Search Results (150)

Background/Objectives: Furcation defects pose a significant challenge in the diagnosis and treatment planning of periodontal diseases. Accurate clinical identification of furcation involvement is essential for improving treatment outcomes. This study aimed to evaluate the accuracy and effectiveness of various artificial intelligence (AI) algorithms in detecting furcation defects (FD) in mandibular molars. Methods: A total of 654 panoramic radiographs were randomly selected from patients who visited the Department of Oral and Maxillofacial Radiology at the Faculty of Dentistry, Ankara University. Each image was labeled as either “healthy” or “FD” and subsequently preprocessed. The performance of different deep learning algorithms in identifying FD was subsequently evaluated. Results: In the classification models employed, the highest scores were calculated as accuracy 97.9%, precision 97.10%, sensitivity 97.08%, and F1 score 97.09% in the Xception model. In the segmentation tests, the highest scores were calculated as accuracy 99.96%, precision 99.26%, sensitivity 97.57%, and F1 score 98.41% in the ENet model. Conclusions: Results of this study indicated that the use of artificial intelligence systems in detecting furcation involvement in mandibular molar teeth in panoramic radiography images is promising. Further studies covering larger data sets, including maxillary molar teeth, will increase the success rates in detecting furcation involvement. Full article

Introduction: Odontogenic sinusitis (ODS) is an underrecognized cause of maxillary sinus inflammation and is frequently associated with dental, periodontal, endodontic, and iatrogenic factors. Accurate identification of the odontogenic source is essential for appropriate treatment planning. Cone-beam computed tomography (CBCT) allows detailed evaluation of the maxillary sinus, adjacent teeth, alveolar bone, and periodontal structures, and may improve the radiologic differentiation of ODS. Materials and Methods: This retrospective observational study analyzed radiologic data from patients evaluated and treated by the authors for suspected odontogenic sinusitis between 2019 and 2026. The final study group included 85 patients with CBCT-based evidence of odontogenic pathology affecting the maxillary sinus. CBCT scans were reviewed to identify tooth-related and treatment-related etiologic factors associated with ODS. Based on the radiologic findings, the authors developed a CBCT-based classification of odontogenic etiologies and proposed an imaging-guided management algorithm. Results: CBCT identified a broad spectrum of odontogenic factors associated with maxillary sinus disease. The most relevant radiologic patterns included endodontic and periapical pathology, periodontal or combined endo-periodontal disease, post-extraction inflammatory changes, odontogenic cysts, oro-antral communication or fistula, retained roots or teeth, displaced endodontic materials, and grafting or implant-related complications. These findings were organized into 16 radiologic categories reflecting the principal etiologic pathways of ODS. The proposed classification facilitated correlation between radiologic presentation and the recommended dental, surgical, and otolaryngologic treatment approach. Conclusions: CBCT is a valuable imaging modality for identifying odontogenic causes of maxillary sinus inflammation and provides more precise diagnostic information than conventional radiography alone. A structured CBCT-based evaluation may improve etiologic diagnosis, support multidisciplinary decision-making, and help guide individualized management of patients with ODS. Full article

The accurate detection of dental caries is often hindered by modality-specific imaging challenges, such as illumination artifacts in intra-oral photographs and low lesion contrast in radiographs. This study proposes a comprehensive framework comprising three key components: (1) HybridAugment+, an entropy-guided adaptive augmentation strategy that applies stronger transformations to low-information images; (2) DBAttNet, a dual-branch attention network featuring illumination–reflection aware attention (IRAA) for photographs and contrast–frequency-aware attention (CFA) for radiographs; and (3) a CAM-based explainability method, selected through a systematic evaluation of five advanced techniques. This study utilized two datasets derived from public sources, comprising 639 intra-oral photographs (481 caries, 158 healthy) and 456 radiographs (268 caries, 188 healthy). These were annotated by two dentists, with established inter-rater reliability (κ = 0.82 for photographs, κ = 0.79 for radiographs). The experimental results demonstrate that HybridAugment+ improved performance over conventional augmentation by up to 8.72% on photographs and 7.67% on radiographs. Furthermore, DBAttNet achieved F1-scores of 97.90% on photographs and 95.72% on radiographs, outperforming ResNet50, InceptionV3, MSDNet, DCANet, and ARM-Net. A comparative evaluation identified XGrad-CAM as the most suitable explainability method, with optimal visualization thresholds of 30% for photographs and 20% for radiographs. Generalization experiments on ophthalmology (APTOS 2019, Messidor-2) and chest radiography datasets (Kermany CXR, NIH ChestX-ray14) demonstrated consistent performance gains over domain-specific methods (DT-Net, ConvNeXt-Tiny). These results confirm that the core design principles effectively transfer to other modalities facing analogous imaging challenges. Full article

Background: Primary teeth play a crucial role in guiding permanent dentition; however, data regarding root apex closure in primary molars remain limited. The aim of this study was to evaluate the age-related root apex closure status of primary second molars in children aged 2–7 years using panoramic radiographs and to obtain clinically guiding data for pediatric dental treatment planning. Materials and Methods: This cross-sectional, descriptive, and retrospective study evaluated panoramic radiographs. A total of 1628 panoramic radiographs obtained from 1628 patients were evaluated, each representing one individual with primary second molars. The relationships between age groups, gender, and root apex closure status were analyzed statistically with a significance level set at p < 0.05. Results: No root apex closure was observed in either maxillary or mandibular primary second molars in the 2–2.99-year age group. In the 3–3.99-year group, a limited number of closed apices were detected only in mandibular primary second molars. A marked increase in the proportion of closed apices was observed in both jaws in the 4–4.99-year group. In the 5–5.99- and 6–6.99-year groups, root apex closure was completed in the majority of maxillary and mandibular primary second molars. Although statistically significant gender-related differences were detected in certain age groups, these differences were not consistent across all age categories. Conclusions: Root apex closure in primary second molars demonstrates a clear age-dependent pattern between 2 and 7 years of age. The findings are expected to provide clinically relevant guidance for pediatric endodontic treatment planning and contribute to the limited literature regarding root development in primary teeth. Full article

Objectives: Oral healthcare and regular dental follow-up are important during pregnancy, as maternal oral health may have important implications for both maternal and fetal well-being. However, dental attendance remains low. Therefore, this cross-sectional e-survey aimed to explore pregnant women’s dental pain management strategies, their perceptions of endodontic treatment, and avoidance of specific endodontic procedures during pregnancy. Methods: An 18-item online questionnaire was administered to 130 pregnant women. Data were collected on dental attendance, experiences of toothache, use of analgesics or antibiotics, and perceptions of the safety of dental anesthesia and radiographic procedures during pregnancy. Statistical analyses were conducted using Chi-square or Fisher’s exact tests and multivariate logistic regression (p < 0.05). Results: The mean age of participants was 32 years. Only 26.15% reported attending regular dental visits during pregnancy. Among participants who experienced toothache, 51.52% used analgesics and 1.54% used antibiotics. Although 92.31% believed dental infections should be treated during pregnancy, concerns regarding dental procedures were common; 76.92% considered dental radiography unsafe and only 50% considered local anesthesia safe. Multivariate analysis showed that the number of pregnancies was associated with dental visits during pregnancy (p = 0.048), age with analgesic use (p = 0.018), and education level with perception of dental radiography safety (p = 0.013). Conclusions: Despite awareness of the importance of treating dental infections, pregnant women may delay endodontic care during pregnancy, highlighting a need for improved patient education and clearer clinical guidance. Full article

This study investigated the radiopacity, elemental composition, cytotoxicity, and cytokine responses of contemporary calcium silicate-based cements containing different radiopacifiers. Four cement materials (NeoMTA2, NeoPUTTY, TheraCal PT, and One-Fil PT) were evaluated. Radiopacity was measured using digital radiography with a 10-step aluminum wedge and expressed in mm Al in accordance with ISO 6876; among three calibration models compared, the quadratic provided the best fit. Elemental composition was analyzed by SEM/EDX. Cytotoxicity was assessed on human dental pulp cells using the MTT assay, and IL-6 and IL-10 levels were quantified by ELISA. One-Fil PT (6.61 mm Al) and NeoPUTTY (6.09 mm Al) showed the highest radiopacity, whereas TheraCal PT (1.61 mm Al) did not meet ISO standards. SEM/EDX revealed tantalum in NeoMTA2 and NeoPUTTY, and zirconium in One-Fil PT and TheraCal PT. NeoPUTTY and NeoMTA2 demonstrated superior cell viability, while One-Fil PT showed the lowest. TheraCal PT and One-Fil PT increased IL-6 expression, whereas NeoPUTTY and NeoMTA2 promoted higher IL-10 levels. Within the limitations of this 24-h in vitro assessment, NeoMTA2 and NeoPUTTY exhibited more favorable short-term cytocompatibility and inflammatory profiles together with adequate radiopacity. These findings require confirmation through long-term in vivo and clinical studies. Full article

Dental developmental anomalies are well documented in clinical veterinary medicine but remain rarely reported in archeological dogs. This study presents a radiologically confirmed case of an unerupted left maxillary canine associated with the absence of an alveolus for the left maxillary first molar and incisors in a dog skull from early medieval Wolin. This study aimed to determine whether the observed absence of teeth resulted from congenital agenesis, developmental arrest, ante-mortem loss, or post-depositional processes. Radiographic examination revealed a fully formed but unerupted canine, while the M¹ region exhibited a smooth bony surface without reactive remodeling, periapical radiolucencies, or signs of ante-mortem tooth loss. Differential diagnosis did not support canine agenesis, ante-mortem loss, or taphonomic damage as primary explanations. The findings most strongly support a congenital or very early developmental origin of the observed alterations. The estimated age of the individual (7–10 years) and the absence of secondary pathological changes suggest that these anomalies did not significantly impair masticatory function. Owing to the single-case nature of the material, broader population-level inferences cannot be made. This case underscores the methodological importance of radiographic imaging in archeological dental research and suggests that alveolar absence should not be automatically equated with impaired survival or poor health in this individual. Full article

Objectives: To evaluate the diagnostic performance of a YOLOv8x-based deep learning model for detecting approximal, occlusal and buccal caries on paediatric panoramic radiographs and to compare its performance with human observers with different levels of clinical experience. Methods: A total of 1526 panoramic radiographs obtained from children aged 5–12 years were retrospectively analysed. Approximal, occlusal, and buccal caries in primary molars were annotated and used to train a YOLOv8x object-detection model. Model performance was evaluated on an independent test set and compared with three human observers: an intern dentist (ID), a novice specialist student (NSS), and an experienced specialist student (ESS). Diagnostic performance was assessed using precision, sensitivity, F1 score, and true positive counts. Results: The YOLOv8x model demonstrated moderate performance in detecting approximal caries (F1 score: 0.576) but showed limited performance for occlusal caries (F1 score: 0.24) and failed to detect buccal caries. The AI model showed lesion-dependent performance. For approximal caries, it performed comparably to ESS observers (p > 0.05) and better than ID (p < 0.001). Performance was poor for buccal caries (p < 0.001), and intermediate for occlusal caries, with no difference from NSS or ESS (p > 0.05) but lower than ID (p < 0.001). Overall, performance was comparable to experienced observers (p > 0.05) and superior to less experienced observers (p < 0.001). Conclusions: The YOLOv8x model achieved diagnostic performance comparable to less experienced clinicians in detecting dental caries on paediatric panoramic radiographs but did not reach expert-level accuracy. These findings suggest that deep learning models may serve as supportive tools in panoramic caries assessment rather than replacements for expert interpretation. Full article

Background and Objectives: Tooth impaction is a common developmental dental anomaly characterized by the failure of eruption within the expected physiological timeframe. Permanent canines represent the second most frequently impacted teeth after third molars and may lead to functional, esthetic, and orthodontic complications. This systematic review aimed to synthesize current evidence regarding the incidence, anatomical distribution, etiological determinants, and diagnostic evaluation of permanent canine impaction. Materials and Methods: A systematic literature search was conducted in PubMed, PubMed Central, and ScienceDirect for studies published between December 2009 and December 2025. Studies reporting prevalence data, anatomical positioning, etiological factors, or imaging characteristics of permanent canine impaction were included. Study selection followed PRISMA 2020 guidelines, and 31 studies were included in the qualitative synthesis. Two independent reviewers screened titles, abstracts, and full texts. Methodological quality was assessed using the Joanna Briggs Institute Critical Appraisal Tools. Results: Thirty-one studies met the inclusion criteria and were included in the qualitative synthesis. The reported prevalence of maxillary canine impaction ranged from 0.97% to 7.10%, while mandibular impaction occurred less frequently. Palatal displacement represented the most common positional pattern. Major etiological factors included retained deciduous canines, dental arch constriction, supernumerary teeth, odontomas, and genetic anomalies such as lateral incisor agenesis. Cone-Beam Computed Tomography (CBCT) demonstrated superior diagnostic accuracy compared with panoramic radiography. Conclusions: Permanent canine impaction is a multifactorial condition predominantly influenced by local anatomical and environmental factors, with genetic predisposition acting as a secondary contributor. Early diagnosis and appropriate imaging assessment are essential to prevent complications such as root resorption and to optimize treatment outcomes. Full article

Background/Objectives: Pulp stones are calcified masses within the dental pulp that may complicate endodontic procedures. Although cone beam computed tomography (CBCT) has been reported to detect pulp stones more frequently than two-dimensional radiography, direct comparisons between digital periapical radiography (DPR) and CBCT, particularly at different voxel sizes, remain limited. This study aimed to compare pulp stone detection rates between DPR and CBCT acquired at two voxel sizes and to evaluate inter-modality agreement using a location-based analysis for pulp stone identification in extracted teeth. Methods: Fifty-two extracted human teeth were examined using DPR and CBCT at voxel sizes of 0.2 mm and 0.1 mm under standardized ex vivo conditions. Pulp stones were evaluated in the coronal and radicular regions using a binary scoring system (presence/absence). Detection rates were compared across imaging modalities, and inter-modality agreement was evaluated using McNemar’s test in the analysis stratified by pulp stone location. Associations between pulp stone detection and age, gender, tooth status, and stone location were explored using chi-square tests. Results: CBCT at 0.1 mm demonstrated the highest detection rate for pulp stones (63.5%), followed by CBCT at 0.2 mm (57.7%) and DPR (50%), with no statistically significant differences among modalities (p > 0.05). Agreement analysis showed that CBCT at 0.2 mm had higher agreement with CBCT at 0.1 mm than DPR, particularly in the coronal region, whereas DPR showed lower agreement in the radicular region. No significant associations were observed between pulp stone detection and age, gender, or tooth status. Conclusions: Under standardized ex vivo conditions, CBCT showed numerically higher pulp stone detection rates than DPR. Location-based agreement analysis indicated greater consistency between CBCT voxel sizes than between CBCT and DPR, particularly in the radicular region. These findings highlight differences in pulp stone detectability across imaging modalities and voxel resolutions and may help explain variability in radiographic detection under controlled conditions. Full article

Background: Dental radiographs are essential for diagnosis and treatment planning in modern dentistry. However, their manual interpretation is time-consuming and subject to variability, highlighting the need for automated tools to improve efficiency and consistency. This study aims to validate ORTHOSEG, a deep learning-based system designed to automate the segmentation of anatomical, pathological, and non-pathological elements in radiographs, including orthopantomograms, bitewings, and periapical images. Methods: ORTHOSEG’s performance was evaluated using a rigorously curated dataset of 150 dental radiographs, including 50 orthopantomograms, 50 bitewings, and 50 periapical images, with manual annotations by expert clinicians serving as the ground truth. The system’s segmentation performance was assessed using standard evaluation metrics, including mean Dice Similarity Coefficient (mDSC) and mean Intersection over Union (mIoU), and inference time was also recorded. Results: The system achieved high accuracy, with mDSC and mIoU values of 0.635 ± 0.233 and 0.576 ± 0.214, respectively. In particular for orthopantomograms, it achieved an mDSC of 0.756 ± 0.174 and an mIoU of 0.684 ± 0.172, surpassing existing benchmarks. Its segmentation capabilities extend to approximately 70 distinct elements, underscoring its comprehensive utility. The system demonstrated efficient computational performance, with processing times of 19.745 ± 3.625 s for orthopantomograms, 8.467 ± 0.903 s for bitewings, and 5.653 ± 0.897 s for periapical radiographs on standard clinical hardware. Conclusions: ORTHOSEG demonstrates efficiency suitable for integration into routine workflows. This study confirms ORTHOSEG’s reliability and potential to improve diagnostic workflows, offering clinicians a valuable tool for faster and more detailed radiograph analysis. Future research will focus on extending validation across diverse clinical scenarios to ensure broader applicability. However, this study has limitations, including the use of a dataset derived from a European population and the absence of usability and clinical workflow evaluation, which should be addressed in future studies. Full article

An association between periodontal disease and comorbid disorders, including gastrointestinal signs, has been reported in cats and investigated in humans, where a bidirectional relationship between oral and gastrointestinal microbiomes exists. A 5-year-old neutered female domestic shorthair cat was presented with a 2-year history of small-bowel diarrhoea. The cat’s appetite was reduced, and coat quality had deteriorated. On examination, the cat was found to have periodontal disease affecting multiple teeth and a matted coat. Biochemistry revealed mild hyperproteinaemia, haematology was unremarkable, cobalamin was normal, folate was elevated, and retroviral testing was negative. Abdominal ultrasound showed diffuse muscularis thickening without other abnormalities, and dental examination and radiography revealed missing teeth, a root remnant, stage 4 periodontal disease, and tooth resorption. Multiple extractions were performed, and multimodal analgesia was provided, including locoregional dental blocks. The cat’s appetite, body condition, energy levels, and coat quality improved after the procedure, and the diarrhoea completely resolved within a month of the procedure without any changes in diet, physical, social environment, or the use of any medications, and did not recur during the following 7 months. This case illustrates the potential role of periodontal disease in the development of gastrointestinal disease and the benefits outside the oral cavity of managing dental disease in cats. Full article

Background: Tooth resorption (TR) is a prevalent dental condition with under-investigated systemic implications, particularly regarding renal health. This study aimed to evaluate renal biomarkers, specifically symmetric dimethylarginine (SDMA), and the association between TR and blood parameters. Methods: Thirty-six cats (24 TR; 12 controls) were evaluated via intraoral radiography and blood analysis. Multivariable logistic regression was performed to identify independent predictors for TR, adjusting for age and sex. Results: Tooth resorption was diagnosed in 66.7% of the cats, predominantly affecting the mandibular first molars (409) and fourth premolars (108). A strong association was identified between TR stages and lesion types (p < 0.001). Cats with TR exhibited significantly higher serum SDMA concentrations (p = 0.011) and significantly lower albumin levels (p < 0.001) compared to controls. Hematological analysis revealed marked leukocytosis and monocytosis (p < 0.001) in the TR group. Most importantly, multivariable logistic regression identified SDMA as a predictor with TR presence (p = 0.012), with each unit increase in SDMA associated with a 3.5-fold increase in the likelihood of having resorptive lesions, independent of age and sex. Conclusions: Our findings regarding the oral-renal axis emphasize that feline TR involves chronic systemic inflammation. Consequently, it should be managed as a condition with measurable systemic impacts rather than merely a localized disease. Full article

Background/Objectives: Extranodal NK/T-cell lymphoma, nasal type (ENKTCL-NT), is a rare and extremely aggressive subtype of non-Hodgkin lymphoma that most frequently involves the nasal cavity and upper aerodigestive tract. Primary isolated oral manifestation is exceptionally uncommon and may mimic odontogenic or infectious diseases, delaying diagnosis. We report a case of ENKTCL-NT presenting initially as a destructive oral lesion without sinonasal involvement at diagnosis. Methods: A 32-year-old man with progressive palatal ulceration underwent clinical and imaging assessment (panoramic radiography and staging ^18F-FDG PET–CT) and repeated biopsies. Diagnosis was established using histopathology (H&E), immunohistochemistry (T-cell markers and cytotoxic profile), EBV detection by EBER in situ hybridization, and T-cell receptor gamma (TCRG) gene rearrangement analysis. Results: The lesion presented as a hemorrhagic, ulcerative palatal destruction covered by pseudomembranous exudate and was complicated by fungal infection, periostitis, and severe dental inflammatory foci, contributing to diagnostic delay. Histopathological examination revealed extensive necrosis with a dense atypical lymphoid infiltrate; angiocentric and angiodestructive growth was identified in one biopsy specimen. Tumor cells expressed T-cell markers (CD2, CD3, CD5, CD7; heterogeneous) and cytotoxic markers (TIA-1) and showed CD30 and CD56 positivity, with EBV positivity confirmed by EBER in situ hybridization. Molecular analysis demonstrated monoclonal TCRG rearrangement, and Ki-67 indicated high proliferative activity. Initial PET–CT demonstrated an intensely FDG-avid, locally invasive lesion without distant organ involvement. The patient was treated with L-asparaginase-based SMILE chemotherapy followed by radiotherapy (50 Gy), achieving marked initial clinical improvement and partial metabolic response; however, systemic relapse subsequently occurred with refractory disease despite salvage therapy and immunotherapy. Conclusions: This case highlights the substantial diagnostic challenge posed by isolated oral extranodal NK/T-cell lymphoma, nasal type, which may closely mimic benign inflammatory or infectious conditions and lead to significant diagnostic delay. Persistent, progressive, or therapy-resistant oral ulcerations should prompt early consideration of hematologic malignancy. Timely biopsy with comprehensive immunophenotyping, EBV testing, and close multidisciplinary collaboration are essential for accurate diagnosis and may contribute to earlier diagnosis and improved patient outcomes in these rare and atypical presentations. Full article

Background: The aim of this study was to develop an artificial intelligence (AI)-based decision support model for evaluating the extraction indication of permanent first molars in pediatric patients using panoramic radiographs, and to investigate the potential contribution of this model to the clinical decision-making process. Methods: This retrospective observational study analyzed 1000 panoramic radiographs obtained from children aged 8–10 years who attended the Clinics of Batman University Faculty of Dentistry for routine dental examination. Among the radiographs meeting the inclusion criteria, a total of 176 panoramic images were selected based on dental maturation assessment using the Demirjian tooth development staging system. Cases in which the permanent second molar was classified as Demirjian stages E–F were labeled as “extraction indication present”, while the remaining stages were labeled as “extraction indication absent”. A balanced dataset was created, consisting of 88 cases in each group. Image features were extracted using Gabor filters and Histogram of Oriented Gradients (HOG). The selected features were analyzed using a Support Vector Machine (SVM) classifier with a radial basis function (RBF) kernel. Model performance was evaluated using accuracy, sensitivity, specificity, F1-score, and area under the receiver operating characteristic curve (ROC–AUC). Results: The proposed Gabor–HOG–SVM-based AI model achieved an overall classification accuracy of 77.78% with an AUC value of 0.77 in distinguishing between “extraction indication present” and “extraction indication absent” cases. For the extraction-indicated group, the sensitivity was 0.81 and the F1-score was 0.79, whereas for the non-indicated group, the sensitivity and F1-score were 0.74 and 0.77, respectively. No statistically significant differences were observed between the groups in terms of age or sex distribution (p > 0.05). Conclusions: This study demonstrates that artificial intelligence-based analysis of panoramic radiographic images can provide an objective and reproducible decision support approach for evaluating extraction indications of permanent first molars in pediatric patients. The proposed model should be considered as an adjunctive tool to reduce observer-dependent variability rather than a replacement for clinical judgment, and its clinical applicability should be further validated through multicenter and multi-parametric studies. Full article