OBJECTIVES: To explore the synthesis of high-quality CT (sCT) from cone-beam CT (CBCT) using PE-CycleGAN for adaptive radiotherapy (ART) for nasopharyngeal carcinoma. METHODS: A perception-enhanced CycleGAN model "PE-CycleGAN" was proposed, introducing dual-contrast discriminator loss, multi-perceptual generator loss, and improved U-Net structure. CBCT and CT data from 80 nasopharyngeal carcinoma patients were used as the training set, with 7 cases as the test set. By quantifying the mean absolute error (MAE), peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), as well as the dose gamma pass rate and the relative dose deviations of the target area and organs at risk (OAR) between sCT and reference CT, the image quality and dose calculation accuracy of sCT were evaluated. RESULTS: The MAE of sCT generated by PE-CycleGAN compared to the reference CT was (56.89±13.84) HU, approximately 30% lower than CBCT's (81.06±15.86) HU (P<0.001). PE-CycleGAN's PSNR and SSIM were 26.69±2.41dB and 0.92±0.02 respectively, significantly higher than CBCT's 21.54±2.37dB and 0.86±0.05 (P<0.001), indicating substantial improvements in image quality and structural similarity. In gamma analysis, under the 2 mm/2% criterion, PE-CycleGAN's sCT achieved a pass rate of (90.13±3.75)%, significantly higher than CBCT's (81.65±3.92)% (P<0.001) and CycleGAN's (87.69±3.50)% (P<0.05). Under the 3 mm/3% criterion, PE-CycleGAN's sCT pass rate of (90.13±3.75)% was also significantly superior to CBCT's (86.92±3.51)% (P<0.001) and CycleGAN's (94.58±2.23)% (P<0.01). The mean relative dose deviation of the target area and OAR between sCT and planned CT was within ±3% for all regions, except for the Lens Dmax (Gy), which had a deviation of 3.38% (P=0.09). The mean relative dose deviations for PTVnx HI, PTVnd HI, PTVnd CI, PTV1 HI, PRV_SC, PRV_BS, Parotid, Larynx, Oral, Mandible, and PRV_ON were all less than ±1% (P>0.05). CONCLUSIONS PE-CycleGAN demonstrates the ability to rapidly synthesize high-quality sCT from CBCT, offering a promising approach for CBCT-guided adaptive radiotherapy in nasopharyngeal carcinoma.
Humans ; Cone-Beam Computed Tomography/methods* ; Nasopharyngeal Neoplasms/diagnostic imaging* ; Nasopharyngeal Carcinoma/radiotherapy* ; Radiotherapy Planning, Computer-Assisted/methods* ; Radiotherapy Dosage ; Signal-To-Noise Ratio ; Radiotherapy, Intensity-Modulated

OBJECTIVES: We propose a sparse-view cone-beam CT reconstruction algorithm based on bidirectional flow field guided projection completion (BBC-Recon) to solve the ill-posed inverse problem in sparse-view cone-beam CT imaging. METHODS: The BBC-Recon method consists of two main modules: the projection completion module and the image restoration module. Based on flow field estimation, the projection completion module, through the designed bidirectional and multi-scale correlators, fully calculates the correlation information and redundant information among projections to precisely guide the generation of bidirectional flow fields and missing frames, thus achieving high-precision completion of missing projections and obtaining pseudo complete projections. The image restoration module reconstructs the obtained pseudo complete projections and then refines the image to remove the residual artifacts and further improve the image quality. RESULTS: The experimental results on the public datasets of Mayo Clinic and Guilin Medical University showed that in the case of a 4-fold sparse angle, compared with the suboptimal method, the BBC-Recon method increased the PSNR index by 1.80% and the SSIM index by 0.29%, and reduced the RMSE index by 4.12%; In the case of an 8-fold sparse angle, the BBC-Recon method increased the PSNR index by 1.43% and the SSIM index by 1.49%, and reduced the RMSE index by 0.77%. CONCLUSIONS The BBC-Recon algorithm fully exploits the correlation information between projections to allow effective removal of streak artifacts while preserving image structure information, and demonstrates significant advantages in maintaining inter-slice consistency.
Algorithms ; Cone-Beam Computed Tomography/methods* ; Image Processing, Computer-Assisted/methods* ; Humans

OBJECTIVES: We propose a segmented backprojection tensor degradation feature encoding (SBP-MAC) model for motion artifact correction in dental cone beam computed tomography (CBCT) to improve the quality of the reconstructed images. METHODS: The proposed motion artifact correction model consists of a generator and a degradation encoder. The segmented limited-angle reconstructed sub-images are stacked into the tensors and used as the model input. A degradation encoder is used to extract spatially varying motion information in the tensor, and the generator's skip connection features are adaptively modulated to guide the model for correcting artifacts caused by different motion waveforms. The artifact consistency loss function was designed to simplify the learning task of the generator. RESULTS: The proposed model could effectively remove motion artifacts and improve the quality of the reconstructed images. For simulated data, the proposed model increased the peak signal-to-noise ratio by 8.28%, increased the structural similarity index measurement by 2.29%, and decreased the root mean square error by 23.84%. For real clinical data, the proposed model achieved the highest expert score of 4.4221 (against a 5-point scale), which was significantly higher than those of all the other comparison methods. CONCLUSIONS The SBP-MAC model can effectively extract spatially varying motion information in the tensors and achieve adaptive artifact correction from the tensor domain to the image domain to improve the quality of reconstructed dental CBCT images.
Cone-Beam Computed Tomography/methods* ; Artifacts ; Humans ; Motion ; Image Processing, Computer-Assisted/methods* ; Signal-To-Noise Ratio ; Algorithms

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: To clarify the role of concentrated growth factors (CGF) in the treatment of periodontal cement defects using calcium phosphate cement (CPC) with self-curing properties. METHODS: Thirty-six intrabony defects were randomly divided into two groups. The experimental group received CGF+CPC treatment (n=18), while the control group received CPC treatment alone (n=18). The probing depth, clinical attachment loss, and hard tissue filling as measured by cone beam CT (CBCT) were evaluated at baseline and 1 year postoperatively in both groups, and the levels of major growth factors in CGF and serum were compared [platelet-derived growth factor-BB (PDGF-BB), transforming growth factor-β1 (TGF-β1), insulin-like growth factor-1 (IGF-1), and vascular endothelial growth factor (VEGF)]. RESULTS: At baseline, there were no statistically significant differences in probing depth, clinical attachment loss and CBCT measurements between the two groups (P>0.05). At 1 year postoperatively, significant improvements were observed in parameters mentioned above in both groups (P < 0.05). The CGF+CPC group seemed more effective compared with the CPC group in reduction of probing depth [(4.5±1.3) mm vs. (3.2±1.1) mm] and clinical attachment gain [(3.8±0.9) mm vs. (2.0±0.5) mm, P < 0.05]. Compared with the group treated with CPC alone, the hard tissue filling degree shown by CBCT in the CGF+CPC group was significantly increased [the reduction of the depth of the intrabony defects was (3.9±1.2) mm vs. (2.1±0.7) mm, respectively, P < 0.01]. At 1 year post-operatively, the volume of the intrabony defects shown by CBCT in the CGF+CPC group was reduced by (0.031 8±0.004 1) mL, which was significantly more than that in the CPC group [(0.019 7±0.001 2) mL, P < 0.05]. In addition, the concentration of the main growth factors (PDGF-BB, TGF-β1, IGF-1, and VEGF) in CGF were higher than those in serum (P < 0.001). CONCLUSION After 1 year of follow-up, the results of the present study indicated that CGF could significantly improve the clinical and radiological effects of CPC on the treatment of periodontal intrabony defects.
Humans ; Calcium Phosphates/therapeutic use* ; Male ; Female ; Bone Cements/therapeutic use* ; Middle Aged ; Cone-Beam Computed Tomography ; Alveolar Bone Loss/therapy* ; Becaplermin ; Adult ; Insulin-Like Growth Factor I ; Intercellular Signaling Peptides and Proteins/therapeutic use* ; Proto-Oncogene Proteins c-sis/blood* ; Transforming Growth Factor beta1/blood* ; Vascular Endothelial Growth Factor A/blood*

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