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 evaluate the clinical and radiographic efficacy of micro crestal flap-alveolar ridge preservation following extraction of mandibular molars with severe periodontitis compared with natural healing, and to preliminarily propose the surgical indication. METHODS: A retrospective analysis was conducted on clinical data from patients with mandibular molars with severe periodontitis either receiving micro crestal flap-alveolar ridge preservation (MCF-ARP group) or undergoing natural healing in department of periodontology, Peking University School and Hospital of Stomatology from September 2013 to June 2021. Cone-beam computed tomography scannings performed before/immediately after extraction (as baseline) and repeated before implantation (after the extraction socket healing) were used to measure the ridge width, height and volumetric changes of the sockets, and the proportion of guided bone regeneration (GBR) during implant therapy were compared between the two groups. RESULTS: Between baseline and healing, significant differences in changes of MCF-ARP group [(8.34±2.81) mm] and natural healing group [(3.82±3.58) mm] in the distances from mandibular canal to center of the tooth socket were recorded (P < 0.001). The ridge width at 1 mm below the most coronal aspect of the crest increased by (3.50±4.88) mm in the MCF-ARP group but decreased by (0.16±5.70) mm in the natural healing group, respectively (P=0.019). After healing, the MCF-ARP group showed the distances from mandibular canal to center of the tooth socket >8 mm in all the cases, with 97.1% exceeding 10 mm. Natural healing group displayed 23.1% of the cases with center bone height < 8 mm and 61.5% exceeding 10 mm. Volume changes at the buccal and lingual aspect as well as the total socket were significantly greater in the MCF-ARP group compared with natural healing group (P < 0.001).At the time of implantation, GBR was performed in 5 out of 68 subjects (8.3%) in the MCF-ARP group, whereas 8 out of 26 subjects (30.8%) in the natural healing group required GBR, reflecting significant difference (P=0.003). CONCLUSION In the sites of mandibular molars with severe periodontitis, when the distances from mandibular canal to center of the tooth socket was not enough (less than 7 mm), clinicians could consider performing the micro crestal flap-alveolar ridge preservation to achieve augmentation for alveolar ridge and reduce the proportion of guided bone regeneration during implant therapy to reduce the difficulty and risk of injuries during implant therapy.
Humans ; Tooth Extraction ; Retrospective Studies ; Surgical Flaps ; Molar/surgery* ; Mandible/surgery* ; Female ; Periodontitis/surgery* ; Male ; Adult ; Middle Aged ; Cone-Beam Computed Tomography ; Alveolar Ridge Augmentation/methods* ; Alveolar Process/surgery* ; Tooth Socket/diagnostic imaging* ; Dental Implantation, Endosseous/methods*

OBJECTIVE: Dynamic navigation approaches are widely employed in the context of implant placement surgery. Implant surgery can be divided into immediate and delayed surgery according to the time of implantation. This retrospective study was developed to compare the accuracy of dynamic navigation system for immediate and delayed implantations. METHODS: In the study, medical records from all patients that had undergone implant surgery between August 2019 and June 2021 in the First Clinical Division of the Peking University School and Hospital of Stomatology were retrospectively reviewed. There were 97 patients [53 males and 44 females, average age (47.14±11.99) years] and 97 implants (delayed group: 51; immediate group: 46) that met with study inclusion criteria and were included. Implant placement accuracy was measured by the superposition of the planned implant position in the preoperative cone beam computed tomography (CBCT) image and the actual implant position in the postoperative CBCT image. The 3-dimensional (3D) entry deviation (3D deviation in the coronal aspect of the alveolar ridge), 3D apex deviation (3D deviation in the apical area of the implant) and angular deviation were analyzed as the main observation index when comparing these two groups. The 2-dimensional (2D) horizontal deviation of the entry point and apex point, and the deviation of entry point depth and apex point depth were the secondary observation index. RESULTS: The overall implant restoration survival rate was 100%, and no mechanical or biological complications were reported. The implantation success rate was 100%. The 3D entry deviation, 3D apex deviation and angular deviation of all analyzed implants were (1.146±0.458) mm, (1.276±0.526) mm, 3.022°±1.566°, respectively; while in the delayed group these respective values were (1.157±0.478) mm, (1.285±0.481) mm and 2.936°±1.470° as compared with (1.134±0.440) mm, (1.265±0.780) mm, 3.117°±1.677° in the immediate group. No significant differences (P=0.809, P=0.850, P=0.575) in accuracy were observed when comparing these two groups. CONCLUSION Dynamic computer-assisted implant surgery system promotes accurate implantation, and both the immediate and delayed implantations exhibit similar levels of accuracy under dynamic navigation system that meets the clinical demands. Dynamic navigation system is feasible for immediate implantation.
Humans ; Male ; Female ; Retrospective Studies ; Middle Aged ; Cone-Beam Computed Tomography ; Dental Implantation, Endosseous/methods* ; Surgery, Computer-Assisted/methods* ; Dental Implants ; Adult ; Surgical Navigation Systems ; Immediate Dental Implant Loading/methods* ; Imaging, Three-Dimensional

OBJECTIVE: To establish a similarity measurement model for patients with dentofacial deformity based on 3D craniofacial features and to validate the similarity results with quantifying subjective expert scoring. METHODS: In the study, 52 cases of patients with skeletal Class Ⅲ malocclusions who underwent bimaxillary surgery and preoperative orthodontic treatment at Peking University School and Hospital of Stomatology from January 2020 to December 2022, including 26 males and 26 females, were selected and divided into 2 groups by sex. One patient in each group was randomly selected as a reference sample, and the others were set as test samples. Three senior surgeons rated the similarity scores between the test samples and the reference sample. Similarity scores ranged from 1 to 10, where 1 was completely different, and 10 was exactly the same. Scores larger than 7.5 was considered as clinically similar. Preoperative cone beam computed tomography (CBCT) and 3D facial images of the patients were collected. The three-dimensional hard and soft tissue features, including distances, angles and 3D point cloud features were extracted. The similarity measurement model was then established to fit with the experts' similarity scoring by feature selection algorithm and linear regression model. To verify the reliability of the model, 14 new patients were selected and input to similarity measurement model for finding similar cases. The similarity scoring of these similar cases were rated by experts, and used to evaluate the reliability of the model. RESULTS: The similarity metric models indicated that the features of the middle and lower craniofacial features were the main features to influence the craniofacial similarity. The main features that were related to the expert' s similarity scoring included distance of anterior nasal spine-menton (ANS-Me), distance of right upper canion point-Frankfurt horizontal plane (U3RH), distance of left superior point of the condyle-left gonion (CoL-GoL), distance of left gonion-menton (CoL-Me), distance of pogonion-midsagittal plane (Pog-MSP), distance of right alar base-left alar base (AlR-AlL), angle of pronasale-soft tissue pogonion-labrale inferius (Pn-Pog' -Li), distance of trichion-right tragus (Tri-TraR), distance of left exocanthion-left alar base (ExL-AlL), lower 1/3 of skeletal face, middle and lower 2/3 of skeletal face and upper lip region of soft tissue. Fourteen new patients were chosen to evaluate the model. The similar cases selected by the model had an average experts' similarity scoring of 7.627± 0.711, which was not significantly different with 7.5. CONCLUSION The similarity measurement model established by this model could find the similar cases which highly matched experts' subjective similarity scoring. The study could be further used for similar cases retrieval in skeletal Ⅲ malocclusion patients.
Humans ; Male ; Female ; Imaging, Three-Dimensional/methods* ; Cone-Beam Computed Tomography ; Malocclusion, Angle Class III/surgery* ; Orthognathic Surgical Procedures/methods* ; Face/anatomy & histology* ; Cephalometry/methods* ; Adult ; Adolescent ; Dentofacial Deformities/surgery* ; Young Adult

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