Search Results (111)

Panoramic radiographs are widely used in dental practice due to their ability to provide a comprehensive view of the teeth, jaws, and surrounding anatomical structures in a single examination. However, automated interpretation remains challenging because multiple conditions may co-exist within a single image, class distributions are highly imbalanced, and several findings exhibit subtle radiographic characteristics. This study presents a deep learning framework for multi-label dental findings classification using panoramic radiographs from the publicly available VZRAD2 dataset. Following a label curation process, eleven clinically relevant classes were retained, including diseases, treatments, and anatomical structures. The proposed EfficientNet-B4-CBAM model integrates an EfficientNet-B4 backbone with a Convolutional Block Attention Module (CBAM) to enhance feature representation through channel and spatial attention. EfficientNet-B4 and ResNet50 were used as baseline models for comparison under a unified training protocol. The training pipeline incorporates data augmentation, weighted sampling to address class imbalance, AdamW optimization, and Binary Cross-Entropy with Logits loss for multi-label learning. On the validation set, the proposed model achieved the highest micro-F1 score of 0.8567, compared to 0.8424 for EfficientNet-B4 and 0.8469 for ResNet50. ROC analysis showed comparable separability across models, with micro-AUC values of 0.946 (EfficientNet-B4-CBAM), 0.947 (EfficientNet-B4), and 0.960 (ResNet50). Class-wise evaluation indicated strong performance for visually distinct findings such as impacted tooth, implant, filling, and root canal treatment, while anatomically diffuse or underrepresented classes remained more challenging. Grad-CAM visualizations suggest that the model focuses on clinically relevant regions, supporting interpretability. Overall, the results indicate that attention-enhanced convolutional models can provide effective and interpretable support for multi-label dental findings classification. However, the observed performance improvements are modest, and further validation on independent datasets, along with clinical evaluation, is required to confirm generalizability and real-world applicability. Full article

Objectives: The aim of this retrospective study was to evaluate the long-term clinical and radiographic performance of zirconia dental implants with one-piece and two-piece configurations supporting single-tooth restorations. The primary outcome was implant survival, while the secondary outcome was the assessment of interproximal marginal bone loss (MBL) over time. Materials and methods: A total of 67 implants placed in 55 patients were included, with a mean follow-up of 60.6 months. Forty-five implants were one-piece systems and twenty-two were two-piece systems. All surgical and prosthetic procedures were performed by the same operator, following the manufacturer’s recommendations. Final restorations were delivered three months after implant placement. Marginal bone levels were assessed radiographically at the time of definitive prosthesis delivery (T0) and at the last follow-up examination (T1). Statistical significance level was set at 5% (α = 0.05). Results: The overall implant survival rate was 100% in both groups. One-piece implants showed higher initial MBL values than two-piece implants; however, bone level changes over time were limited in both configurations, with no significant intra-group differences between T0 and T1. Conclusions: Both implant configurations showed excellent clinical and radiographic outcomes, with a 100% survival rate and limited marginal bone loss during long-term follow-up. Marginal bone levels appeared to be influenced more by implant neck design than by implant configuration, suggesting that zirconia implants with a smooth transmucosal design may represent a reliable metal-free option for single-tooth rehabilitation in properly selected patients. Full article

The accuracy of static computer-aided implant surgery (s-CAIS) is fundamental for predictable clinical outcomes. The objective of this study was to evaluate the influence of different guide-support modalities on the linear and angular accuracy of implant placement. In this retrospective clinical investigation conducted at a single specialty hospital, a total of 180 implants were analyzed, divided into three equal groups (n = 60) based on the guide support type: tooth-supported, bone-supported, and mucosa-supported. Accuracy was assessed by superimposing preoperative virtual plans with postoperative cone-beam computed tomography (CBCT) scans, measuring linear deviations at the neck and apex of the implant, as well as angular discrepancies. The type of guide support was found to be a significant factor associated with surgical accuracy (p < 0.001). Tooth-supported guides demonstrated the highest level of accuracy, with a mean angular deviation of 1.81° ± 0.45° and linear deviations at the neck and apex of 0.59 ± 0.18 mm and 0.73 ± 0.19 mm, respectively. These were followed by bone-supported guides (2.14° ± 0.48°; 1.04 ± 0.26 mm; 1.61 ± 0.31 mm), while mucosa-supported guides exhibited the greatest deviations (2.95° ± 0.60°; 1.47 ± 0.29 mm; 1.87 ± 0.37 mm). Significant intergroup differences and large effect sizes were observed, particularly regarding angular and horizontal discrepancies. These findings demonstrate a distinct gradient of accuracy based on guide support, establishing tooth-supported guides as the most accurate, followed by bone-supported and, lastly, mucosa-supported guides. While all modalities are clinically applicable, the use of mucosa-supported guides necessitates increased safety margins to account for the increased risk of linear and angular discrepancies inherent to mucosal tissue displacement. Full article

Background/Objectives: Pterygoid implant placement represents a valuable alternative to conventional bone grafting procedures in the rehabilitation of the atrophic posterior maxilla; however, the procedure remains technically demanding because of limited visibility, difficult access, complex pterygomaxillary anatomy, and the need for precise angulation and distal bicortical anchorage. Although digital guidance has increasingly been applied in implant dentistry, a clearly described workflow integrating automatic segmentation, selective virtual trimming of the posterior maxillary anatomy, and direct three-dimensional planning for static-guided pterygoid implant placement remains insufficiently detailed in the literature. The aim of this report was to describe and illustrate such a workflow in a proof-of-concept clinical application. Methods: This work was designed as a methodological proof-of-concept with a single clinical illustration. A CBCT dataset was imported into BlueSkyPlan, where automatic segmentation was used to generate three-dimensional models of the maxilla, teeth, and pterygoid process. The segmented volumes were then selectively trimmed to expose the relevant pterygomaxillary anatomy and to support direct three-dimensional planning of the implant axis in the rendered model. A static surgical guide with combined tooth and mucosal support was subsequently designed, positioned on a printed jaw model derived from the intraoral scan, and assessed by CBCT-based internal verification. Results: In this proof-of-concept application, the workflow enabled three-dimensional visualization of the pterygomaxillary trajectory, supported implant axis planning in the rendered model, and facilitated guide design and radiographic verification of the planned trajectory. The verification step provided an internal methodological consistency check between the planned implant axis and the drill-guided direction visible on CBCT. Conclusions: The present report describes a segmentation-assisted three-dimensional planning workflow for static-guided pterygoid implant placement in a single proof-of-concept clinical application. The workflow should be interpreted as a methodological illustration rather than a quantitative validation study. Further investigations are required to evaluate accuracy, inter-operator reproducibility, and broader clinical applicability. Full article

Background/Objectives: The objective assessment of natural tooth mobility remains challenging in clinical practice. This pilot study aimed to investigate the feasibility, repeatability, and agreement of a modified implant stability measurement system adapted for natural teeth using a custom-fabricated titanium bracket and a modified SmartPeg. Methods: Sixteen systemically healthy patients (10 males, six females) and 94 single-rooted permanent teeth with varying mobility grades were included. The tooth mobility was assessed using the Miller Mobility Index, Periotest M, and resonance frequency analysis (RFA) with the Osstell Beacon device. For the Osstell measurements, a custom titanium bracket bonded to the buccal tooth surface allowed for the placement of a modified SmartPeg. Each tooth was measured twice under standardized conditions, and mean values were recorded. The statistical analyses included Spearman correlation analysis, Cohen’s kappa for agreement with Miller categories, and intraclass correlation coefficients (ICCs) to assess the measurement repeatability. Results: The mean Periotest value was 12.70 ± 13.69, and the mean ISQ (implant stability quotient) value was 69.45 ± 19.37. The repeated measurements demonstrated excellent intra-examiner repeatability for both devices (ICC > 0.95). The Periotest values showed substantial agreement with the Miller mobility grades (κ = 0.763; p < 0.001), whereas the Osstell values demonstrated weak agreement with these ordinal categories (κ = 0.094; p = 0.048). A strong negative correlation was observed between the Periotest and Osstell measurements irrespective of the scales (r = −0.865; p < 0.001). Conclusions: In natural dentition, the resonance frequency analysis demonstrated reproducible measurements under controlled experimental conditions and showed measurable associations with conventional mobility assessments. However, the method remains investigational. The findings do not establish clinical validity for the routine assessment of natural tooth mobility. Further studies with larger sample sizes and statistical models accounting for patient-level clustering are required before clinical implementation can be considered. This study is registered at ClinicalTrials.gov (NCT07188168). Full article

Adequate alveolar bone volume is a prerequisite for predictable and long-term success in dental implant therapy. Physiological post-extraction remodeling frequently results in horizontal and vertical ridge deficiencies, which may compromise optimal implant placement. Guided bone regeneration (GBR) has become a cornerstone procedure in implant dentistry, with clinical outcomes largely influenced by the biological and mechanical characteristics of grafting materials. Different bone grafts and their combinations are currently clinically applicable, each exhibiting distinct osteogenic, osteoinductive, and osteoconductive properties, as well as varying resorption profiles and volumetric stability. This narrative review aims to analyze the biological principles of alveolar ridge augmentation, compare the properties of commonly used graft materials, evaluate clinical outcomes, and discuss emerging regenerative strategies. Literature published between 2000 and 2025 was assessed to synthesize current evidence regarding graft integration, bone formation, desorption dynamics, and clinical indications. Autogenous bone remains the gold standard due to its combined osteogenic, osteoinductive, and osteoconductive potential; however, its limitations have driven the development of alternative materials, including allografts, xenografts, alloplastic substitutes, demineralized tooth matrices, platelet concentrates, and customized scaffolds. While no single material is universally ideal, appropriate selection based on defect characteristics and clinical objectives is essential for predictable outcomes. Future research should prioritize long-term comparative trials, biomaterial standardization, and biologically enhanced regenerative approaches. Full article

Background and Objectives: When a single missing tooth must be replaced, the best solution is the placement of an implant. In adults, most of the time the space for implant is totally or partially closed due to the shift in the adjacent teeth. The objective of the study was to describe the clinical parameters, treatment choices, and outcomes associated with orthodontic space opening for single-tooth implants in various treatment solutions, as well as to determine their influence on the variation in the dimension of the edentulous space. Materials and Methods: An observational prospective cohort study was designed in which patients with a single missing tooth were selected to be included in the study. After the clinical examination two groups were formed: patients who opted for fixed orthodontic treatment (metallic or sapphire) to open space for implant and patients who opted for alignment to achieve this (with Invisalign or Spark). All subjects received orthodontic treatment. A dental chart was created for each patient which included demographics, clinical data, orthopantomography (OPG), profile cephalograms, and photographs. The potential implant prosthetic space was measured during orthodontic treatment to observe the space dimension evolution in time. Results: In total, 97 patients were included in the study, 60 women and 37 men, with ages between 14 and 60 years. Edentulous spaces dimensions were opened from 1–4 mm to 5–6 mm (39.18% patients), 6–8 mm (48.45%), and >8 mm (12.37%). Both types of orthodontic treatments were effective in opening the potential prosthetic space for implant. Conclusions: Large prosthetic spaces and older edentulism tend to require longer treatments. Older patients had experienced edentulism for a longer period, indicating a correlation between age and the duration of tooth loss. Metal fixed orthodontic appliances were used in exceedingly long treatments, while aligners/sapphire brackets were used in short–medium durations. For the study group, fixed appliances and aligners proved to be effective in opening the space for future implants. Full article

Dental implantation affects masticatory bite and muscle forces. The temporomandibular joint (TMJ) bears a substantial amount of these masticatory forces. Thus, the objective of the current study was to investigate whether dental implantation alters the human mandibular condyle. Among 556 images, 54 and 22 CBCT scans were successfully identified from 27 patients (10 males and 17 females; 54.93 ± 19.46 years) in the control group and 11 patients (3 males and 8 females; 51.32 ± 13.13 years) in the implant group, respectively. In the control group, CBCT images were obtained longitudinally at the time of implantation and after the post-implantation healing period, both prior to crown placement. In the implant group, CBCT images were obtained at the time of crown placement on a single-tooth implant and after the functional loading period following crown placement. Left and right mandibular condyles were digitally isolated from the images. The bone mineral density (BMD) parameters and morphological changes were assessed using frequency plots of BMD and TMJ osteoarthritis (OA) counts, respectively. In the control group, BMD values were not significantly different between the first and second scans. In contrast, the implant group showed a significant decrease in BMD values, along with a marginal increase in TMJ OA counts after the functional loading period. The TMJ OA counts were highest in the anterior regions, followed by the middle and posterior regions. Most regions showed significantly reduced BMD values, except the antero-lateral and antero-central regions. The current findings give an insight that dental implantation may alter the morphology and BMD of human mandibular condyles. The TMJ OA counts increased, while BMD decreased during the functional loading period of more than 3 months following implantation. Masticatory loading associated with the dental implant likely increases the load on the TMJ, which could stimulate new bone formation to balance the load distribution on the mandibular condyle. Full article

Objectives: To compare artificial intelligence (AI) crown design with expert or non-AI computer-aided (CAD) design for single-unit tooth and implant-supported crowns across efficiency, marginal and internal fit, morphology and occlusion, and mechanical performance. Materials and Methods: This systematic review was conducted and reported in accordance with PRISMA 2020. PubMed MEDLINE, Scopus, Web of Science, IEEE Xplore, and Dentistry and Oral Sciences Source were searched from 2016 to 2025 with citation chasing. Eligible studies directly contrasted artificial intelligence-generated or artificial intelligence-assisted crown designs with human design in clinical, ex vivo, or in silico settings. Primary outcomes were design time, marginal and internal fit, morphology and occlusion, and mechanical performance. Risk of bias was assessed with ROBINS-I for non-randomized clinical studies, QUIN for bench studies, and PROBAST + AI for computational investigations, with TRIPOD + AI items mapped descriptively. Given heterogeneity in settings and endpoints, a narrative synthesis was used. Results: A total of 14 studies met inclusion criteria, including a clinical patient study, multiple ex vivo experiments, and in silico evaluations. Artificial intelligence design reduced design time by between 40% and 90% relative to expert computer-aided design or manual workflows. Marginal and internal fit for artificial intelligence and human designs were statistically equivalent in multiple comparisons. Mechanical performance matched technician designs in load-to-fracture testing, and modeling indicated stress distributions similar to natural teeth. Overall risk of bias was judged as some concerns across tiers. Conclusions: Artificial intelligence crown design delivers efficiency gains while showing short-term technical comparability across fit, morphology, occlusion, and strength for single-unit crowns in predominantly bench and in silico evidence, with limited patient-level feasibility data. Prospective clinical trials with standardized, preregistered endpoints are needed to confirm durability, generalizability, and patient-relevant outcomes, and to establish whether short-term technical advantages translate into clinical benefit. Full article

This study aimed to evaluate the biomechanical behavior of different implant macrogeometries under immediate and delayed implantation protocols in a single maxillary anterior tooth model using three-dimensional finite element analysis. Six implant models from three different implant systems were analyzed, each including one aggressive and one passive macrogeometric design. In the immediate implantation models, implants were placed within the extraction socket, with the buccal gap filled using a xenograft material, whereas in the delayed implantation models, a fully remodeled healed bone condition was simulated. Stress and strain distributions were evaluated under a 120 N static oblique load representing functional occlusal forces in the anterior maxilla. Under immediate implantation conditions, aggressive designs demonstrated a more homogeneous stress distribution and reduced cervical stress concentration compared with passive designs, while maintaining comparable apical stress levels. Similarly, in delayed implantation models, aggressive macrogeometries exhibited lower stress concentrations in the cervical cortical bone relative to cylindrical designs. Overall, these findings suggest that aggressive implant macrogeometry may favorably balance cervical stress reduction and apical load transfer, supporting peri-implant bone preservation while maintaining primary mechanical anchorage. Full article

The milled surface topography of NiTi SMA critically affects its frictional behavior, corrosion resistance, and biocompatibility, which are essential for biomedical and aerospace applications. This study combines simulation and single-factor experiments to investigate the coupling behavior among surface topography evolution, work hardening, plastic deformation, and residual stress evolution. Results showed that increasing feed per tooth led to a significant rise in surface residual height and an improvement in surface isotropy. With the increase in feed per tooth, the error between the experimental and simulated heights gradually decreased from 105.6% to 30.9%, indicating that both material properties and feed per tooth strongly affect residual profile formation in the feed direction. In addition, larger feed per tooth intensifies work hardening and plastic deformation but reduces surface residual stress, thereby increasing microhardness. These effects can mitigate material rebound and improve surface profile accuracy. The results provide a direct basis for controlling the surface integrity of NiTi SMA components through machining parameter optimization, enabling precise tailoring of functional surface characteristics, such as wear performance, chemical stability, and biological response, which is of critical importance for high-end biomedical implants and aerospace systems. Full article

Background: Extended platelet-rich fibrin (e-PRF) membranes are a novel 100% autologous biomaterial with a longer resorption time (4–6 months) than traditional solid-PRF membranes (two weeks). In part 1 of this 2-part publication series, four clinical variations for using these novel e-PRF membranes for socket preservation were introduced. In this randomized clinical trial (RCT), all four iterations of e-PRF membranes were compared to traditional collagen membranes in alveolar ridge preservation for hard and soft tissue dimensional changes and early wound healing outcomes. Methods: A single-center RCT was conducted, including 55 patients requiring the extraction of a single tooth with planned implant placement. All sockets were grafted with a “sticky bone” (bone allograft mixed with PRF) and secured with either a collagen membrane (control) or e-PRF membranes utilizing the four variations present in Part 1 (both formed extra-orally or intra-orally, each with or without an overlying solid PRF membrane). The time of fabrication and application of each e-PRF iteration was recorded. Cone beam computed tomography was utilized to evaluate horizontal and vertical ridge dimensions at baseline and 3 months post-operatively, and soft tissue thickness was also measured at both time intervals utilizing an endodontic reamer. Early wound healing was recorded at 2 weeks, utilizing the Landry, Turnbull, and Howley Index by three blinded clinicians. Results: The results demonstrated that, at 3 months, the e-PRF membranes fabricated utilizing all 4 treatment variations demonstrated equal improvements in horizontal and vertical ridge dimensions and soft tissue thickness when compared to collagen membranes. Additionally, the membrane (p = 0.029) and membrane w/solid (p = 0.021) groups demonstrated statistically significant superior early wound healing compared to the collagen membrane group. Notably, the Bio-Filler groups demonstrated statistically significant reduction in fabrication/application time compared to the membrane groups. Conclusions: Within the limitations of this RCT, all e-PRF iterations performed comparably to collagen membranes in maintaining both hard and soft tissue ridge dimensions when combined with sticky bone, while also significantly improving soft tissue wound healing. Future RCTs with alternative grafting materials, direct wound-margin assessment, and evaluation of patient-reported outcomes are necessary to clarify the advantages of each membrane type. Full article

Tooth extraction induces changes in both hard and soft tissues, which may compromise implant placement. Leukocyte- and platelet-rich fibrin (L-PRF) is used to promote tissue healing, either alone or in combination with other grafting materials. Objective: This study aimed to compare post-extraction socket healing using L-PRF alone or combined with a biphasic calcium phosphate graft (HA/β-TCP) after eight weeks. Materials and Methods: 15 patients, both sexes, mean age 56.7 ± 8.2 years, requiring alveolar ridge preservation after single-rooted tooth extraction for subsequent implant placement, were included. Sockets were randomly assigned to four groups: control with blood clot only (CTR), autogenous bone graft (AB), L-PRF membrane (LPRF), and L-PRF combined with HA/β-TCP (LPRFHA). The protocol consisted of tooth extraction and immediate graft placement, followed by bone biopsy at 8 weeks for histomorphometric analysis and implant installation. New Bone Formation (NBF) was quantified from ten photomicrographs per sample using ImageJ software (version 1.54, 5 February 2025). One-way ANOVA with Bonferroni post hoc tests was applied, with statistical significance set at p ≤ 0.05. Results: A significant difference in NBF (%) was observed between the control and LPRFHA groups (p = 0.014), with greater bone formation in the control group (62.4 ± 18.6%) compared with LPRFHA (55.8 ± 17.2%; p = 0.012). No significant differences were found among AB, LPRF, and LPRFHA groups. LPRF and AB showed comparable bone formation (60.2 ± 17.5% and 60.1 ± 20.0%, respectively). Conclusions: L-PRF, either alone or combined with HA/β-TCP, can be used for alveolar ridge preservation in maxillary sockets. L-PRF, alone or with synthetic HA/β-TCP graft, effectively preserves the anterior maxillary ridge for early loading at eight weeks. All treatments achieved bone formation for implant placement, with the blood clot alone showing superior results. Full article

Background/Objectives: Artificial intelligence (AI) systems may enhance diagnostic accuracy in cone-beam computed tomography (CBCT) analysis. However, most validations focus on isolated tooth-level tasks rather than clinically meaningful full-mouth assessment outcomes. To evaluate the diagnostic accuracy of a commercial AI platform for detecting dental treatment features on CBCT images at both tooth and full-scan levels. Methods: In this retrospective single-center study, 147 CBCT scans (4704 tooth positions) were analyzed. Two experienced readers annotated treatment features (missing teeth, fillings, endodontic treatments, crowns, pontics, orthodontic appliances, implants), and consensus served as the reference. Anonymized datasets were processed by a cloud-based AI system (Diagnocat Inc., San Francisco, CA, USA). Diagnostic metrics—sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and F1-score—were calculated with 95% patient-clustered bootstrap confidence intervals. A “Perfect Agreement” criterion defined full-scan level success as an entirely error-free full-mouth report. Results: Tooth-level AI performance was excellent, with accuracy exceeding 99% for most categories. Sensitivity was highest for missing teeth (99.3%) and endodontic treatments (99.0%). Specificity and NPV exceeded 98.5% and 99.7%, respectively. Full-scan level Perfect Agreement was achieved in 82.3% (95% CI: 76.2–88.4%), with errors concentrated in teeth presenting multiple co-existing findings. Conclusions: The evaluated AI platform demonstrates near-perfect accuracy in detecting isolated dental features but moderate reliability in generating complete full-mouth reports. It functions best as an assistive diagnostic tool, not as an autonomous system. Full article

Xenodens calminechari is a highly derived mosasaurid from the latest Maastrichtian Phosphates of the Oulad Abdoun Basin, Morocco. Originally described based on a single maxilla, Xenodens differs from all known squamates in its closely packed, bladelike marginal teeth and modified tooth implantation and replacement. Xenodens’ relationships and anatomy remain poorly understood, and a recent study suggested that the holotype represents a composite, and furthermore that the animal might represent a juvenile of Carinodens. Evidence from a new referred specimen of Xenodens and CT scans corroborate the original description of Xenodens. Scans of the holotype and referred specimen of Xenodens reveal highly derived tooth implantation; interdental ridges are reduced in the posterior part of the jaw and teeth implant in a groove, with adjacent roots contacting and fusing. Tooth roots bear large, deep replacement pits, as is typical of derived mosasaurids, but in posterior teeth the replacement pits merge lingually to create a single large pit for two teeth. We provide an updated diagnosis of Xenodens, detailing unusual features of its tooth anatomy, implantation and replacement. Differences between Xenodens and Carinodens are numerous and no intermediate morphologies exist; furthermore, the size overlap between Carinodens and Xenodens indicates that Xenodens cannot represent a juvenile Carinodens. Xenodens highlights the remarkable diversity of mosasaurids, as well as the exceptional range of ecological niches occupied by this highly successful group of marine reptiles before their extinction. Full article