To explore transfer learning (TL) techniques for enhancing vertical root fracture (VRF) diagnosis accuracy and to assess the impact of artificial intelligence (AI) on image enhancement for VRF detection on both extracted teeth images and intraoral images taken from patients.

A dataset of 378 intraoral periapical radiographs comprising 195 teeth with fractures and 183 teeth without fractures serving as controls was included. DenseNet, ConvNext, Inception121, and MobileNetV2 were employed with model fusion. Prior to evaluation, Particle Swarm Optimization (PSO) and Deep Learning (DL) image enhancement were applied. Performance assessment included accuracy rate, precision, recall, F1-score, AUC, and kappa values. Intra- and inter-observer agreement, according to the Gold Standard (GS), were assessed using ICC and t-tests. Statistical significance was set at p < 0.05.

The DenseNet + Inception fusion model achieved the highest accuracy rate of 0.80, with commendable recall, F1-score, and AUC values, supported by precision (0.81) and kappa (0.60) values. Molar tooth examination yielded an accuracy rate, precision, recall, and F1-score of 0.80, with an AUC of 0.84 and kappa of 0.60. For premolar teeth, the fusion network showed an accuracy rate of 0.78, an AUC of 0.78, and notable metrics, including F1-score (0.80), recall (0.85), precision (0.71), and kappa (0.55). ICC results demonstrated acceptable agreement (≥ 0.57 for molars, ≥ 0.52 for premolars).

TL methods have demonstrated significant potential in enhancing diagnostic accuracy for VRFs in radiographic imaging. TL is emerging as a valuable tool in the development of robust, automated diagnostic systems for VRF identification, ultimately supporting clinicians in delivering more accurate diagnoses.

Cone-beam computed tomography (CBCT) is widely used in radiotherapy to image patient configuration before treatment but its image quality is lower than planning CT due to scattering, motion, and reconstruction methods. This reduces the accuracy of Hounsfield units (HU) and limits its use in adaptive radiation therapy (ART). However, synthetic CT (sCT) generation using deep learning methods for CBCT intensity correction faces challenges due to deformation. To address these issues, we propose enhancing CBCT quality using a conditional denoising diffusion probability model (CDDPM), which is trained on pseudo-CBCT created by adding pseudo-scatter to planning CT. The CDDPM transforms CBCT into high-quality sCT, improving HU accuracy while preserving anatomical configuration. The performance evaluation of the proposed sCT showed a reduction in mean absolute error (MAE) from 81.19 HU for CBCT to 24.89 HU for the sCT. Peak signal-to-noise ratio (PSNR) improved from 31.20 dB for CBCT to 33.81 dB for the sCT. The Dice and Jaccard coefficients between CBCT and sCT for the colon, prostate, and bladder ranged from 0.69 to 0.91. When compared to other deep learning models, the proposed sCT outperformed them in terms of accuracy and anatomical preservation. The dosimetry analysis for prostate cancer revealed a dose error of over 10% with CBCT but nearly 0% with the sCT. Gamma pass rates for the proposed sCT exceeded 90% for all dose criteria, indicating high agreement with CT-based dose distributions. These results show that the proposed sCT improves image quality, dosimetry accuracy, and treatment planning, advancing ART for pelvic cancer.

This study aimed to explore the reliability of cone beam computed tomography (CBCT) in evaluating the quality of augmented bone after lateral sinus floor elevation (LSFE) with xenografts.

Thirty-six patients with lost maxillary molars were included, with half of whom received LSFE with xenografts and staged implant placement, and the other half showed no vertical bone defects and underwent implant placement directly. A total of 36 implants were included, with 18 implants in each group. A CBCT exam was taken before implant placement to acquire data on mineral quality at the future implant site, including bone mineral density (BMD), various microstructure indices, and gray values (GVs) within different threshold ranges. Augmented bone biopsies were collected during implant preparation. The microstructure indices and histological characteristics of the biopsies were evaluated by micro computed tomography (μCT) and histological staining. An implant-oriented volume of interest for CBCT analysis was established to co-locate the CBCT-measured data and the biopsy-related data using 3DSlicer. A Spearman rank correlation test was used to analyze the relationship between CBCT-measured data and the biopsy-related data.

μCT-measured microstructure indices of the augmented bone (BV/TV and Tb.Th) were significantly correlated with new bone area (BV/TV, p = 0.035, r = 0.498; Tb.Th, p = 0.027, r = 0.520). No correlation was found between the CBCT-measured and μCT-measured microstructure indices. CBCT-measured BMD and microstructure indices hardly showed any correlation with histological indices (p > 0.05). When the threshold was set from 0 to 50, the mean GVs were significantly, positively correlated with new bone area (p = 0.041, r = 0.486), and bone substitute area was positively correlated to the mean GVs of higher threshold (range 60-255, p = 0.048, r = 0.472; range 70-255, p = 0.009, r = 0.593).

CBCT without bone substitute segmentation was not reliable for evaluating the quality of xenogenic augmented bone after LSFE. The influence of the xenogenic substitute on CBCT analysis can be reduced by setting a low GV threshold. The bone substitute segmentation strategy may present a new way to increase the reliability of CBCT in evaluating xenogenic augmented bone.

Synthetic CT (sCT) generation from cone-beam CT (CBCT) must maintain stable performance and allow for accurate dose calculation across all treatment fractions to effectively support adaptive proton therapy. This study evaluated a 3D deep-learning (DL) network for sCT generation for prostate cancer patients over the full treatment course.

Patient data from 25/6 prostate cancer patients were used to train/test the DL network. Patients in the test set had a planning CT, 39 CBCT images, and at least one repeat CT (reCT) used for replanning. The generated sCT images were compared to fan-beam planning and reCT images in terms of i) CT number accuracy and stability within spherical regions-of-interest (ROIs) in the bladder, prostate, and femoral heads, ii) proton range calculation accuracy through single-spot plans, and iii) dose trends in target coverage over the treatment course (one patient).

The sCT images demonstrated image quality comparable to CT, while preserving the CBCT anatomy. The mean CT numbers on the sCT and CT images were comparable, e.g. for the prostate ROI they ranged from 29 HU to 59 HU for sCT, and from 36 HU to 50 HU for CT. The largest median proton range difference was 1.9 mm. Proton dose calculations showed excellent target coverage (V95%≥99.6 %) for the high-dose target.

The DL network effectively generated high-quality sCT images with CT numbers, proton range, and dose characteristics comparable to fan-beam CT. Its robustness against intra-patient variations makes it a feasible tool for adaptive proton therapy.

Lack of Hounsfield Unit (HU) accuracy leads to misrepresentation of tissue densities and causes image artifacts in dental cone beam computed tomography (CBCT) images. This work investigates the improvement in HU accuracy in dental CBCT by suppressing scatter with a novel two-dimensional anti-scatter grid (2D ASG) approach.

A 2D ASG prototype was developed and integrated into an experimental CBCT system, emulating dental CBCT geometry. CBCT scans were acquired using a multidetector CT (MDCT), a clinical dental CBCT, and the proposed 2D ASG-based experimental CBCT system. Subsequently, HU accuracy, nonuniformity, and contrast-to-noise ratio (CNR) were evaluated in image quality phantoms benchmarked against MDCT images. The effect of scatter suppression on the implant-induced HU degradation was also studied.

2D ASG reduced scatter content up to a factor of 6.6 in CBCT scans and HU nonuniformity in soft tissue-like regions was reduced from 23 to 4 HU. HU errors in high-density structures were within 65 HU of values measured in the gold standard MDCT images. Robust scatter suppression also reduced streak artifacts caused by implants. CNR increased up to 47% in images acquired with the 2D ASG.

HU accuracy in dental CBCT may reach the accuracy of MDCT with the proposed 2D ASG. Moreover, artifacts are reduced, and contrast visualization can be improved. Hence, this approach may enable a more accurate assessment of tissue densities in CBCT images, and improved image quality may positively impact the diagnostic capabilities of dental CBCT systems.

The aim of this study was to determine the efficacy of different protocols of cone beam computed tomography units with image resolutions for identifying dental root fractures. Accordingly, 24 single-rooted teeth were endodontically prepared using gutta-percha, fibreglass, or metal. Root fractures were caused in 50% of the samples. The teeth were included in a dry jaw and scanned using two tomographic units: OP300 and 3D Veraview. These tomographs respectively achieved an accuracy of 0.88 and 0.83 and a sensitivity of 0.78 and 0.83. The OP300 Maxio device had a high specificity of 0.98 compared to the 3D Veraview's 0.83. Thus, the two devices tested were both adequate for the identification of root fractures. However, the 3D Veraview demonstrated greater accuracy in the detection of root fractures in roots containing metal posts, while the OP300 showed greater accuracy with the use of fibreglass posts. The presence of gutta-percha compromised the identification of fractures with both devices.

The purpose of this study was to evaluate how artefacts caused by titanium and zirconia dental implants affect the bone quality assessment in CBCT images. The effect of scan mode and the use of metal artefact reduction (MAR) algorithm on artefacts suppression were taken in consideration.

Titanium and zirconia dental implants were installed in porcine bone samples and scanned with two CBCT devices with adjustments on scan mode and with the use of MAR. The control group consisted of bone sample without implant and scanned with full-rotation scan mode without MAR. Artefacts extension and bone quality around implants were measured by deviation of grey values and bone histomorphometry measurements (trabecular volume fraction, bone specific surface, trabecular thickness, and trabecular separation), respectively. Mean difference among groups was assessed by within ANOVA with Bonferroni correction. Correlation between bone quality measurements acquired in the experimental and control groups was assessed by Spearman correlation test (α = .05).

No statistical difference was found for artefacts extension in images acquired by half and full-rotation modes (P = .82). The application of MAR reduced artefacts caused by titanium and zirconia dental implants, showing no statistically significant difference from the control group (titanium: P = .20; zirconia: P = .31). However, there was no correlation between bone quality measurements (P < .05).

Bone quality assessment was affected by the presence of artefacts caused by dental implants. Rotation mode did not affect the appearance of artefacts and bone qualitative measurements. MAR was able to decrease artefacts, however, it did not improve the accuracy of bone quality measurements.

To evaluate the effect of various tube voltage (kV) settings on the accuracy of cone-beam computed tomography (CBCT) images in measuring trabecular microstructure and cortical morphology, using micro-CT (μCT) as the reference.

Ten bone samples of sheep mandibles were scanned using both μCT and CBCT at three different tube voltage settings (80, 85, and 90 kV). Identical regions of interest (ROIs) on trabecular and cortical bones were analyzed in all images. Measurements of trabecular microstructure included bone volume fraction (BV/TV), trabecular thickness (Tb.Th) and space (Tb.Sp), while thickness (Ct.Th) and area (Ct.Ar) of cortical bone were measured to determine cortical morphology. Measurements were compared using paired t-test, while agreement between measurements of two modalities was assessed using Bland-Altman analysis. One-way ANOVA was used to determine differences in measurements of CBCT images at different kVs (p < 0.01).

Compared to μCT, CBCT overestimated trabecular parameters and Ct.Th but underestimated Ct.Ar, with high agreement observed between the methods. Significant differences were found for all measurements except BV/TV and Ct.Ar at all kVs. No differences were observed between CBCT measurements at different tube potentials.

The tube voltage of CBCT has minimal impact on the measurement accuracy of most microstructural parameters. BV/TV and Ct.Ar measurements may be particularly preferred for bone evaluations using CBCT images.

Leukemic patients often display clinical signs like anemia, thrombocytopenia, and hepatosplenomegaly. Early diagnosis is crucial for intervention and improved prognosis. Dentists can help identify these signs through oral masses, gingival bleeding, and oral ulceration, with radiographical features like bone osteolysis, moth-eating appearance, and abnormal tooth chronology. This study aimed to achieve early diagnosis of leukemic child patients (LCP) by the dentist based on their clinical, age estimation, and radiographical oral signs. Twenty-three children suffer from leukemia, selected after an initial diagnosis based on their clinical signs with an abnormal CBC or abnormal WBCs. These patients were accessed clinically for oral signs and radiographically using panoramic radiographs and cone beam computed tomography (CBCT) to evaluate chronology and bone density. LCP were compared with systematically free control child cases (SFC) who went for a panoramic image and CBCT scan needed for their orthodontic problems. Clinical results for LCP revealed (100%) of cases showed gingival bleeding, (87%) of cases showed gingival masses, (83%) of cases revealed aphthous-like ulceration, and (100%) of cases had different grades of mobility related to the lower first permanent molar used as markers for tooth affection. Radiographical results revealed a statistically significant decrease (P value ≤ 0.05) in LCP age revealed by panoramic and CBCT images in comparison with their actual age. Also, there was a statistically significant decrease in bone density shown by LCP regarding selected regions. LCP could be early diagnosed by the dentist through clinical and radiographical indicators. Diagnosing acute lymphoblastic leukemia (ALL) in its early stages remains a significant challenge due to the nonspecific and often subtle nature of initial symptoms. Dental practitioners can bridge the gap between routine dental care and early systemic disease detection, potentially expediting medical intervention and improving outcomes for children with acute lymphoblastic leukemia.

Cone Beam Computed Tomography (CBCT) has improved diagnosis and treatment planning in paediatric dentistry, but no bibliometric studies have examined the research landscape. This study provides an overview regarding the role of CBCT in paediatric dentistry.

A bibliometric review was conducted using articles from the Web of Science database. The search was performed on 22 February 2024, including publications up to that date. Conference papers and editorials were excluded. Data extracted included citation counts, publication dates, journals, impact factors, study designs, topics, geographical and institutional affiliations, authors, and keywords. Collaborative networks were visualised using VOSviewer, and Spearman's correlation assessed the relationship between citation counts and other variables.

The review analysed 517 articles, with the most cited receiving 557 citations. Publication dates ranged from 2005 to 2024, with a peak in 2023. Observational studies were the most common, particularly on maxillary expansion. The American Journal of Orthodontics and Dentofacial Orthopedics was the most cited journal, and the USA was a major contributor. Jacobs R authored the most articles (n=19), and the University of Alberta led in institutional output. Spearman's correlation showed a weak positive correlation between citation count and journal impact factor (rho=0.272, p<0.001) and a strong negative correlation with publication year (rho=-0.762, p<0.001).

This bibliometric review provides an overview of the use of CBCT in paediatric dentistry, particularly in maxillary expansion. The findings suggest that more specific imaging protocols may improve safety and clinical outcomes, and that further investigation of long-term outcomes may provide valuable insights.

The precision of dentin thickness evaluations in the presence of artifacts is vital, as inaccuracies may increase the risk of over-preparation and consequent structural damage to the tooth. The purpose of this in vitro study was to evaluate the accuracy of residual dentin thickness measurements in CBCT images of teeth with high-density intracanal materials, utilizing the blooming artifact reduction (BAR) filter. Twelve single-rooted human teeth were selected. Axial cuts were performed, and the root thickness was measured at the buccal, lingual, mesial, and distal surfaces, which represented the reference standard. CBCT scans were acquired of each specimen in 5 different settings: empty root canals (ERC), gutta-percha cone (GPC), gutta-percha and endodontic sealer (GPC + S), fiberglass post (FGP), and metal post (MP). Measurements were performed before and after the application of the BAR filter in the e-vol DX software. ANOVA with the Dunnet's post hoc test was used for comparison between measurements in CBCT images and the reference standard. The BAR filter did not influence the measurements in teeth with ERC, GPC, and FGP (p > 0.05). In teeth with GPC + S, the measurements with the BAR filter had no difference from the reference standard (p < 0.05). CBCT images measurements were comparable to the reference standard in the ERC, GPC, and FGP groups. BAR filter was restricted to the GPC + S group in the cervical third, and the MP group in the apical third. In root canals with metal posts, the overall dentin thickness was significantly underestimated in all CBCT images within the cervical and middle thirds.

Cone-beam computed tomography (CBCT) scans, performed fractionally (e.g., daily or weekly), are widely utilized for patient alignment in the image-guided radiotherapy (IGRT) process, thereby making it a potential imaging modality for the implementation of adaptive radiotherapy (ART) protocols. Nonetheless, significant artifacts and incorrect Hounsfield unit (HU) values hinder their application in quantitative tasks such as target and organ segmentations and dose calculation. Therefore, acquiring CT-quality images from the CBCT scans is essential to implement online ART in clinical settings.

This work aims to develop an unsupervised learning method using the patient-specific diffusion model for CBCT-based synthetic CT (sCT) generation to improve the image quality of CBCT.

The proposed method is in an unsupervised framework that utilizes a patient-specific score-based model as the image prior alongside a customized total variation (TV) regularization to enforce coherence across different transverse slices. The score-based model is unconditionally trained using the same patient's planning CT (pCT) images to characterize the manifold of CT-quality images and capture the unique anatomical information of the specific patient. The efficacy of the proposed method was assessed on images from anatomical sites including head and neck (H&N) cancer, pancreatic cancer, and lung cancer. The performance of the proposed CBCT correction method was evaluated using quantitative metrics, including mean absolute error (MAE), non-uniformity (NU), and structural similarity index measure (SSIM). Additionally, the proposed algorithm was benchmarked against other unsupervised learning-based CBCT correction algorithms.

The proposed method significantly reduced various kinds of CBCT artifacts in the studies of H&N, pancreatic, and lung cancer patients. In the lung stereotactic body radiation therapy (SBRT) patient study, the MAE, NU, and SSIM were improved from 47 HU, 45 HU, and 0.58 in the original CBCT images to 13 HU, 14 dB, and 0.67 in the generated sCT images. Compared to other unsupervised learning-based algorithms, the proposed method demonstrated superior performance in artifact reduction.

The proposed unsupervised method can generate sCT from CBCT with reduced artifacts and precise HU values, enabling CBCT-guided segmentation and replanning for online ART.

To evaluate the influence of different dental implant materials within the exomass on the image quality in cone-beam computed tomography (CBCT).

Five pig jaws were scanned using four CBCT devices, first without any dental implants, followed by scans with three dental implants of the same material-pure titanium, titanium-zirconium alloy, and zirconium dioxide. Two fields of view (FOVs) were used for each device to position the implants in the exomass of a small FOV and within a large FOV. Voxel values were obtained from tubes containing a radiopaque solution to calculate mean voxel value (MVV), voxel value inhomogeneity (VVI), and image noise (IN), which were compared across implant materials and FOVs using repeated measures analysis of variance (α = 0.05). Three observers independently scored image quality using a 5-point scale.

In general, MVV remained unaffected, except for a significant increase in the X800 device when titanium or titanium-zirconium alloy implants were in the exomass of a small FOV (p ≤ 0.05). A trend of increased VVI was observed when implants were in the exomass of a small FOV, with a greater effect for zirconium dioxide, followed by titanium-zirconium alloy and titanium. IN was higher when implants were in the exomass, especially for zirconium dioxide implants (p ≤ 0.05). Image quality perception was consistent overall, though zirconium dioxide implants in both FOVs resulted in diminished quality.

The presence of implants in the exomass can negatively affect CBCT image quality, with zirconium dioxide having the greatest impact.

Dental radiography is an essential tool in endodontics for determination of diagnosis, treatment planning and monitoring of treatment outcome. Conventional two-dimensional imaging remains the most commonly used and the standard method of radiographic imaging in endodontics due to accessibility and low radiation exposure. The use of cone beam computed tomography is increasing worldwide due to the benefits of three-dimensional visualisation of the teeth under investigation and surrounding structures. Its use, however, should be considered on a case-by-case basis, taking into consideration the benefits and increased dose of radiation in line with published guidelines.

This research developed an innovative Mask-based Swin Transformer network (MBST) to enhance the quality of 4D cone-beam computed tomography (4D-CBCT) reconstruction. The network is trained on 4D-CBCT reconstructed under limited scanning conditions, enabling its application to a broad range of 4D-CBCT reconstruction scenarios, including those with high scanning speeds.

4D imaging data from 20 patients with thoracic tumors were used to train and evaluate the deep learning model. 15 cases were used for training, and 5 cases were employed for simulation testing. The Feldkamp-Davis-Kress algorithm was employed to simulate 4D-CBCT from downsampled 4D-CT data to mitigate the uncertainties associated with respiratory motion between treatment fractions, and the 4D-CT data served as the ground truth for training. The study reconstructed 4D-CBCT images under 11 different scanning intervals including full angle acquisition at 1°, 2°, 3°, 4°, 5°, 6°, 12°, 18°, 24° intervals, and 1/3 full angles acquisition at 5°, 10° inrevals respectively for capturing 4D-CBCT projections. The test results were quantitatively evaluated using the structural similarity index measure (SSIM), peak signal-to-noise ratio (PSNR), mean error (ME), and mean absolute error (MAE), and image quality was qualitatively assessed. Real clinical patients who were not included in the training were tested to evaluate the network's ability to generalize. Moreover, the proposed method was compared with other deep learning approaches, and statistical analyses were performed.

Simulation data assessment revealed that with small projection acquisition interval, such as the 4°interval, the 4D-CBCT images optimized by MBST showed a considerable improvement over the original 4D-CBCT images in terms of SSIM (42.3% increase) and PSNR (10.8 dB increase), and the ME and MAE values approached 0. The improvements were statistically significant (P < 0.001). Compared with other deep learning methods, MBST demonstrated superior performance with improvements of 1.4% in SSIM and 1.21 dB in PSNR and a reduction of 0.94 in MAE. With large projection intervals, such as the 24°interval, MBST outperformed other deep learning methods. Specifically, its SSIM, PSNR, and MAE increased by 3.8%, 0.81 dB, and 10.34, respectively, compared with those of other deep learning methods, and the improvements were statistically significant (P < 0.01). In addition, MBST could reconstruct bone tissue and optimize the quality of 4D-CBCT images even when the number of projections was small (12°, 18°, 24°intervals). Clinical data evaluation revealed that after optimization by MBST, the SSIM, PSNR, ME, and MAE of 4D-CBCT compared with those of 4D-CT registration improved from the original 22.8%, 15.49 dB, -345.5, and 432.2 to 81.5%, 27.93 dB, -53.79, and 73.77, respectively. Moreover, MBST exhibited the most pronounced improvement among all the compared methods. MBST could accurately recover high-density structure, lung structures, and tracheal walls.

This study comprehensively demonstrated the ability of MBST to reconstruct 4D-CBCT images under various scanning conditions. When the method was tested on clinical patient datasets, its CT values and image quality achieved satisfactory results. Thus, MBST can serve as a highly generalized reconstruction network for improving the quality of 4D-CBCT images.

Micro-CT enables volumetric analysis of peri-implant tissue, but grey value alterations due to metal artefacts can impair analyses. This study aimed to assess to which extent peri-implant grey values are affected by metal artefacts at increasing distance to the implant, and whether mathematical correction is possible. In nine rats, two Ti6Al4V orthodontic mini-implants (OMIs), 0.8 mm in diameter and 3.0 mm in length, were placed in a single tail vertebra. Micro-CT scans were performed before (T0) and after (T1) careful removal of the OMIs. Consecutive micro-CT scans were registered and differences in local grey values were computed at increasing distance to the implant (10.4 μm to 405.6 μm). Correction coefficient (CC) computation was performed using a smoothing spline fit, with the distance to the implant and the grey value difference as independent and dependent variable, respectively. To validate the effectiveness of the CC, the amount of calcified bone volume per total volume (BV/TV) was assessed within a standardized volume of interest (VOI) reaching up to 1 mm around the OMIs before and after the application of CC, and the T1-T0 differences between corrected and uncorrected scans were compared using the Wilcoxon signed-rank test. The grey value difference between uncorrected T0 and T1 scans was low in proximity to the implant (32.7%±6.11%) and improved at a distance of at least 100 μm (93.4%±4.46%). CC computation revealed a satisfactory fit (R2 = 0.989, RMSE = 0.031) and the difference in grey values was significantly lower after correction (p < 0.001). Most VOIs showed significant improvement, though overcorrection was observed in a few cases. Within the limitations of the study, metal artefacts decreased with increasing distance to the OMIs, and significant improvement was possible using the CC.

Cone-beam computed tomography (CBCT) scans are widely used for real time monitoring and patient positioning corrections in image-guided radiation therapy (IGRT), enhancing the precision of radiation treatment. However, compared to high-quality computed tomography (CT) images, CBCT images suffer from severe artifacts and noise, which significantly hinder their application in IGRT. Therefore, synthesizing CBCT images into CT-like quality has become a critical necessity. In this study, we propose a hybrid U-Net diffusion model (HUDiff) based on Vision Transformer (ViT) and the information bottleneck theory to improve CBCT image quality. First, to address the limitations of the original U-Net in diffusion models, which primarily retain and transfer only local feature information, we introduce a ViT-based U-Net framework. By leveraging the self-attention mechanism, our model automatically focuses on different regions of the image during generation, aiming to better capture global features. Second, we incorporate a variational information bottleneck module at the base of the U-Net. This module filters out redundant and irrelevant information while compressing essential input data, thereby enabling more efficient summarization and better feature extraction. Finally, a dynamic modulation factor is introduced to balance the contributions of the main network and skip connections, optimizing the reverse denoising process in the diffusion model. We conducted extensive experiments on private Brain and Head & Neck datasets. The results, evaluated from multiple perspectives, demonstrate that our model outperforms state-of-the-art methods, validating its clinical applicability and robustness. In future clinical practice, our model has the potential to assist clinicians in formulating more precise radiation therapy plans.

There is difficulty in identifying the mesiobuccal canal in clinical routine. The use of cone-beam computed tomography (CBCT) helps overcome this difficulty by providing volumetric details of the teeth and surroundings. Thus, the objective of this study was to determine the effectiveness of different CBCT protocols, with different image resolutions, in visualizing the second mesiobuccal canal in maxillary molars in the presence of artifacts.

To perform the study, the visualization of the second mesiobuccal canal of 28 maxillary molars with root canal preparation and obturation was used, with the exception of the second mesiobuccal canal. The teeth were placed in a dry maxilla and then scanned with the OP300 MAXIO CBCT unit (4 protocols) and 3D Veraview X800 F150P (3 protocols). Five experienced and blinded evaluators analyzed the images to assess accuracy, sensitivity, and specificity. The presence of the second mesiobuccal canal was confirmed by light microscopy (×50 magnification) of cross-sections of the roots.

Our data showed that the Veraview X800 CT scanner provided better results for accuracy (96%), sensitivity (100%), and specificity (86%). The 50 × 50/0.085 protocol showed the highest sensitivity (78%), specificity (100%), and accuracy (82%). It was possible to visualize the second mesiovestibular canals in both CT scanners tested; however, the 3D Veraview X800 F150P offered better results for the evaluated patterns.

The best protocol in the presence of artifacts was 80 × 40 FOV and 0.125 voxel size of 3D Veraview X800 F150P.

Background: One of the parameters of maximum interest regarding the quality of the intraoral hard tissues is represented by the bone density, with direct clinical implications. The evaluation of this extremely important clinical parameter can be achieved by several imaging methods, of which the most known in dentistry is represented by the cone beam computed tomography (CBCT). Objectives: The purpose of the study is to obtain a quantitative analysis of bone mineral density changes in patients who underwent treatments of photobiomodulation (PBM), as complementary to a surgical approach in oral surgery and implantology. Methods: The study included the retrospective analysis of maxillary cone beam computed tomography of 28 patients without pathology or medication known to affect bone metabolism or its qualitative and quantitative properties. All patients from the study group followed the same laser PBM treatment protocol after placing dental implants; the PBM protocol implied the intraoral use of a gallium aluminum arsenide laser (GaAlAs) of 808 nm, 450 mW, in pulsed mode, administering an energy of 6 J in 3 points corresponding to each inserted dental implant-mesial, distal, and apical-totaling 18 J/implant. Treatment sessions were performed immediately postoperatively and at a subsequent distance of 48 h for 2 weeks (a total of eight sessions). For every patient, bone density was analyzed before and after PBM treatment, in the same areas of interest, within the same anatomical landmarks. A comparison was also made between the results obtained for the anterior maxilla and the posterior maxilla. All the measurements made were analyzed statistically, the results being presented in the dedicated section. Results: Based on the data analysis, the comparison between the lasered and non-lasered groups reveals that patients who underwent PBM showed a statistically significant improvement in bone mineral density, with the mean increasing from 530.91 HU before treatment to 842.55 HU after treatment (t-test: p < 0.001). In contrast, the non-lasered group showed no significant improvement, with a slight decrease in bone mineral density, as the mean dropped from 495.19 HU before treatment to 462.16 HU after treatment (t-test: p = 0.47). Conclusions: The study demonstrated results with statistical significance regarding the mineral bone density improvement of patients who underwent laser PBM treatment. This positive effect of laser therapy has been shown, both at the level of the vestibular cortical bone and at level of the trabecular bone, independent of the patient's sex, for the anterior maxilla and at the lateral areas also.

The aim of this study was to clinically validate an artificial intelligence (AI)-based tool for automatic segmentation of the mandibular incisive canal (MIC) on cone beam computed tomography (CBCT), enabling prevention and detection of iatrogenic implant-related nerve injuries. Patient records from University Hospitals Leuven were screened for CBCT related to implant surgery cases with nerve injuries. CBCT scans were imported into Virtual Patient Creator for canal segmentation and 3D model generation. Two oral radiologists compared the AI-segmented canals with respective CBCT images. Five observers then performed canal identification and injury detection (present/absent) and reported their confidence level on a five-point Likert scale. Ten patient cases were assessed (eight female, two male; age 49-81 years). The AI-based tool enabled clear visualization of bilateral MIC in both pre- and postoperative images, revealing implant-canal relationships consistent with recorded post-implant pain or neural disturbance. For preoperative assessment, the AI-based tool significantly improved incisive canal detection (by 25%; P = 0.025) and observer confidence (by 8%; P = 0.038). The AI-based tool proved to be clinically useful to enable bilateral MIC visualization on CBCT images. Through canal segmentation with integrated 3D modelling, preoperative canal detection and the experts' confidence level were significantly improved.

The present study uses deformable image registration to produce synthetic CT (sCT) images and investigate their use in treatment planning and improving clinical judgment in assessing the need for adaptive radiotherapy (ART).

A total of 30 patients with squamous cell carcinoma of the head and neck (HNSCC) who underwent ART were included in this study. The patients considered for adaptive planning, were re-simulated within 1-2 days. Both the Day 1 planning CT (pCT) and acquired CBCT were imported in Velocity® and a new sCT was created. The new treatment plan on re-simulation CT (rCT) which was planned for treatment delivery was recalculated on sCT. The geometric differences (Volume, Dice Similarity coefficient (DSC), mean distance to agreement (MDA)) in structures and dosimetric differences (Gamma analysis, mean doses and other DVH parameters) in treatment plans between the two images (sCT and rCT) were compared.

The evaluation between sCT and rCT revealed that the average DSC and MDA for all the structures obtained was 0.86(0.05) and 1.15(0.20) respectively. Global gamma passing rate for 3 %, 3 mm was 96.85 ± 2.10 %. Mean dose for OARs and PTVs were found to be similar (difference within 3 %) in the two images.

sCT can be used to predict the per fraction dose delivered to the patient and could be a better alternative than only relying on clinical judgments, to take the patient for ART. Further work needs to be done on the use of sCT images to replace rCT images for ART.

The objective of this study is to investigate the influence of metal artifact reduction (MAR) on two cone beam computed tomography (CBCT) units in the evaluation of bone graft loss adjacent to titanium (Ti) and zirconium (Zr) implants.

Twelve Ti and twelve Zr implants were placed in the posterior region of dry human mandibles. Bone graft was applied to the level of the cover screw. Bone graft loss was simulated in half of the sample (6 Ti and 6 Zr) by removing the graft material up to the third implant thread on the buccal surface. CBCT images were acquired on two units, varying the application of MAR (OP300-off and on; Eagle 3D-standard, intermediate, and extreme). The images were assessed by five evaluators that scored the presence of graft loss according to a 5-point scale. The diagnostic values were calculated and compared by non-parametric tests with a significance level of 5%.

Higher diagnostic values were achieved with MAR activated in the OP300 unit, for Ti and Zr (p < 0.05). On the Eagle 3D unit, MAR in extreme mode resulted in lower diagnostic values for both types of implants (p < 0.05). The diagnostic values of Ti implants were higher than Zr implants (p < 0.05).

The application of MAR influences the diagnosis of bone graft loss adjacent to Ti and Zr dental implants. However, the extreme mode of MAR in the Eagle 3D unit can impair the diagnostic task in both types of implants and should be avoided.

Radiation therapy (RT) is a highly digitized field relying heavily on computational methods and, as such, has a high affinity for the automation potential afforded by modern artificial intelligence (AI). This is particularly relevant where imaging is concerned and is especially so during image-guided RT (IGRT). With the advent of online adaptive RT (ART) workflows at magnetic resonance (MR) linear accelerators (linacs) and at cone-beam computed tomography (CBCT) linacs, the need for automation is further increased. AI as applied to modern IGRT is thus one area of RT where we can expect important developments in the near future. In this review article, after outlining modern IGRT and online ART workflows, we cover the role of AI in CBCT and MRI correction for dose calculation, auto-segmentation on IGRT imaging, motion management, and response assessment based on in-room imaging.

Synthetic CT (sCT) generated from CBCT has proven effective in artifact reduction and CT number correction, facilitating precise radiation dose calculation. However, the quality of different regions in sCT images is severely imbalanced, with soft tissue region exhibiting notably inferior quality compared to others. To address this imbalance, we proposed a Multi-Task Attention Network (MuTA-Net) based on VGG-16, specifically focusing the enhancement of image quality in soft tissue region of sCT. First, we introduced a multi-task learning strategy that divides the sCT generation task into three sub-tasks: global image generation, soft tissue region generation and bone region segmentation. This approach ensured the quality of overall sCT image while enhancing the network's focus on feature extraction and generation for soft tissues region. The result of bone region segmentation task guided the fusion of sub-tasks results. Then, we designed an attention module to further optimize feature extraction capabilities of the network. Finally, by employing a results fusion module, the results of three sub-tasks were integrated, generating a high-quality sCT image. Experimental results on head and neck CBCT demonstrated that the sCT images generated by the proposed MuTA-Net exhibited a 12.52% reduction in mean absolute error in soft tissue region, compared to the best performance among the three comparative methods, including ResNet, U-Net, and U-Net++. It can be seen that MuTA-Net is suitable for high-quality sCT image generation and has potential application value in the field of CBCT guided adaptive radiation therapy.

To compare the intrafraction prostate motion monitoring capabilities between intrafraction Cone Beam Computed Tomography (IF-CBCT) and SeedTracker-based real-time monitoring, and to optimize imaging doses in real-time monitoring using the IF-CBCT image acquisition method. Simulations of static and dynamic intrafraction prostate motions were conducted on a phantom using a robotic arm. The study utilized the XVI imaging system of the Elekta linear accelerator for IF-CBCT and SeedTracker-based monitoring during hypofractionation and Stereotactic Body Radiation Therapy (SBRT). The optimal imaging frequency for real-time monitoring was determined by calculating VMAT gantry traverse times. The effective dose resulting from IF-CBCT and SeedTracker-based monitoring approaches were compared. IF-CBCT showed static offsets as seed duplications and the offsets calculated using 'Seed' automatic image registration available XVI system depend on the initial position of the seeds in verification and localisation image sets. This dependency resulted in large differences (up to 4.9 mm) between actual and calculated position offsets. Dynamic offsets resulted in blurring or duplication of seeds in IF-CBCT images depending on the type of the dynamic motion. SeedTracker-based real-time monitoring successfully identified position deviation events as they occurred during treatment. For hypofractionation and SBRT treatments, IF-CBCT imaging resulted in an effective dose of 54.3 mSv and 13.6 mSv, respectively. Optimized imaging frequency for real-time monitoring led to a dose reduction of up to 86.2% and 97.2% for hypofractionation and SBRT regimens, respectively, compared to the IF-CBCT approach. SeedTracker real-time monitoring effectively identified target position deviations in real-time, surpassing the capabilities of the IF-CBCT approach. Moreover, the SeedTracker imaging approach significantly reduced imaging doses compared to IF-CBCT.

The present study aimed to compare the performance of a 3D-endodontic guide (EG) and a conventional technique on the access of root canals containing fiberglass posts. Thirty single-canal lower human premolars were endodontically treated, filled using the single-cone technique, and prepared for fiberglass post luting. The teeth were positioned in the alveoli of human mandibles and cone beam computed tomography (CBCT) examination was performed. The specimens were randomly distributed (n = 10) according to the root canal access technique: control group (GC)-no access; conventional access group (GCA)-root canal accessed with spherical diamond burs and ultrasonic inserts; and EG group (GEG)-root canal accessed with bone graft/anchorage drills and EG. At the end of the root canal access, new CBCT examination was performed to assess the root canal walls' thickness and the volume of dental tissue removed during the fiberglass post removal. The time required for the access was also recorded. The data were submitted to statistical analysis (Kruskal-Wallis and Mann-Whitney tests, α = 0.05). GCA promoted greater deviation than the GEG (p < 0.05) and resulted in greater removal of the root canal walls. The volume of dental tissue/fiberglass post removed, deviations promoted, and the time spent were significantly lower (p < 0.05 and p < 0.001, respectively) in GEG than in GCA. The use of the EG provided a lower volume of dental tissue removed, less deviation from the original root canal path, and less time for endodontic access when compared to conventional access technique.

Vertical root fractures (VRF) are challenging to detect, especially in endodontically treated teeth. Cone-Beam Computed Tomography (CBCT) has improved VRF detection over periapical radiography but is limited by metal artifacts. Iterative Reconstruction (IR) algorithms are an alternative to the traditional Filtered-Back Projection (FBP) and has been shown to reduce image noise due to metal artifacts. This study aimed to evaluate the impact of IR on VRF detection in the presence of metal artifacts from intracanal materials and/or adjacent implants.

This ex-vivo study included 22 single-rooted teeth (10 fractured, 12 non-fractured) placed in a human mandible phantom. CBCT scans were performed using Midmark EIOS CBCT with both reconstruction methods (FBP and IR), with and without metal artifact reduction (MAR) tool activation. Clinical conditions included the presence or absence of gutta-percha and adjacent titanium dental implants. Five oral radiologists evaluated the anonymized images for VRF presence using a 5-point scale. Diagnostic accuracy, sensitivity, specificity, and intra- and interobserver agreement were assessed using receiver operating characteristic curves and multi-way ANOVA.

The area under the curve (AUC) values ranged from 0.60 to 0.85, with no significant differences between reconstruction methods (p>0.05). Sensitivity and specificity were generally unaffected by reconstruction method or MAR activation (p>0.05), except when MAR reduced sensitivity in FBP with gutta-percha (p<0.05). Metal artifacts from gutta-percha and implants negatively impacted VRF detection.

The reconstruction method did not significantly influence VRF detection, suggesting that either method can be used in clinical practice without compromising diagnostic accuracy, even in the presence of metal artifacts.

Separated endodontics instruments and high-density obturating materials produce metal artifacts on cone-beam computed tomography (CBCT) scans. This study evaluated a novel methodology to detect separated instruments using artifact suppression and color map algorithms with CBCT post-processing software and compared with periapical radiographs (PRs). Endodontic instruments were incorporated into 168 root canals filled with four sealers. Additionally, 40 root canals were only filled, serving as control. CBCT scans were acquired in PreXion-3D-Elite, and digital PRs were taken in distoradial, mesioradial, orthoradial, and proximal directions. The treated teeth were analyzed using an artifact suppression algorithm combined with a color map algorithm. The separated instruments appear in the color map with larger expansion in red to allow identification. This map provides valuable information by showing dynamic visualization toward the point of expansion of the high-density object, hence suggesting a separated instrument. The chi-square test was used to compare the separated instruments among the imaging methods. Bonferroni correction was used for multiple comparisons. Statistical significance was considered P < 0.05. Overall, CBCT performed significantly better than PRs (P < 0.001) in detecting separated instruments. PR was influenced by all the variables studied (P < 0.05). The artifact suppression and color map algorithms, combined with dynamic navigation, effectively identified separated instrument fragments in all the root canal fillings, regardless of filling material, image view, or root canal. Only 32.3% of the root canal fillings viewed by PR detected separated instrument fragments. This method seems to be useful in the resolution of the problem of viewing separated instruments with CBCT post-processing software.

The aim of this study was to evaluate the efficacy of detecting dental caries under fixed dental prostheses (FDPs) through the analysis of panoramic radiographs utilizing convolutional neural network (CNN) based You Only Look Once (YOLO) models. Deep learning algorithms can analyze datasets of dental images, such as panoramic radiographs to accurately identify and classify carious lesions. Using artificial intelligence, specifically deep learning methods, may help practitioners to detect and diagnose caries using radiograph images.

The panoramic radiographs of 1004 patients, who had FDPs on their teeth and met the inclusion criteria, were divided into 904 (90%) images as training dataset and 100 (10%) images as the test dataset. Following the attainment of elevated detection scores with YOLOv7, regions of interest (ROIs) containing FDPs were automatically detected and cropped by the YOLOv7 model. In the second stage, 2467 cropped images were divided into 2248 (91%) images as the training dataset and 219 (9%) images as the test dataset. Caries under the FDPs were detected using both the YOLOv7 and the improved YOLOv7 (YOLOv7 + CBAM) models. The performance of the deep learning models used in the study was evaluated using recall, precision, F1, and mean average precision (mAP) scores.

In the first stage, the YOLOv7 model achieved 0.947 recall, 0.966 precision, 0.968 mAP and 0.956 F1 scores in detecting the FDPs. In the second stage the YOLOv7 model achieved 0.791 recall, 0.837 precision, 0.800 mAP and 0.813 F1 scores in detecting the caries under the FDPs, while the YOLOv7 + CBAM model achieved 0.827 recall, 0.834 precision, 0.846 mAP, and 0.830 F1 scores.

The use of deep learning models to detect dental caries under FDPs by analyzing panoramic radiographs has shown promising results. The study highlights that panoramic radiographs with appropriate image features can be used in combination with a detection system supported by deep learning methods. In the long term, our study may allow for accurate and rapid diagnoses that significantly improve the preservation of teeth under FDPs.

The aim of this study was to investigate the influence of bone microstructure on the accuracy of robot-assisted dental implant surgery.

This retrospective study analyzed 52 patients who received robot-assisted implant surgery between January 2023 and October 2023. Cone beam computed tomography (CBCT) scans were used to evaluate bone microstructural parameters, including the bone volume (BV), tissue volume (TV), bone volume fraction (BV/TV), bone surface (BS), bone surface fraction (BS/BV), trabecular thickness (Tb.Th), and trabecular separation (Tb.Sp). Preoperative and postoperative CBCT data were used to evaluate implant accuracy, and the relationship between bone microstructure parameters and implant deviation including platform deviation, apex deviation, and angular deviation was statistically analyzed.

In robot-assisted implant surgery, BS/BV was a potential facilitator of several implant deviations, while BV/TV and Tb.Th were potential inhibitors of apex global deviation and angular deviation, respectively. Implant deviations were divided into two groups of large and small deviations by median, and the receiver operating characteristic (ROC) curve analysis showed that Tb.Th had the largest area under the ROC for predicting large apex global deviation, 0.711 (p < 0.001), with an optimal cutoff value > 0.179, a sensitivity and specificity of 70.37% and 76.92%.

The study concluded that bone microstructure might affect the accuracy of dental implant placement in robotic surgeries. Incorporating bone quality assessments into preoperative planning may enhance the precision and outcomes of implant procedures, highlighting the potential for further refinement in robotic-assisted dental surgery techniques.

ClinicalTrials.gov identifier: ChiCTR2400085813.

To evaluate the bone profile around dental implants placed in the esthetic zone through periodontal assessment and radiographic analysis using cone-beam computed tomography (CBCT).

We conducted a clinical observational study of 35 subjects who received dental implants placed in the esthetic zone to replace lost anterior teeth. Clinical evaluation included a comprehensive periodontal examination. The esthetic outcomes of the soft tissue around the implants were assessed using the pink esthetic score (PES). Patient satisfaction was assessed by using a specially designed questionnaire. The Oral Health Impact Profile (OHIP)-14 was used to assess the quality of life. The bone profile around the implant was assessed using CBCT. All the values were compared and statistically analyzed.

A soft tissue graft (STG) was associated with the presence of > 2 mm of bone thickness 1 mm from the implant shoulder (p < 0.01). The STG was also significantly associated with bone thickness at 3 and 5 mm (p = 0.04). PES was not significantly associated with the bone thickness, OHIP score, or satisfaction score. Patients with fenestrations had significantly higher scores for functional limitations and pain than those without fenestrations (p = 0.01 and 0.04 respectively).

The bone profile around the anterior implant is not ideal. Although the buccal bone was thin around the implant placed in the esthetic zone, it did not affect the esthetic outcomes or overall satisfaction of the patient. However, fenestration defects may affect patients' quality of life.

The increasing use of cone beam computed tomography (CBCT) has led to a growing demand for DICOM software that enables the assessment and measurement of craniofacial structures. This study aimed to compare the airway volume and the minimum axial area in patients with cleft lip and palate using five different imaging software programs: Dolphin3D, InVivo Dental, ITK Snap, InVesalius, and NemoFAB. Initially, 100 CBCT scans were selected by an examiner, and their corresponding DICOM files were collected. The oropharyngeal segments were delineated following the manufacturer's guidelines, using two different segmentation techniques: interactive and fixed threshold. The results were analyzed using the Friedman test and Wilcoxon post hoc test, with a 5% significance level for all statistical tests. The findings for both the minimum axial area and total volume revealed that the median values across the software groups were higher than expected, and significant differences were observed when comparing the groups (p < 0.001). All five software programs showed notable differences in their outputs. Specifically, a statistically significant difference in volume was found across all groups, except between InVivo and ITK-Snap. It is recommended that pre- and post-treatment comparisons be performed using the same software for consistency.

Cone beam computed tomography (CBCT) is an imaging exam used increasingly in various fields of dentistry, and a greater number of endodontists are progressively gaining access to this technology. This study focused on applying an artifact suppression algorithm featured in CBCT software, and designed specifically to address artifacts related to root canal filling materials.

The sample consisted of eighty-four mandibular molars, with mesial root canals endodontically treated by using the lateral condensation technique. Four root canal sealers were applied: G1 - Sealapex®, G2 - AH Plus®, G3 - Endofill®, and G4 - Bio-C Sealer. CBCT scans were taken using PreXion 3D Elite®. Initially, the diameter of the root canal filling (in the mesiodistal and buccolingual directions) was measured using a digital micrometer (control). Next, these diameters were reevaluated in the CBCT images using the blooming artifact reduction (BAR) tool of the e-Vol DX software. The Van der Waerden nonparametric analysis of variance was performed, followed by applying the Tukey test to the normalized data. The significance level was set at α = 5%.

There were no statistically significant differences (p>0.05) in the measurement of original root canal filling materials obtained by the micrometer versus the e-Vol DX software in the mesiodistal and buccolingual directions.

The tested software algorithm effectively suppressed artifacts resulting from obturation materials.

To develop and evaluate a deep learning (DL) model to reduce metal artefacts originating from the exomass in cone-beam CT (CBCT) of the jaws.

Five porcine mandibles, each featuring six tubes filled with a radiopaque solution, were scanned using four CBCT units before and after the incremental insertion of up to three titanium, titanium-zirconium, and zirconia dental implants in the exomass of a small field of view. A conditional denoising diffusion probabilistic model, using DL techniques, was employed to correct axial images from exomass-related metal artefacts across the CBCT units and implant scenarios. Three examiners independently scored the image quality of all datasets, including those without an implant (ground truth), with implants in the exomass (original), and DL-generated ones. Quantitative analysis compared contrast-to-noise ratio (CNR) to validate artefact reduction using repeated measures analysis of variance in a factorial design followed by Tukey test (α = .05).

The visualisation of the hard tissues and overall image quality was reduced in the original and increased in the DL-generated images. The score variation observed in the original images was not observed in the DL-generated images, which generally scored higher than the original images. DL-generated images revealed significantly greater CNR than both the ground truth and their corresponding original images, regardless of the material and quantity of dental implants and the CBCT unit (P < .05). Original images revealed significantly lower CNR than the ground truth (P < .05).

The developed DL model using porcine mandibles demonstrated promising performance in correcting exomass-related metal artefacts in CBCT, serving as a proof-of-principle for future applications of this approach.

To systematically evaluate the mean gray values (MGVs) and noise provided by bone and soft tissue equivalent materials and air imaged with varied acquisition parameters in 9 cone-beam computed tomography (CBCT) machines.

The DIN6868-161 phantom, composed of bone and soft tissue equivalent material and air gap, was scanned in 9 CBCT machines. Tube current (mA) and tube voltage (kV), field of view (FOV) size, and rotation angle were varied over the possible range. The effect of the acquisition parameters on the MGV and contrast-to-noise indicator (CNI) was analyzed by Kruskal Wallis and Dunn-Bonferroni tests for each machine independently (α = 0.05).

Tube current did not influence MGV in most machines. Viso G7 and Veraview X800 presented a decrease in the MGV for increasing kV. For ProMax 3D Max and X1, the kV did not affect the MGV. For the majority of machines, MGV decreased with increasing FOV height. In general, the rotation angle did not affect the MGV. In addition, CNI was lower with lower radiation and large FOV and did not change from 80 kV in all machines.

The MGV and noise provided by the tested phantom vary largely among machines. The MGV is mainly influenced by the FOV size, especially for bone equivalent radiodensity. For most machines, when the acquisition parameters affect the MGV, the MGV decrease with the increase in the acquisition parameters.

This experimental phantom study investigates current standard of care protocols in cone beam computed tomography (CBCT), energy-integrating-detector (EID) CT, and photon-counting-detector (PCD) CT regarding their potential in delineation of dental root canals. Artificial accessory canals (diameters: 1000, 600, 400, 300 and 200 μm) were drilled into three bovine teeth mounted on a bovine rib as a jaw substitute. The phantom was scanned in two dental CBCTs, two EID-CTs and a PCD-CT using standard clinical protocols. Scans from a micro-CT served as reference standard. Spatial resolution was evaluated via line profiles through the canals, whereby visibility compared to surrounding noise and compared to the ground truth were assessed. PCD-CT was able to delineate all artificial canals down to 200 μm diameter. In CBCT and EID-CT canals could only be reliably detected down to 300 μm. Also, PCD-CT showed a considerably smaller width-divergence from the ground trough with 4.4% at 1000 μm and 35.1% at 300 μm compared to CBCT (13.5 and 72.9%) and EID-CT (10.1 and 115.7%). PCD-CT provided superior resolution, accurate size measurement, and enhanced detection of small dental root canals, thereby offering improvements in diagnostic capabilities compared to CBCT and EID-CT systems.

This study assesses radiation doses in cone beam computed tomography (CBCT) procedures in Sri Lanka, with the goal of establishing initial diagnostic reference levels (DRLs). Data from 1162 retrospective scans across four institutions were analyzed, and the medians of the pooled dose distribution for seven clinical indication categories were presented as the DRL values. The proposed DRLs based on clinical indications are 1013 mGy·cm2 for pathological conditions including cysts, tumors, and lesions, 1307 mGy·cm2 for implant planning, 1266 mGy·cm2 for presurgery assessment, and 1585 mGy·cm2 for evaluation of sinus and nasal pathology, temporomandibular disorder, and facial trauma. Considerable variability in doses across facilities was observed, driven by differences in equipment and imaging practices. Therefore, this study recommends adopting suggested DRL values as benchmarks, standardizing protocols to reduce dose variability, and implementing a national framework for regular updates of DRL values.

A novel classification system, termed the Sivan classification, was developed to enhance the diagnosis of jaw lesions by utilizing visual volumetric analysis of three-dimensional Cone Beam Computed Tomography (CBCT) images. This classification groups lesions into ten categories, primarily divided into hypovolumetric, hypervolumetric, and normovolumetric groups. To validate this system, 10 raters-comprising 5 general dentists and 5 oral radiology specialists-assessed the CBCT images and diagnosed the lesions using the Sivan classification. Eight raters repeated the process after one month to assess consistency. The overall agreement between raters, quantified using kappa statistics, was 0.82, indicating excellent consistency. Hypervolumetric and normovolumetric lesions demonstrated the highest agreement (kappa 0.84 and 0.82, respectively), while hypovolumetric lesions showed substantial agreement (kappa 0.77). Pairwise interrater agreement ranged from 76 to 93%, with kappa values between 0.75 and 0.87. Intrarater reliability was equally strong, with kappa values between 0.79 and 0.89.These results suggest that the Sivan classification provides a robust and reliable framework for diagnosing jaw lesions using CBCT volumetric analysis, surpassing traditional diagnostic methods in accuracy and consistency.

Stereotactic body radiotherapy has been established as a viable treatment option for inoperable early-stage non-small cell lung cancer or secondary lesions mainly in oligoprogressive/oligometastatic scenarios. Treating lesions in the so-called "no flight zone" has always been challenging and conflicting data never cleared how to safely treat these lesions. This is truer considering ultra-central lesions, i.e., directly abutting or whose PTV is overlapping critical mediastinal organs. While historical retrospective data are abundant but mostly heterogenous in terms of the definition of ultra-central lesions, dosing regimens and outcomes, prospective data remain scarce, even though recently published studies have given new encouraging results for such delicate treatment scenarios. For this reason, we aimed to review and summarize current knowledge on stereotactic radiation treatment for ultra-central thoracic lesions, highlighting the most recent advances and the messages that can be taken from them. Lastly, we propose a workflow of the necessary steps to identify and treat such patients, therefore helping in elucidating the advantages and caveats of such treatment options.

Radiotherapy commonly utilizes cone beam computed tomography (CBCT) for patient positioning and treatment monitoring. CBCT is deemed to be secure for patients, making it suitable for the delivery of fractional doses. However, limitations such as a narrow field of view, beam hardening, scattered radiation artifacts, and variability in pixel intensity hinder the direct use of raw CBCT for dose recalculation during treatment. To address this issue, reliable correction techniques are necessary to remove artifacts and remap pixel intensity into Hounsfield Units (HU) values. This study proposes a deep-learning framework for calibrating CBCT images acquired with narrow field of view (FOV) systems and demonstrates its potential use in proton treatment planning updates. Cycle-consistent generative adversarial networks (cGAN) processes raw CBCT to reduce scatter and remap HU. Monte Carlo simulation is used to generate CBCT scans, enabling the possibility to focus solely on the algorithm's ability to reduce artifacts and cupping effects without considering intra-patient longitudinal variability and producing a fair comparison between planning CT (pCT) and calibrated CBCT dosimetry. To showcase the viability of the approach using real-world data, experiments were also conducted using real CBCT. Tests were performed on a publicly available dataset of 40 patients who received ablative radiation therapy for pancreatic cancer. The simulated CBCT calibration led to a difference in proton dosimetry of less than 2%, compared to the planning CT. The potential toxicity effect on the organs at risk decreased from about 50% (uncalibrated) up the 2% (calibrated). The gamma pass rate at 3%/2 mm produced an improvement of about 37% in replicating the prescribed dose before and after calibration (53.78% vs 90.26%). Real data also confirmed this with slightly inferior performances for the same criteria (65.36% vs 87.20%). These results may confirm that generative artificial intelligence brings the use of narrow FOV CBCT scans incrementally closer to clinical translation in proton therapy planning updates.

To assess the effect of a blooming artifact reduction (BAR) filter on cone beam computed tomography (CBCT) images in the dimensional analysis of dental implants.

Six types of implants (n = 5 for each type) composed of titanium (3 types), titanium-zirconia alloy, zirconium oxide, and titanium-aluminum-vanadium alloy, and made with 2 manufacturing processes (milled and printed) were individually installed in a bovine rib block according to the manufacturer's protocol. CBCT images were acquired with i-CAT and Carestream scanners, randomized, and analyzed without and with the e-Vol DX BAR filter (60 images for each scanner). Implant length, diameter, and thread-to-thread distance were measured by two radiologists, with a stereomicroscopic image of each implant as the reference standard for calculation of distortion in measurements. Repeated measures ANOVA with Bonferroni corrections and intraclass correlation coefficients (ICC) were applied (α = 0.05).

The BAR filter significantly reduced distortion in various parameters for specific implants, aligning closely with stereomicroscopic measurements. Titanium and printed implants showed reduced dimensional distortion regardless of BAR filter use. Carestream measurements presented smaller dimensional differences than i-CAT for most implants and parameters, especially without BAR (P < .05). Interexaminer reliability was good to excellent, with ICC ranging from 0.80 to 0.95.

The BAR filter can enhance implant dimensional analysis, although variations based on implant material and manufacturing process were observed.

Image-guided treatment adaptation is a game changer in oncological particle therapy (PT), especially for younger patients. The purpose of this study is to present a cycle generative adversarial network (CycleGAN)-based method for synthetic computed tomography (sCT) generation from cone beam CT (CBCT) towards adaptive PT (APT) of paediatric patients. Firstly, 44 CBCTs of 15 young pelvic patients were pre-processed to reduce ring artefacts and rigidly registered on same-day CT scans (i.e., verification CT scans, vCT scans) and then inputted to the CycleGAN network (employing either Res-Net and U-Net generators) to synthesise sCT. In particular, 36 and 8 volumes were used for training and testing, respectively. Image quality was evaluated qualitatively and quantitatively using the structural similarity index metric (SSIM) and the peak signal-to-noise ratio (PSNR) between registered CBCT (rCBCT) and vCT and between sCT and vCT to evaluate the improvements brought by CycleGAN. Despite limitations due to the sub-optimal input image quality and the small field of view (FOV), the quality of sCT was found to be overall satisfactory from a quantitative and qualitative perspective. Our findings indicate that CycleGAN is promising to produce sCT scans with acceptable CT-like image texture in paediatric settings, even when CBCT with narrow fields of view (FOV) are employed.