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.
Cone-Beam Computed Tomography/methods* ; Humans ; Image Processing, Computer-Assisted/methods* ; Artifacts ; Algorithms ; Bone and Bones/diagnostic imaging* ; Neural Networks, Computer

This paper aims to propose a noninvasive radiotherapy patient positioning system based on structured light surface imaging, and evaluate its clinical feasibility. First, structured light sensors were used to obtain the panoramic point clouds during radiotherapy positioning in real time. The fusion of different point clouds and coordinate transformation were realized based on optical calibration and pose estimation, and the body surface was segmented referring to the preset region of interest (ROI). Then, the global-local registration of cross-source point cloud was achieved based on algorithms such as random sample consensus (RANSAC) and iterative closest point (ICP), to calculate 6 degrees of freedom (DoF) positioning deviation and provide guidance for the correction of couch shifts. The evaluation of the system was carried out based on a rigid adult phantom and volunteers' body, which included positioning error, correlation analysis, and receiver operating characteristic (ROC) analysis. Using Cone Beam CT (CBCT) as the gold standard, the maximum translation and rotation errors of this system were (1.5 ± 0.9) mm along Vrt direction (chest) and (0.7 ± 0.3) ° along Pitch direction (head and neck). The Pearson correlation coefficient between results of system outputs and CBCT verification distributed in an interval of [0.80, 0.84]. Results of ROC analysis showed that the translational and rotational AUC values were 0.82 and 0.85, respectively. In the 4D freedom accuracy test on the human body of volunteers, the maximum translation and rotation errors were (2.6 ± 1.1) mm (Vrt direction, chest and abdomen) and (0.8 ± 0.4)° (Rtn direction, chest and abdomen) respectively. In summary, the positioning system based on structured light body surface imaging proposed in this article can ensure positioning accuracy without surface markers and additional doses, and is feasible for clinical application.
Humans ; Patient Positioning/methods* ; Phantoms, Imaging ; Cone-Beam Computed Tomography ; Algorithms ; Radiotherapy, Image-Guided/methods* ; Radiotherapy Planning, Computer-Assisted/methods*

Cone-beam computed tomography (CBCT) is widely used in dentistry, surgery, radiotherapy and other medical fields. However, repeated CBCT scans expose patients to additional radiation doses, increasing the risk of secondary malignant tumors. Low-dose CBCT image reconstruction technology, which employs advanced algorithms to reduce radiation dose while enhancing image quality, has emerged as a focal point of recent research. This review systematically examined deep learning-based methods for low-dose CBCT reconstruction. It compared different network architectures in terms of noise reduction, artifact removal, detail preservation, and computational efficiency, covering three approaches: image-domain, projection-domain, and dual-domain techniques. The review also explored how emerging technologies like multimodal fusion and self-supervised learning could enhance these methods. By summarizing the strengths and weaknesses of current approaches, this work provides insights to optimize low-dose CBCT algorithms and support their clinical adoption.
Cone-Beam Computed Tomography/methods* ; Deep Learning ; Humans ; Algorithms ; Image Processing, Computer-Assisted/methods* ; Radiation Dosage ; Artifacts

This study aims to develop a fully automated method for tooth segmentation and root canal measurement based on cone beam computed tomography (CBCT) images, providing objective, efficient, and accurate measurement results to guide and assist clinicians in root canal diagnosis grading, instrument selection, and preoperative planning. The method utilized Attention U-Net to recognize tooth descriptors, cropped regions of interest (ROIs) based on the center of mass of these descriptors, and applied an integrated deep learning method for segmentation. The segmentation results were mapped back to the original coordinates and position-corrected, followed by automatic measurement and visualization of root canal lengths and angles. The results indicated that the Dice coefficient for segmentation was 96.42%, the Jaccard coefficient was 93.11%, the Hausdorff Distance was 2.07 mm, and the average surface distance was 0.23 mm, all of which surpassed existing methods. The relative error of the root canal working length measurement was 3.15% (< 5%), the curvature angle error was 2.85 °, and the correct classification rate of the treatment difficulty coefficient was 90.48%. The proposed methods all achieved favorable results, which can provide an important reference for clinical application.
Cone-Beam Computed Tomography/methods* ; Deep Learning ; Humans ; Dental Pulp Cavity/diagnostic imaging* ; Image Processing, Computer-Assisted/methods*

OBJECTIVE: To compare the registration accuracy of cone beam computed tomography (CBCT) images while registering to virtual craniodentofacial patients based on soft tissue and the dentition registration method. METHODS: Virtual dentofacial patients out of 13 selected participants who needed CBCT scanning were established by impression with a registered-block impression (RBI) based on digital dental images, three-dimensional (3D) facial images and maxillofacial CBCT images. CBCT images were processed in the Mimics software program, establishing the craniofacial virtual patients based on CBCT images (CCTs). Registration between virtual patients from RBI and CCT, using the soft tissue in lower half face (STE) and dentition (DTN) as the reference area, respectively, forming two kinds of virtual craniofacial patients based on digital dental images, 3D facial images and skeletal images of CBCT (hiding the soft tissue and dental casts from CBCT). Three-dimensional deviation analysis was performed in the upper half face and lower half face of facial images from CBCT between two kinds of virtual craniodentofacial patients and compared with 3D facial images from RBI and recorded as root mean square error (RMSE). Paired-t test was used to compare the deviations of RMSEs between the upper and lower half of the face and the upper half of the face of facial images from CCT, respectively, between the two kinds of virtual craniodentofacial patients based on STE and DTN methods. RESULTS: Paired-t tests showed that there was no statistically significant difference between the upper and lower half faces of facial images from CCT between STE and DTN (P>0.05), but the deviation of RMSEs of the upper half face of facial images from CCT in STE was smaller than those in DTN [(1.696±0.420) mm vs. (1.752±0.424) mm, P < 0.01]. CONCLUSION The registration accuracy of CBCT registered in virtual craniodentofacial patients using soft tissue as the reference area was higher.
Humans ; Cone-Beam Computed Tomography/methods* ; Imaging, Three-Dimensional/methods* ; Male ; Face/anatomy & histology* ; Female ; Adult ; Image Processing, Computer-Assisted/methods* ; Young Adult ; User-Computer Interface

OBJECTIVE: To evaluate the filling quality of single cone obturation in root canal model with irregular structure (Hus&Kim Ⅴ, Yin Ⅱ-type isthmus) which established by 3D printing technology using slices and radiographic methods, in order to provide reference for clinical practice. METHODS: (1) Extracted fresh premolars with Hus&Kim Ⅴ and Yin-type Ⅱ isthmus were collected and scanned by cone-beam computed tomography (CBCT), then standard root canal models were designed and printed. Rhodamine B staining and bias fitting were used to verify the availability of the models. (2) 30 root canal models were randomly divided into 3 groups according to different filling methods (n=10). CONTROL GROUP: vertical compaction obturation; Experimental group 1: single cone obturation with 0.06-taper cone (30#); Experimental group 2: single cone obturation with 0.04-taper cone (35#), GuttaFlow 2 as canal sealers. Slices were taken at 2, 4, 6, and 8 mm from the root apex in the direction perpendicular to the long axis of the root and observed under a stereomicroscope to calculate the percentage of filling area (PAV), percentage of gutta-percha-filled area (PGFA), percentage of sealer filled area (PSFA). (3) On the basis of the above results, two groups (n=4) were selected to further analyze the filling quality by micro-computed tomography (Micro-CT), the filling volume of main root canal and the isthmus were obtained, and the percentage of filling volume (PFV) was calculated. Two-way ANOVA was used to evaluate the differences between the groups, and Tukey' s multiple comparison was used to compare the data between the groups and within the groups. RESULTS: (1) Rhodamine B staining solution could overflow the apical foramen, and the main root canal system and the isthmus area were stained, showed no remnants of support material. The 3D standard deviation of the printed model data was 0.03 mm, and the average fitting distance was 0.02 mm. (2) The PFA of the two experimental groups were both significantly lower than that of the control group (F=45.04, P < 0.01). There was no statistical difference of the PFA at apical 2 and 4 mm between the two experimental groups (P>0.01), but at the middle and coronal portions of the root canal (6, 8 mm), the PFA of the experimental group 1 was higher than that of the experimental group 2 (P < 0.01). PFA in the apical 2, 4 mm of the two experimental groups were both lower than that in the middle and coronal portions 6, 8 mm of the canal (P < 0.01). There was no difference in the PGFA and PSFA between the two experimental groups at the apical 2, 4 mm (F=2.383, P>0.01). (3) The results of Micro-CT showed that the PFV of the experimental group 1 was statistically different with the control group (F=47.33, P < 0.01). The PFV of the experimental group 1 was 54.33%±4.35% in the isthmus and 78.31%±4.21% in the main root canal, which were both lower than the PFV of the control group of 76.48%±4.89% (isthmus) and 86.90%±3.29% (main root canal, P < 0.01). The PFV of the main root canal in the experimental group 1 was higher than that in the isthmus (P < 0.01), while there was no difference between the isthmus and the main root canal in the control group (P>0.01). CONCLUSION In the irregular root canal structure with isthmus, using large-taper gutta-percha can improve the filling quality of the middle and upper part of the canal, but the percentage of filling volume in the isthmus is lower than that of the main canal, and more technical improvements are needed.
Humans ; Root Canal Obturation/methods* ; Cone-Beam Computed Tomography ; Root Canal Filling Materials ; Dental Pulp Cavity/diagnostic imaging* ; Printing, Three-Dimensional ; In Vitro Techniques ; Gutta-Percha ; Bicuspid

OBJECTIVE: To establish a three-dimensional finite element model of a digital wire loop space maintainer for the mandible and primary tooth loss, in order to investigate the stress, deformation, and shear force experienced by patients with the loss of the second primary molar when wearing the wire loop space maintainer. METHODS: Cone beam computed tomography (CBCT) scans were performed on the patients to create a digital model of the mandible with the absence of the second primary molar using Mimics 21.0 software. A digital model integrating the crown's retention and the wire loop structure of the full crown and ring wire loop space maintainer was constructed using pediatric space maintainer design software, utilizing three different materials: cobalt-chromium alloy, polyether ether ketone (PEEK), and titanium alloy. In ANSYS Work Beach 2023 R2 software, vertical loads of 70 N, tilted 45° along the long axis of the tooth loads of 70 N, and a 10 N load on the surface of the wire loop were applied to the occlusal surfaces of models 46 and 84, simulating centric and lateral occlusions during chewing with the wire loop space maintainer in place. The stress states of the wire loop space maintainer and supporting teeth were analyzed. RESULTS: Under various loading conditions, the maximum principal stress of the ring wire loop space maintainer was significantly lower than that of the full crown. Stress contour maps indicated that the peak of the maximum principal stress occurred at the junction of the wire loop and crown structure, indicating that this area was more susceptible to fracture. The ring wire loop space maintainer made from PEEK material exhibited the lowest maximum shear stress on the internal organizational surfaces, with equivalent stresses of 23.18 MPa and 36.35 MPa for models 46 and 84, respectively. Stress contour maps demonstrated that the maximum stress on tooth 46 was located at its mesial, while the maximum stress on tooth 84 was situated near the root area on its distal, in contact with the wire loop space maintainer. CONCLUSION In cases of second primary molar loss, wearing the digital ring wire loop space maintainer can effectively distribute stress, and the ring wire loop space maintainer made from PEEK material reduces the stress experienced by supporting teeth to some extent, demonstrating its superiority in clinical application.
Finite Element Analysis ; Humans ; Tooth, Deciduous ; Cone-Beam Computed Tomography ; Space Maintenance, Orthodontic/methods* ; Imaging, Three-Dimensional ; Orthodontic Wires ; Dental Stress Analysis ; Mandible ; Stress, Mechanical

OBJECTIVE: To assess the osteogenesis height in maxillary sinus segment one year after zygomatic implantation by imaging methods, and evaluate the influence of patient factors, maxillary sinus anatomical factors and surgical factors on postoperative osteogenesis height. METHODS: This study is a retrospective study, including patients who underwent zygomatic implantation and whose zygomatic implants passed through the maxillary sinus at the Department of Implantology, Peking University School and Hospital of Stomatology from July 2017 to January 2022. Preoperative and postoperative cone beam CT (CBCT)was taken to measure and calculate the average osteogenesis height (AOH) in maxillary sinus segment of the zygomatic implants, then the residual bone height, the width and morphology of the maxillary sinus floor in the buccal and palatal directions were measured. Besides, the integrity of Schneiderian membrane during implant surgery, and the general information of the patients and zygomatic implants were recorded. By comparing anatomical situations and surgical characteristics, the differences of AOH under different conditions were analyzed. Then AOH was divided into two groups (obvious osteogenesis group and non-obvious osteogenesis group) using the median as the threshold, and the influencing factors of osteogenesis were evaluated using mixed effect generalized linear model univariable and multivariable analysis. RESULTS: A total of 47 zygomatic implants were implanted in 24 patients. During the average follow-up period of 12.1 months, there was no implant failure, and the implant survival rate was 100%. Postoperative CBCT showed that 43 zygomatic implants had osteogenic images in the maxillary sinus segment, most of which originated from the floor of the maxillary sinus, and the median AOH was 3.1 mm [interquartile range (IQR): 4.0 mm]. In terms of maxillary sinus width, there were 31 cases (66.0%) of wide type and 16 cases (34.0%) of narrow type. In the aspect of buccal and palatal morphology, 17 cases were taper (36.2%), 20 cases were round (42.6%), and 10 cases were flat (21.3%). The median of residual bone height was 2.8 mm (IQR: 2.2 mm) before operation. Univa-riate analysis of mixed effect generalized linear model showed that postoperative obvious osteogenic rate was related to the residual bone height (OR=2.09, P=0.006). Multivariate analysis showed that the resi-dual bone height (OR=2.55, P=0.022) and the shape of a taper maxillary sinus (OR=11.44, P=0.040) had a significant impact on the postoperative obvious osteogenic rate. CONCLUSION The maxillary sinus floor showed osteogenic images 1 year after the zygomatic implantation surgery. Larger residual bone height and the shape of a taper maxillary sinus may be favorable factors for osteogenesis.
Humans ; Maxillary Sinus/surgery* ; Cone-Beam Computed Tomography ; Retrospective Studies ; Zygoma/diagnostic imaging* ; Male ; Female ; Osteogenesis/physiology* ; Middle Aged ; Adult ; Dental Implants ; Aged ; Dental Implantation, Endosseous/methods*

OBJECTIVE: To evaluate the feasibility and accuracy of cone-beam CT (CBCT) images for radiotherapy dose calculation in pelvic tumors. METHODS: An improved volumetric density coverage method was used to establish CT value-relative electron density (RED) curves for CBCT images. The planning CT plans were transferred to the CBCT images, and the constructed density curves were applied to calculate doses for CBCT plans while maintaining the optimization parameters unchanged. Dose calculation deviations between the two plans were analyzed. RESULTS: The mean differences in dosimetric parameters for the target volume and organs at risk (OAR) between the two plans were less than 1% and 1.5%, respectively. The target conformity index (CI), homogeneity index (HI), and gamma passing rates were highly consistent, with no statistically significant differences. CONCLUSION CBCT images corrected by this method can be used for dose calculation in pelvic tumor radiotherapy planning.
Cone-Beam Computed Tomography/methods* ; Humans ; Radiotherapy Planning, Computer-Assisted/methods* ; Radiotherapy Dosage ; Pelvic Neoplasms/diagnostic imaging*

OBJECTIVE: To investigate the impact of different iterative cone beam CT (iCBCT) scanning beam currents from a ring-mounted linac on synthetic CT image quality for lung adaptive radiotherapy under lung scanning protocol. METHODS: The CIRS lung motion phantom was configured to simulate conventional respiratory motion pattern, followed by 4D-CT simulation. After transferring the radiotherapy plan to the ring-mounted Halcyon 3.0 linac, three groups of typical iCBCT scans with different beam currents [ I _low (160 mA), I _middle (282 mA), and I _high (491 mA)] were performed and corresponding image reconstructions were completed. Synthetic CT (sCT) images were subsequently obtained based on the deformable registration algorithm. RESULTS: Compared to the corresponding CBCT images, the sCT images exhibited a significant reduction in artifacts. The fine structure of the planning CT (pCT) image was preserved for sCT images corresponding to different scanning beam currents, with Dice similarity coefficients exceeding 0.90 for all cases. CONCLUSION The image quality of sCT corresponding to different iCBCTs is comparable to that of pCT, and changes in iCBCT beam parameters have a negligible impact on sCT image quality. Taking into account both image quality and imaging dose factors associated with the beam currents, iCBCT with a lower beam current on the ring-mounted Halcyon linac offers greater clinical value in lung adaptive radiotherapy.
Cone-Beam Computed Tomography/methods* ; Phantoms, Imaging ; Humans ; Radiotherapy Planning, Computer-Assisted/methods* ; Lung/diagnostic imaging* ; Lung Neoplasms/diagnostic imaging*