3D CBCT Artefact Removal Using Perpendicular Score-Based Diffusion Models
Authors: Susanne Schaub, Florentin Bieder, Matheus L. Oliveira, Yulan Wang, Dorothea Dagassan-Berndt, Michael M. Bornstein, Philippe C. Cattin
Organizations: Department of Biomedical Engineering, University of Basel, Allschwil, Switzerland · Piracicaba Dental School, University of Campinas, Piracicaba, Brazil · State Key Laboratory of Oral & Maxillofacial Reconstruction and Regeneration, Key Laboratory of Oral Biomedicine Ministry of Education, Hubei Key Laboratory of Stomatology, School & Hospital of Stomatology, Wuhan University, Wuhan, China · Department of Oral Health & Medicine, University Center for Dental Medicine, University of Basel, Basel, Switzerland · Dental Imaging, University Center for Dental Medicine, University of Basel, Basel, Switzerland
Cone-beam computed tomography (CBCT) is a widely used 3D imaging technique in dentistry, offering high-resolution images while minimising radiation exposure for patients. However, CBCT is highly susceptible to artefacts arising from high-density objects such as dental implants, which can compromise image quality and diagnostic accuracy. To reduce artefacts, implant inpainting in the sequence of projections plays a crucial role in many artefact reduction approaches. Recently, diffusion models have achieved state-of-the-art results in image generation and have widely been applied to image inpainting tasks. However, to our knowledge, existing diffusion-based methods for implant inpainting operate on independent 2D projections. This approach neglects the correlations among individual projections, resulting in inconsistencies in the reconstructed images. To address this, we propose a 3D dental implant inpainting approach based on perpendicular score-based diffusion models, each trained in two different planes and operating in the projection domain. The 3D distribution of the projection series is modelled by combining the two 2D score-based diffusion models in the sampling scheme. Our results demonstrate the method's effectiveness in producing high-quality, artefact-reduced 3D CBCT images, making it a promising solution for improving clinical imaging.
Figures & tables
Figure 1: A primary diffusion model is trained on projections along the original projection direction, while a secondary model is trained on perpendicular projections. During sampling, the algorithm alternates between the two models to generate a coherent 3D image.
Figure 2: We computed the projection series from our implant-free CBCT reconstructions. Implants were added with a mask, which serves as input to the TPDM.
SSIM ( ↑ )
PSNR ( ↑ )
RMSE ( ↓ )
Projections
TPDM
0.9290 ± 0.0085
35.8660 ± 1.1841
0.0037 ± 0.0010
DPS
0.9110 ± 0.0152
33.0039 ± 1.7146
0.0044 ± 0.0010
LI
0.8834 ± 0.0168
30.3120 ± 1.1217
0.0055 ± 0.0017
Reconstruction
TPDM
0.9850 ± 0.0078
50.3875 ± 3.8834
0.0008 ± 0.0003
DPS
0.9848 ± 0.0100
49.9010 ± 4.0727
0.0008 ± 0.0003
LI
0.9810 ± 0.0084
47.1244 ± 3.3138
0.0010 ± 0.0004
Table 1: We report the average scores for our test set. The projection row shows the scores calculated only within the inpainted masks in the projections. The results in the reconstruction row were calculated over the whole reconstruction.
Figure 3: Top: CBCT reconstructions of an exemplary image. Bottom: Difference maps with respect to the reference image. The images used for the difference maps are in the range [-0.04, 0.07].
Metal artifacts generated by dental implants significantly degrade cone-beam computed tomography (CBCT) volumes, obscuring critical anatomical structures and compromising diagnostic precision. To address this, an unsupervised deep learning framework has been proposed for Metal Artifact Reduction (MAR) utilizing a Cycle-Consistent Adversarial Network (CycleGAN) optimized for high-fidelity restoration. Unlike supervised methods that rely on unattainable voxel-aligned paired datasets, the proposed approach leverages an unpaired dataset of approximately 4,000 images, curated from the public ToothFairy dataset. The architecture integrates U-Net-based generators and PatchGAN discriminators, specifically tuned to mitigate generative hallucinations and preserve morphological integrity. Quantitative benchmarking on a held-out test set demonstrates a 34.6% improvement in the Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE) score, a substantial reduction in Fréchet Inception Distance (FID) from 207.03 to 157.04, and a superior Structural Similarity Index Measure (SSIM) of 0.9105. The framework achieves real-time efficiency with a 3.03 ms inference time per slice, effectively suppressing artifacts while preserving anatomical detail. Expert validation confirms high fidelity; however, to ensure reliability in extreme cases, the architecture is recommended as a clinical decision-support tool under human-in-the-loop oversight. By enhancing diagnostic clarity via a scalable software pipeline, this study provides a robust solution for high-fidelity dental implant imaging.
G. L. T. Chamika, S. N. A. Dhanapala, P. H. S. V. Nimalaweera +2
Department of Electrical and Electronic Engineering, University of Peradeniya, Peradeniya, Sri Lanka · Department of Oral Medicine and Periodontology, Faculty of Dental Sciences, University of Peradeniya, Peradeniya, Sri Lanka
Dental cone-beam computed tomography (CBCT) systems often employ detector configurations that provide a truncated field of view (FOV) that only captures a small part of the patient's anatomy. In this work, we aim to reconstruct an extended FOV using projections of truncated FOV scans. To this end, we propose a three-stage framework that consists of (1) an implicit neural representation (INR) for estimating missing parts of the truncated projection data, (2) an iterative reconstruction for generating a secondary volumetric image with improved anatomical consistency and (3) a fast diffusion model for image enhancement. The proposed approach combines the strengths of continuous representations, physics-based reconstruction and generative refinement within a unified pipeline for truncated CBCT imaging. Experimental results demonstrate that the method effectively reduces truncation artifacts, improves the reconstruction of structures extending beyond the original FOV and produces images with enhanced quality. Our code is publicly available at https://github.com/SusanneSchaub/CBCT-FOV-Extension.
Susanne Schaub, Florentin Bieder, Matheus L. Oliveira +5
Department of Biomedical Engineering, University of Basel, Allschwil, Switzerland · Piracicaba Dental School, University of Campinas, Piracicaba, Brazil · State Key Laboratory of Oral & Maxillofacial Reconstruction and Regeneration, Key Laboratory of Oral Biomedicine Ministry of Education, Hubei Key Laboratory of Stomatology, School & Hospital of Stomatology, Wuhan University, Wuhan, China +2
Accurate 3D dental imaging is vital for diagnosis and treatment planning, yet CBCT's high radiation dose and cost limit its accessibility. Reconstructing 3D volumes from a single low-dose panoramic X-ray is a promising alternative but remains challenging due to geometric inconsistencies and limited accuracy. We propose HiCT, a two-stage framework that first generates geometrically consistent multi-view projections from a single panoramic image using a video diffusion model, and then reconstructs high-fidelity CBCT from the projections using a ray-based dynamic attention network and an X-ray sampling strategy. To support this, we built XCT, a large-scale dataset combining public CBCT data with 500 paired PX-CBCT cases. Extensive experiments show that HiCT achieves state-of-the-art performance, delivering accurate and geometrically consistent reconstructions for clinical use.