Convolutional neural network-based metal and streak artifacts reduction in dental CT images with sparse-view sampling scheme.

PURPOSE: Sparse-view sampling has attracted attention for reducing the scan time and radiation dose of dental cone-beam computed tomography (CBCT). Recently, various deep learning-based image reconstruction techniques for sparse-view CT have been employed to produce high-quality image while effectively reducing streak artifacts caused by the lack of projection views. However, most of these methods do not fully consider the effects of metal implants. As sparse-view sampling strengthens the artifacts caused by metal objects, simultaneously reducing both metal and streak artifacts in sparse-view CT images has been challenging. To solve this problem, in this study, we propose a novel framework. METHODS: The proposed method was based on the normalized metal artifact reduction (NMAR) method, and its performance was enhanced using two convolutional neural networks (CNNs). The first network reduced the initial artifacts while preserving the fine details to generate high-quality priors for NMAR processing. Subsequently, the second network was employed to reduce the streak artifacts after NMAR processing of sparse-view CT data. To validate the proposed method, we generated training and test data by computer simulations using both extended cardiac-torso (XCAT) and clinical data sets. RESULTS: Visual inspection and quantitative evaluations demonstrated that the proposed method effectively reduced both metal and streak artifacts while preserving the details of anatomical structures compared with the conventional metal artifact reduction methods. CONCLUSIONS: We propose a framework for reconstructing accurate CT images in metal-inserted sparse-view CT. The proposed method reduces streak artifacts from both metal objects and sparse-view sampling while recovering the anatomical details, indicating the feasibility of fast-scan dental CBCT imaging.

Cone-Beam Angle Dependency of 3D Models Computed from Cone-Beam CT Images.

Cone-beam dental CT can provide high-precision 3D images of the teeth and surrounding bones. From the 3D CT images, 3D models, also called digital impressions, can be computed for CAD/CAM-based fabrication of dental restorations or orthodontic devices. However, the cone-beam angle-dependent artifacts, mostly caused by the incompleteness of the projection data acquired in the circular cone-beam scan geometry, can induce significant errors in the 3D models. Using a micro-CT, we acquired CT projection data of plaster cast models at several different cone-beam angles, and we investigated the dependency of the model errors on the cone-beam angle in comparison with the reference models obtained from the optical scanning of the plaster models. For the 3D CT image reconstruction, we used the conventional Feldkamp algorithm and the combined half-scan image reconstruction algorithm to investigate the dependency of the model errors on the image reconstruction algorithm. We analyzed the mean of positive deviations and the mean of negative deviations of the surface points on the CT-image-derived 3D models from the reference model, and we compared them between the two image reconstruction algorithms. It has been found that the model error increases as the cone-beam angle increases in both algorithms. However, the model errors are smaller in the combined half-scan image reconstruction when the cone-beam angle is as large as 10 degrees.

Half-scan artifact correction using generative adversarial network for dental CT.

Half-scan image reconstruction with Parker weighting can correct motion artifacts in dental CT images taken with a slow scan-based dental CT. Since the residual half-scan artifacts in the dental CT images appear much stronger than those in medical CT images, the artifacts often persist to the extent that they compromise the surface-rendered bone and tooth images computed from the dental CT images. We used a variation of generative adversarial network (GAN), so-called U-WGAN, to correct half-scan artifacts in dental CT images. For the generative network of GAN, we used a U-net structure of five stages to take advantage of its high computational efficiency. We trained the network using the Wasserstein loss function on the dental CT images of 40 patients. We tested the network with comparing its output images to the half-scan images corrected with other methods; Parker weighting and the other two popular GANs, that is, SRGAN and m-WGAN. For the quantitative comparison, we used the image quality metrics measuring the similarity of the corrected images to the full-scan images (reference images) and the noise level on the corrected images. We also compared the visual quality of the surface-rendered bone and tooth images. We observed that the proposed network outperformed Parker weighting and other GANs in all the image quality metrics. The computation time for the proposed network to process 336×336×336 3D images on a GPU-equipped personal computer was about 3 s, which was much shorter than those of SRGAN and m-WGAN, 50 s and 54 s, respectively.

Dose Reduction in Dental CT: A Phantom Study With Special Focus on Tin Filter Technique.

OBJECTIVE. The purpose of this study was to determine in a phantom the dose exposure of different dental 3D sectional imaging methods (CT and cone-beam CT [CBCT]) and different CT protocols. The aim was to establish optimal protocols with the lowest possible dose and diagnostically high image quality with special consideration given to tin prefiltration. MATERIALS AND METHODS. Dose was determined with thermoluminescence detectors at 20 different measuring points on an anthropomorphic phantom. Eight different CT protocols with and without tin filtering were compared with iterative reconstruction methods and a standard CBCT protocol. Objective and subjective image evaluations and a figure-of-merit analysis of the image data were performed by radiologists and maxillofacial surgeons. RESULTS. The determined dose-length products of the nine examinations were 5.0-111.9 mGy · cm with a calculated effective whole body dose of 20.7-505.9 µSv. Cone-beam CT was in the upper midfield with an effective dose of 229.3 µSv. On the basis of dose, objective image quality, and clinical evaluation results, tin filter protocols performed best. Protocols with higher doses were significantly less useful in the figure of merit comparison but because of their detailed bony representation are particularly necessary to answer certain questions about trauma and tumors. CONCLUSION. The use of tin filtering can reduce dose in dental CT examinations, compared with standard low-dose examinations, while maintaining good image quality. The dose performance is significantly inferior even to that of a cone-beam CT examination. High-dose protocols are necessary only for certain questions.

U-net based metal segmentation on projection domain for metal artifact reduction in dental CT.

Unlike medical computed tomography (CT), dental CT often suffers from severe metal artifacts stemming from high-density materials employed for dental prostheses. Despite the many metal artifact reduction (MAR) methods available for medical CT, those methods do not sufficiently reduce metal artifacts in dental CT images because MAR performance is often compromised by the enamel layer of teeth, whose X-ray attenuation coefficient is not so different from that of prosthetic materials. We propose a deep learning-based metal segmentation method on the projection domain to improve MAR performance in dental CT. We adopted a simplified U-net for metal segmentation on the projection domain without using any information from the metal-artifacts-corrupted CT images. After training the network with the projection data of five patients, we segmented the metal objects on the projection data of other patients using the trained network parameters. With the segmentation results, we corrected the projection data by applying region filling inside the segmented region. We fused two CT images, one from the corrected projection data and the other from the original raw projection data, and then we forward-projected the fused CT image to get the fused projection data. To get the final corrected projection data, we replaced the metal regions in the original projection data with the ones in the fused projection data. To evaluate the efficacy of the proposed segmentation method on MAR, we compared the MAR performance of the proposed segmentation method with a conventional MAR method based on metal segmentation on the CT image domain. For the MAR performance evaluation, we considered the three primary MAR performance metrics: the relative error (REL), the sum of square difference (SSD), and the normalized absolute difference (NAD). The proposed segmentation method improved MAR performances by around 5.7% for REL, 6.8% for SSD, and 8.2% for NAD. The proposed metal segmentation method on the projection domain showed better MAR performance than the conventional segmentation on the CT image domain. We expect that the proposed segmentation method can improve the performance of the existing MAR methods that are based on metal segmentation on the CT image domain.

Artifact correction in low-dose dental CT imaging using Wasserstein generative adversarial networks.

PURPOSE: In recent years, health risks concerning high-dose x-ray radiation have become a major concern in dental computed tomography (CT) examinations. Therefore, adopting low-dose computed tomography (LDCT) technology has become a major focus in the CT imaging field. One of these LDCT technologies is downsampling data acquisition during low-dose x-ray imaging processes. However, reducing the radiation dose can adversely affect CT image quality by introducing noise and artifacts in the resultant image that can compromise diagnostic information. In this paper, we propose an artifact correction method for downsampling CT reconstruction based on deep learning. METHOD: We used clinical dental CT data with low-dose artifacts reconstructed by conventional filtered back projection (FBP) as inputs to a deep neural network and corresponding high-quality labeled normal-dose CT data during training. We trained a generative adversarial network (GAN) with Wasserstein distance (WGAN) and mean squared error (MSE) loss, called m-WGAN, to remove artifacts and obtain high-quality CT dental images in a clinical dental CT examination environment. RESULTS: The experimental results confirmed that the proposed algorithm effectively removes low-dose artifacts from dental CT scans. In addition, we showed that the proposed method is efficient for removing noise from low-dose CT scan images compared to existing approaches. We compared the performances of the general GAN, convolutional neural networks, and m-WGAN. Through quantitative and qualitative analysis of the results, we concluded that the proposed m-WGAN method resulted in better artifact correction performance preserving the texture in dental CT scanning. CONCLUSIONS: The image quality evaluation metrics indicated that the proposed method effectively improves image quality when used as a postprocessing technique for dental CT images. To the best of our knowledge, this work is the first deep learning architecture used with a commercial cone-beam dental CT scanner. The artifact correction performance was rigorously evaluated and demonstrated to be effective. Therefore, we believe that the proposed algorithm represents a new direction in the research area of low-dose dental CT artifact correction.

Dental caries on CT in the ER population: prevalence and reporting practices.

PURPOSE: Although dental caries can be identified on CT and may be treatable, the literature provides little, if any, guidance on the responsibility of a neuroradiologist in reporting them. Untreated dental caries can impact diet and nutrition and can result in a variety of complications such as an odontogenic abscess, tooth loss, sinusitis, and dental pain, which can impact quality of life. The estimated prevalence of untreated dental caries in adults is 27%. In our experience, the prevalence of untreated dental caries in patients presenting to the Emergency Department (ED) is higher but dental caries are often unmentioned or unrecognized. We aim to determine the frequency of unreported dental caries and propose a paradigm for reporting and management. METHODS: Our research was IRB-approved and HIPPA compliant. We searched the radiology database for adult patients who underwent a CT of the facial bones while in the Emergency Department between January 1, 2015 and June 30, 2015. The examinations were reviewed by a faculty neuroradiologist for the presence of untreated dental caries. Untreated dental caries were documented and characterized by depth. Caries that were partially or completely obscured by dental amalgam artifact were excluded. The radiology reports were reviewed to evaluate reporting frequency. Statistical analysis was performed using Statistical Package for the Social Sciences (SPSS) software. RESULTS: A total of 200 patients (113 male, 87 female; age 18-98 years) underwent 200 CT examinations of the facial bones. One hundred fourteen (57%) patients had at least one dental caries. When caries were present, 14.9% of radiology reports included caries in the findings section and 9.6% of the reports mentioned caries in the impression. CONCLUSIONS: The presence of dental caries should be mentioned in the radiology report. The prevalence of untreated dental caries is higher in our cohort than reported in the general population, and dental caries are underreported by neuroradiologists at our institution. A paradigm for reporting and management was created upon collaboration with faculty from the University of Vermont Dental and Oral Health practice. A visit with a dentist should be recommended within 6 months if caries are limited to the enamel, within 3 months if caries involve the dentin, and within 2 weeks if caries extend in to the pulp. Further research is necessary to determine the clinical impact of improved reporting.

A motion artifact reduction method for dental CT based on subpixel-resolution image registration of projection data.

High-resolution imaging is essential in three-dimensional (3D) CT image-based digital dentistry. A small amount of head motion during a CT scan can degrade the spatial resolution of the images to the extent where the efficacy of 3D image-based digital dentistry is greatly compromised. We introduce a retrospective motion artifact reduction (MAR) method for dental CTs that eliminates the necessity for any external motion tracking devices. Assuming that rigid-body motions are dominant in a dental scan of a human head, we extracted motion information from the projection data. By taking the cross-correlation between two successive projection data for every projection view, we determined the displacement of the projection data at each view. We experimentally found that any motion of the imaging object during the scan resulted in displacement of the projection data proportional to the motion amplitude. We decomposed the displacement into two components, one caused by translational motion and the other caused by rotational motion. The displacement components were used to correct the projection data before CT image reconstruction. We experimentally verified the MAR method using the projection data of a few phantoms acquired through a clinical dental CT machine. When the MAR performance was evaluated by the structural similarity index (SSIM) and the normalized absolute error (NAE) in reference to the motion-less images, the SSIM improved to 99% while the NAE was reduced by 80-90%.

Dual-energy-based metal segmentation for metal artifact reduction in dental computed tomography.

PURPOSE: In a dental CT scan, the presence of dental fillings or dental implants generates severe metal artifacts that often compromise readability of the CT images. Many metal artifact reduction (MAR) techniques have been introduced, but dental CT scans still suffer from severe metal artifacts particularly when multiple dental fillings or implants exist around the region of interest. The high attenuation coefficient of teeth often causes erroneous metal segmentation, compromising the MAR performance. We propose a metal segmentation method for a dental CT that is based on dual-energy imaging with a narrow energy gap. METHODS: Unlike a conventional dual-energy CT, we acquire two projection data sets at two close tube voltages (80 and 90 kVp ), and then, we compute the difference image between the two projection images with an optimized weighting factor so as to maximize the contrast of the metal regions. We reconstruct CT images from the weighted difference image to identify the metal region with global thresholding. We forward project the identified metal region to designate metal trace on the projection image. We substitute the pixel values on the metal trace with the ones computed by the region filling method. The region filling in the metal trace removes high-intensity data made by the metallic objects from the projection image. We reconstruct final CT images from the region-filled projection image with the fusion-based approach. We have done imaging experiments on a dental phantom and a human skull phantom using a lab-built micro-CT and a commercial dental CT system. RESULTS: We have corrected the projection images of a dental phantom and a human skull phantom using the single-energy and dual-energy-based metal segmentation methods. The single-energy-based method often failed in correcting the metal artifacts on the slices on which tooth enamel exists. The dual-energy-based method showed better MAR performances in all cases regardless of the presence of tooth enamel on the slice of interest. We have compared the MAR performances between both methods in terms of the relative error (REL), the sum of squared difference (SSD) and the normalized absolute difference (NAD). For the dental phantom images corrected by the single-energy-based method, the metric values were 95.3%, 94.5%, and 90.6%, respectively, while they were 90.1%, 90.05%, and 86.4%, respectively, for the images corrected by the dual-energy-based method. For the human skull phantom images, the metric values were improved from 95.6%, 91.5%, and 89.6%, respectively, to 88.2%, 82.5%, and 81.3%, respectively. CONCLUSIONS: The proposed dual-energy-based method has shown better performance in metal segmentation leading to better MAR performance in dental imaging. We expect the proposed metal segmentation method can be used to improve the MAR performance of existing MAR techniques that have metal segmentation steps in their correction procedures.

Metal Artifact Reduction in Dental Computed Tomography Images Based on Sinogram Segmentation Using Curvelet Transform Followed by Hough Transform.

In X-ray computed tomography (CT), the presence of metal objects in a patient's body produces streak artifacts in the reconstructed images. During the past decades, many different methods were proposed for the reduction or elimination of the streaking artifacts. When scanning a patient, the projection data affected by metal objects (missing projections) appear as regions with high intensities in the sinogram. In spiral fan beam CT, these regions are sinusoid-like curves on sinogram. During the first time, if the metal curves are detected carefully, then, they can be replaced by corresponding unaffected projections using other slices or opposite views; therefore, the CT slices regenerated by the modified sonogram will be imaged with high quality. In this paper, a new method of the segmentation of metal traces in spiral fan-beam CT sinogram is proposed. This method is based on a sinogram curve detection using a curvelet transform followed by 2D Hough transform. The initial enhancement of the sinogram using modified curvelet transform coefficients is performed by suppressing all the coefficients of one band and applying 2D Hough transform to detect more precisely metal curves. To evaluate the performance of the proposed method for the detection of metal curves in a sinogram, precision and recall metrics are calculated. Compared with other methods, the results show that the proposed method is capable of detecting metal curves, with better precision and good recovery.

A bench-top micro-CT capable of simulating head motions.

Computational three-dimensional (3D) models of a dental structure generated from 3D dental computed tomography (CT) images are now widely used in digital dentistry. To generate precise 3D models, high-resolution imaging of the dental structure with a dental CT is required. However, a small head motion of the patient during the dental CT scan could degrade the spatial resolution of CT images to the extent that digital dentistry is no longer possible. A bench-top micro-CT has been built to evaluate the head motion effects on the dental CT images. A micro-CT has been built on an optic table with a micro-focus x-ray source and a flat-panel detector. A rotation stage, placed in between the x-ray source and the detector, is mounted on two-directional goniometers that can rotate the rotation stage in two orthogonal directions while the rotation stage is performing the CT scan. The goniometers can make object motions of an arbitrary waveform to simulate head tilting or head nodding. CT images of a phantom have been taken with and without introducing the motions, and the motion effects on the CT images have been evaluated. Object motions parallel to the detector plane have greater effects on the CT images than those against the detector plane. With the bench-top micro-CT, the motion effects have been visually seen at a tiny rotational motion as small as 0.3°. The bench-top micro-CT can be used to evaluate head motion effects on the dental CT images. The projection data, taken with the motion effects, would be used to develop motion artifact correction methods for a high-resolution dental-CT.

Analysis of human dentition from Early Bronze Age: 4000-year-old puzzle.

This paper presents the first ever paleodontological investigation of human remains from an archeological site in Central Europe dating from the Early Bronze Age and attributed to the Strzyzow Culture. It corroborates the knowledge gained from archeological, anthropological and genetical investigations. Our study aimed to assess dental status, dental morphology and dental pathologies as well as tooth wear and enamel hypoplasia based on visual inspection and stereomicroscopic investigation. The research was supported by CBCT imaging to obtain digital images and 3D reconstructions as well as 2D radiographs essential for dental age estimation. All of the 191 teeth discovered showed morphological similarity, with adult teeth showing similar color, shape and size. A maxillary molar presenting with a unique root morphology and a mandibular molar with a rare occlusal surface were found. Both permanent and deciduous dentition presented significant tooth wear. A few specimens displayed signs of dental caries, periapical pathology and antemortem tooth loss. Three individuals exhibited linear enamel hypoplasia. CBCT provided high-quality 2D images useful for dental age estimation by non-destructive methods. Estimated dental age correlated with the age estimated by other anthropological methods. In one case, this was crucial because of insufficient material for anthropological analysis. The presented studies have proved that besides the skeleton, teeth can be used as a fundamental tool in assessing the overall health and living conditions of paleopopulations. It would seem that there is potential for considerable development to be made in the research and investigation of paleodontological material using CBCT.

A metal artifact reduction method for a dental CT based on adaptive local thresholding and prior image generation.

BACKGROUND: Metal artifacts appearing as streaks and shadows often compromise readability of computed tomography (CT) images. Particularly in a dental CT in which high resolution imaging is crucial for precise preparation of dental implants or orthodontic devices, reduction of metal artifacts is very important. However, metal artifact reduction algorithms developed for a general medical CT may not work well in a dental CT since teeth themselves also have high attenuation coefficients. METHODS: To reduce metal artifacts in dental CT images, we made prior images by weighted summation of two images: one, a streak-reduced image reconstructed from the metal-region-modified projection data, and the other a metal-free image reconstructed from the original projection data followed by metal region deletion. To make the streak-reduced image, we precisely segmented the metal region based on adaptive local thresholding, and then, we modified the metal region on the projection data using linear interpolation. We made forward projection of the prior image to make the prior projection data. We replaced the pixel values at the metal region in the original projection data with the ones taken from the prior projection data, and then, we finally reconstructed images from the replaced projection data. To validate the proposed method, we made computational simulations and also we made experiments on teeth phantoms using a micro-CT. We compared the results with the ones obtained by the fusion prior-based metal artifact reduction (FP-MAR) method. RESULTS: In the simulation studies using a bilateral prostheses phantom and a dental phantom, the proposed method showed a performance similar to the FP-MAR method in terms of the edge profile and the structural similarity index when an optimal global threshold was chosen for the FP-MAR method. In the imaging studies of teeth phantoms, the proposed method showed a better performance than the FP-MAR method in reducing the streak artifacts without introducing any contrast anomaly. CONCLUSIONS: The simulation and experimental imaging studies suggest that the proposed method can be used for reducing metal artifacts in dental CT images.

Comparative study of dentascan and radiography for radiological evaluation of impacted teeth.

INTRODUCTION: Impacted teeth present a very common problem in dentistry due to the variable numbers of problems they cause. They have previously been imaged by radiography which is very inaccurate. Dental CT is an upcoming modality which very accurately images the teeth. AIM: The aim of our study was to compare the efficacy of Dental CT with radiography in assessing the morphology of the impacted tooth and its relation to adjacent structures. MATERIALS AND METHODS: We conducted a hospital based prospective study in which all patients with impacted teeth who underwent Dental CT and Radiographic evaluation were evaluated. RESULTS: The morphology of all the teeth was well visualized on CT. Resorption of adjacent tooth was missed in 7 teeth by radiography. In a significant number of cases (10/30) the relation of the impacted tooth with the mandibular canal could not be visualized on the radiographs. CONCLUSION: We concluded that Dental CT yields markedly better information than radiographs regarding impacted teeth with respect to divergence of the roots, relation of the impacted tooth with the adjacent tooth, nasal floor, maxillary sinus and mandibular canal. However, Dental CT was found to be only marginally better than Radiographs for assessment of number of roots, inclination of the impacted tooth and relation of the tooth with alveolar crest. Dental CT was also proved to be an indispensable diagnostic tool for the determination of the buccolingual inclination and relationsof the impacted tooth.

Evaluation of Bone Density Around the Implants Placed Using Drilling Technique and Bone Expansion Technique: An In vivo Study.

Bone density is a key parameter in determining the surgical procedure of implant placement and for the predictability of successful implant treatment. Several clinical studies have shown lower survival rates of implants in maxilla which was attributed to poor bone quality. The present study compared the variations in the pre-operative and post-operative bone density values in Hounsfield units using CT between drilling technique and bone expansion technique at 0.25 and 1.0 mm sections at two sites which were selected in maxillary arch between the second premolar regions of either quadrants and results have shown bone expansion technique is superior to drilling technique in division III bone.

Detection of a secondary mesio-buccal canal in maxillary first molar: A comparative study.

AIM: The purpose of this study was to clarify detection characteristics of the secondary mesio-buccal canal in maxillary first molars using various methods. MATERIALS AND METHODS: The root canal system of 86 extracted human maxillary first molars was inspected using micro-focus-computed tomography to accurately determine the number of canals. Radiographs or floors of the pulp chamber for all samples were observed for the secondary mesio-buccal canal with computed tomography for dentistry, digital dental radiography, magnifier, or the naked eye. Sensitivity, specificity, positive, and negative predictive values and diagnostic accuracy for these four methods were investigated using the results from the micro-focus-computed tomography inspection as the gold standard. All samples of each method were observed by 10 endodontists. Using these results, the χ(2) test was used to compare and analyze differences between the various conditions (P<0.05). RESULTS: The secondary mesio-buccal canal could be recognized in 60.9% of samples with the micro-focus-computed tomography. No significant difference was seen between efficiencies of the computed tomography for dentistry and the micro-focus-computed tomography. The computed tomography for dentistry was superior to the other three methods. CONCLUSION: Detectability of the secondary mesio-buccal canal in the maxillary first molar was superior using dental-computed tomography compared to digital dental radiography, magnification telescope, and the naked eye.

3D imaging reconstruction and impacted third molars: case reports.

There is a debate in the literature about the need for Computed Tomagraphy (CT) before removing third molars, even if positive radiographic signs are present. In few cases, the third molar is so close to the inferior alveolar nerve that its extraction might expose patients to the risk of post-operative neuro-sensitive alterations of the skin and the mucosa of the homolateral lower lip and chin. Thus, the injury of the inferior alveolar nerve may represent a serious, though infrequent, neurologic complication in the surgery of the third molars rendering necessary a careful pre-operative evaluation of their anatomical relationship with the inferior alveolar nerve by means of radiographic imaging techniques. This contribution presents two case reports showing positive radiographic signs, which are the hallmarks of a possible close relationship between the inferior alveolar nerve and the third molars. We aim at better defining the relationship between third molars and the mandibular canal using Dental CT Scan, DICOM image acquisition and 3D reconstruction with a dedicated software. By our study we deduce that 3D images are not indispensable, but they can provide a very agreeable assistance in the most complicated cases.