The average registration error was 0.519 mm (95% CI 0.507 to 0.531) with metal artifact reduction deactivated, compared to 0.478 mm (95% CI 0.460 to 0.496) without metal artifact reduction. Therefore, activation of the metal artifact reduction algorithm was associated with a 0.041 mm (95% CI 0.020 to 0.061, p < 0.001) increase in average registration error. The use of the metal artifact reduction algorithm slightly reduced trueness in this in vitro study. Clinicians are advised not to rely on a metal artifact reduction (MAR) algorithm for registration of a cone-beam computed tomography scan with an intraoral scan when planning guided implant surgery in the presence of restoration artifacts.

To develop a semi-supervised domain adaptation technique for metal artifact reduction with a spatial-frequency transformer (SFTrans) model (Semi-SFTrans), and to quantitatively compare its performance with supervised models (Sup-SFTrans and ResUNet) and traditional linear interpolation MAR method (LI) in oral and maxillofacial CT. Supervised models, including Sup-SFTrans and a state-of-the-art model termed ResUNet, were trained with paired simulated CT images, while semi-supervised model, Semi-SFTrans, was trained with both paired simulated and unpaired clinical CT images. For evaluation on the simulated data, we calculated Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) on the images corrected by four methods: LI, ResUNet, Sup-SFTrans, and Semi-SFTrans. For evaluation on the clinical data, we collected twenty-two clinical cases with real metal artifacts, and the corresponding intraoral scan data. Three radiologists visually assessed the severity of artifacts using Likert scales on the original, Sup-SFTrans-corrected, and Semi-SFTrans-corrected images. Quantitative MAR evaluation was conducted by measuring Mean Hounsfield Unit (HU) values, standard deviations, and Signal-to-Noise Ratios (SNRs) across Regions of Interest (ROIs) such as the tongue, bilateral buccal, lips, and bilateral masseter muscles, using paired t-tests and Wilcoxon signed-rank tests. Further, teeth integrity in the corrected images was assessed by comparing teeth segmentation results from the corrected images against the ground-truth segmentation derived from registered intraoral scan data, using Dice Score and Hausdorff Distance. Sup-SFTrans outperformed LI, ResUNet and Semi-SFTrans on the simulated dataset. Visual assessments from the radiologists showed that average scores were (2.02 ± 0.91) for original CT, (4.46 ± 0.51) for Semi-SFTrans CT, and (3.64 ± 0.90) for Sup-SFTrans CT, with intra correlation coefficients (ICCs)＞0.8 of all groups and p < 0.001 between groups. On soft tissue, both Semi-SFTrans and Sup-SFTrans significantly reduced metal artifacts in tongue (p < 0.001), lips, bilateral buccal regions, and masseter muscle areas (p < 0.05). Semi-SFTrans achieved superior metal artifact reduction than Sup-SFTrans in all ROIs (p < 0.001). SNR results indicated significant differences between Semi-SFTrans and Sup-SFTrans in tongue (p = 0.0391), bilateral buccal (p = 0.0067), lips (p = 0.0208), and bilateral masseter muscle areas (p = 0.0031). Notably, Semi-SFTrans demonstrated better teeth integrity preservation than Sup-SFTrans (Dice Score: p < 0.001; Hausdorff Distance: p = 0.0022). The semi-supervised MAR model, Semi-SFTrans, demonstrated superior metal artifact reduction performance over supervised counterparts in real dental CT images.

No abstract

For this research two different ways for integrating intra-oral scans into three-dimensional (3D) stereophotogrammetric images are analyzed and compared to the gold standard method. A cross-sectional study was performed. For each patient a complete dataset was collected, which was used to generate 3D fusion models by three different methods: method A using cheek retractors, method B using a tracer and method C using full-skull CBCT. The experimental methods A and B were compared to the gold standard method C. A group of eighteen patients were included in this study. The translation (X, Y,Z), the euclidean distance and the rotation (roll, pitch, yaw) were calculated for both experimental methods A and B in comparison with the gold standard method C. Twelve out of fourteen measurements were clinically acceptable (below 2 mm or 2 degrees). Method A shows the highest deviation in the pitch-orientation for rotation (2.51 degrees, 95% CI [1.756 … 3.272]), while method B shows a higher deviation along the y-axis (1.85 mm, 95% CI [1.224 … 2.467]). This study shows promising results of non-ionizing methods to integrate intra-oral scans into 3D stereophotogrammetric images. With improved accuracy in pitch in method A and translation along the Y-axis in method B, all measurements will be within the clinically acceptable threshold. However, since these two measurements exceed the clinically acceptable thresholds, the complete model positioning is less accurate. Therefore the main goal in further research should be to improve the accuracy of the pitch in method A and the translation along the Y-axis in method B. Additionally, for clinical use the biggest improvement could be gained by optimizing the clinical workflow and data processing. By using a non-ionizing 3D fusion model instead of a conventional cephalogram for treatment planning, the ionizing dose during orthodontic treatment can be significantly reduced.

The purpose of this article was to describe a fully digital workflow used to perform computer-guided flapless implant placement in an edentulous patient without the use of conventional impressions, models, or a radiographic guide. Digital data for the workflow were acquired using an intraoral scanner and cone-beam computed tomography (CBCT). The image fusion of the intraoral scan data and CBCT data was performed by matching resin markers placed in the patient's mouth. The definitive digital data were used to design a prosthetically driven implant position, surgical template, and computer-aided design and computer-aided manufacturing fabricated fixed dental prosthesis. The authors believe this is the first published case describing such a technique in computer-guided flapless implant surgery for edentulous patients.

To investigate the accuracy of conventional and automatic artificial intelligence (AI)-based registration of cone-beam computed tomography (CBCT) with intraoral scans and to evaluate the impact of user's experience, restoration artifact, number of missing teeth, and free-ended edentulous area. Three initial registrations were performed for each of the 150 randomly selected patients, in an implant planning software: one from an experienced user, one from an inexperienced operator, and one from a randomly selected post-graduate student of implant dentistry. Six more registrations were performed for each dataset by the experienced clinician: implementing a manual or an automatic refinement, selecting 3 small or 3 large in-diameter surface areas and using multiple small or multiple large in-diameter surface areas. Finally, an automatic AI-driven registration was performed, using the AI tools that were integrated into the utilized implant planning software. The accuracy between each type of registration was measured using linear measurements between anatomical landmarks in metrology software. Fully automatic-based AI registration was not significantly different from the conventional methods tested for patients without restorations. In the presence of multiple restoration artifacts, user's experience was important for an accurate registration. Registrations' accuracy was affected by the number of free-ended edentulous areas, but not by the absolute number of missing teeth (p < .0083). In the absence of imaging artifacts, automated AI-based registration of CBCT data and model scan data can be as accurate as conventional superimposition methods. The number and size of selected superimposition areas should be individually chosen depending on each clinical situation.

Inaccurate visualization of the inter-occlusal relationship has raised an important challenge to virtual planning for orthognathic surgery based on cone beam computerized tomography (CBCT). The aim of this study was to evaluate an innovative workflow for orthognathic surgery planning and surgical splint fabrication. The clinical protocol consists of a single cone beam computerized tomography (CBCT) scan of the patient, surface scanning of the dental arches with an intraoral digital scanner, and subsequent fusion of the two datasets. The "virtual patient" thus created undergoes virtual surgery, and the resulting file with the intermediate intermaxillary relationship is used to obtain the intermediate splint by CAD/CAM technology (computer-aided design and computer-aided manufacturing). A proof-of-concept study was performed in order to assess the accuracy and reliability of this protocol. The study comprised two parts: an in vitro evaluation on three dentate skull models and a prospective in vivo assessment on six consecutive patients. Vector error calculation between the virtually simulated intermaxillary position and the intraoperative intermediate intermaxillary relationship revealed high accuracy. The greatest average variation corresponded to the y axis. Compared to previously described methods for obtaining an augmented three-dimensional virtual model, this procedure eliminates the need for dental impressions, simplifies the necessary technical steps and computational work, and reduces the patient's exposure to ionizing radiation.

This technical evaluation aimed to compare 5 techniques for measuring sagittal (SCI) and transverse condylar inclination (TCI) to optimize virtual articulator programming in digital dentistry. 14 healthy participants (7 males, 7 females; aged 18-25 years) with 28 temporomandibular joints were evaluated. A novel virtual facebow system was developed to assess 5 measurement approaches based on natural head position (NHP) with horizontal plane markers: (1) Adjustable articulator (AAG); (2) Facial/intraoral scan integration (FIG); (3) CBCT/intraoral scan fusion (CIG); (4) Direct CBCT measurement (CTG), and (5) Kinematic facebow with T-Scan analysis (KFG). Triplicate measurements of interocclusal, protrusive, and lateral records were averaged. Statistical analysis included paired t-tests for bilateral comparisons and repeated measures ANOVA with Bonferroni-Greenhouse-Geisser corrections for technique comparisons. No significant differences were observed between left and right condylar inclination values (P > 0.05). Significant differences were detected among the measurement techniques for both SCI and TCI values (P < 0.001). Specifically, for SCI, KFG (41.81 ± 13.92°), CIG (43.05 ± 13.38°), and FIG (43.60 ± 12.64°) showed similar results (P > 0.05), while CTG (47.52 ± 9.12°) produced significantly higher values than AAG (37.68 ± 9.75°) (P < 0.05). For TCI, KFG (12.58 ± 7.27°), FIG (13.91 ± 7.72°), and CIG (11.85 ± 8.14°) again demonstrated similarity (P > 0.05), whereas both CTG (18.57 ± 8.75°) and AAG (19.50 ± 6.33°) yielded significantly higher values (P < 0.05). Digital workflows based on natural head position with horizontal plane markers-integrating facial, intraoral, and cone beam computed tomography data-achieve sagittal and transverse condylar inclination values comparable to kinematic facebow recordings, supporting their use as reliable alternatives for virtual articulator programming. Integrated natural head position‑based digital protocols provide efficient, clinically valid solutions for condylar inclination assessment, supporting the transition to digital prosthodontic workflows.

No abstract

Intraoral 3D scanning is now widely adopted in modern dentistry and plays a central role in supporting key tasks such as tooth segmentation, detection, labeling, and dental landmark identification. Accurate analysis of these scans is essential for orthodontic and restorative treatment planning, as it enables automated workflows and minimizes the need for manual intervention. However, the development of robust learning-based solutions remains challenging due to the limited availability of high-quality public datasets and standardized benchmarks. This article presents Teeth3DS+, an extended public benchmark dedicated to intraoral 3D scan analysis. Developed in the context of the MICCAI 3DTeethSeg and 3DTeethLand challenges, Teeth3DS+ supports multiple fundamental tasks, including tooth detection, segmentation, labeling, 3D modeling, and dental landmark identification. The dataset consists of rigorously curated intraoral scans acquired using state-of-the-art scanners and validated by experienced orthodontists and dental surgeons. In addition to the data, Teeth3DS+ provides standardized data splits and evaluation protocols to enable fair and reproducible comparison of methods, with the goal of fostering progress in learning-based analysis of 3D dental scans. Detailed instructions for accessing the dataset are available at https://crns-smartvision.github.io/teeth3ds

Intraoral 3D reconstruction is fundamental to digital orthodontics, yet conventional methods like intraoral scanning are inaccessible for remote tele-orthodontics, which typically relies on sparse smartphone imagery. While 3D Gaussian Splatting (3DGS) shows promise for novel view synthesis, its application to the standard clinical triad of unposed anterior and bilateral buccal photographs is challenging. The large view baselines, inconsistent illumination, and specular surfaces common in intraoral settings can destabilize simultaneous pose and geometry estimation. Furthermore, sparse-view photometric supervision often induces a frequency bias, leading to over-smoothed reconstructions that lose critical diagnostic details. To address these limitations, we propose \textbf{Dental3R}, a pose-free, graph-guided pipeline for robust, high-fidelity reconstruction from sparse intraoral photographs. Our method first constructs a Geometry-Aware Pairing Strategy (GAPS) to intelligently select a compact subgraph of high-value image pairs. The GAPS focuses on correspondence matching, thereby improving the stability of the geometry initialization and reducing memory usage. Building on the recovered poses and point cloud, we train the 3DGS model with a wavelet-regularized objective. By enforcing band-limited fidelity using a discrete wavelet transform, our approach preserves fine enamel boundaries and interproximal edges while suppressing high-frequency artifacts. We validate our approach on a large-scale dataset of 950 clinical cases and an additional video-based test set of 195 cases. Experimental results demonstrate that Dental3R effectively handles sparse, unposed inputs and achieves superior novel view synthesis quality for dental occlusion visualization, outperforming state-of-the-art methods.

Optical Intraoral Scanners (IOS) are widely used in digital dentistry to provide detailed 3D information of dental crowns and the gingiva. Accurate 3D tooth segmentation in IOSs is critical for various dental applications, while previous methods are error-prone at complicated boundaries and exhibit unsatisfactory results across patients. In this paper, we propose TSegFormer which captures both local and global dependencies among different teeth and the gingiva in the IOS point clouds with a multi-task 3D transformer architecture. Moreover, we design a geometry-guided loss based on a novel point curvature to refine boundaries in an end-to-end manner, avoiding time-consuming post-processing to reach clinically applicable segmentation. In addition, we create a dataset with 16,000 IOSs, the largest ever IOS dataset to the best of our knowledge. The experimental results demonstrate that our TSegFormer consistently surpasses existing state-of-the-art baselines. The superiority of TSegFormer is corroborated by extensive analysis, visualizations and real-world clinical applicability tests. Our code is available at https://github.com/huiminxiong/TSegFormer.

This paper proposes an extension to the Dual Branch Prior-Net for sparse view interventional CBCT reconstruction incorporating a high quality planning scan. An additional head learns to segment interventional instruments and thus guides the reconstruction task. The prior scans are misaligned by up to +-5deg in-plane during training. Experiments show that the proposed model, Dual Branch Prior-SegNet, significantly outperforms any other evaluated model by >2.8dB PSNR. It also stays robust wrt. rotations of up to +-5.5deg.

This paper presents a fully automatic registration method of dental cone-beam computed tomography (CBCT) and face scan data. It can be used for a digital platform of 3D jaw-teeth-face models in a variety of applications, including 3D digital treatment planning and orthognathic surgery. Difficulties in accurately merging facial scans and CBCT images are due to the different image acquisition methods and limited area of correspondence between the two facial surfaces. In addition, it is difficult to use machine learning techniques because they use face-related 3D medical data with radiation exposure, which are difficult to obtain for training. The proposed method addresses these problems by reusing an existing machine-learning-based 2D landmark detection algorithm in an open-source library and developing a novel mathematical algorithm that identifies paired 3D landmarks from knowledge of the corresponding 2D landmarks. A main contribution of this study is that the proposed method does not require annotated training data of facial landmarks because it uses a pre-trained facial landmark detection algorithm that is known to be robust and generalized to various 2D face image models. Note that this reduces a 3D landmark detection problem to a 2D problem of identifying the corresponding landmarks on two 2D projection images generated from two different projection angles. Here, the 3D landmarks for registration were selected from the sub-surfaces with the least geometric change under the CBCT and face scan environments. For the final fine-tuning of the registration, the Iterative Closest Point method was applied, which utilizes geometrical information around the 3D landmarks. The experimental results show that the proposed method achieved an averaged surface distance error of 0.74 mm for three pairs of CBCT and face scan datasets.

Cone Beam Computed Tomography (CBCT) is widely used in dentistry for diagnostics and treatment planning. CBCT Imaging has a long acquisition time and consequently, the patient is likely to move. This motion causes significant artifacts in the reconstructed data which may lead to misdiagnosis. Existing motion correction algorithms only address this issue partially, struggling with inconsistencies due to truncation, accuracy, and execution speed. On the other hand, a short-scan reconstruction using a subset of motion-free projections with appropriate weighting methods can have a sufficient clinical image quality for most diagnostic purposes. Therefore, a framework is used in this study to extract the motion-free part of the scanned projections with which a clean short-scan volume can be reconstructed without using correction algorithms. Motion artifacts are detected using deep learning with a slice-based prediction scheme followed by volume averaging to get the final result. A realistic motion simulation strategy and data augmentation has been implemented to address data scarcity. The framework has been validated by testing it with real motion-affected data while the model was trained only with simulated motion data. This shows the feasibility to apply the proposed framework to a broad variety of motion cases for further research.

This work introduces a new efficient iterative solver for the reconstruction of real-time cone-beam computed tomography (CBCT), which is based on the Prior Image Constrained Compressed Sensing (PICCS) regularization and leverages the efficiency of Krylov subspace methods. In particular, we focus on the setting where a sequence of under-sampled CT scans are taken on the same object with only local changes (e.g. changes in a tumour size or the introduction of a surgical tool). This is very common, for example, in image-guided surgery, where the amount of measurements is limited to ensure the safety of the patient. In this case, we can also typically assume that a (good) initial reconstruction for the solution exists, coming from a previously over-sampled scan, so we can use this information to aid the subsequent reconstructions. The effectiveness of this method is demonstrated in both a synthetic scan and using real CT data, where it can be observed that the PICCS framework is very effective for the reduction of artifacts, and that the new method is faster than other common alternatives used in the same setting.

Cone Beam Computed Tomography (CBCT) and Panoramic X-rays are the most commonly used imaging modalities in dental health care. CBCT can produce three-dimensional views of a patient's head, providing clinicians with better diagnostic capability, whereas Panoramic X-ray can capture the entire maxillofacial region in a single image. If the CBCT is already available, it can be beneficial to synthesize a Panoramic X-ray, thereby avoiding an immediate additional scan and extra radiation exposure. Existing methods focus on delineating an approximate dental arch and creating orthogonal projections along this arch. However, no golden standard is available for such dental arch extractions, and this choice can affect the quality of synthesized X-rays. To avoid such issues, we propose a novel method for synthesizing Panoramic X-rays from diverse head CBCTs, employing a simulated projection geometry and dynamic rotation centers. Our method effectively synthesized panoramic views from CBCT, even for patients with missing or nonexistent teeth and in the presence of severe metal implants. Our results demonstrate that this method can generate high-quality panoramic images irrespective of the CBCT scanner geometry.