Yazar "Kizilay, Fatma Nur" seçeneğine göre listele

Listeleniyor 1 - 4 / 4
  • Küçük Resim Yok
    Öğe
    Deep learning-based 3D automatic segmentation of impacted canines in CBCT scans
    (Bmc, 2025) Unal, Turkan; Kuran, Alican; Gulsen, Ibrahim Tevfik; Kizilay, Fatma Nur; Gulsen, Emine; Ozudogru, Semanur; Gordeli, Kadir
    BackgroundImpacted canines are one of the most frequently encountered dental anomalies in maxillofacial practice. Accurate localization of these teeth is crucial for treatment planning, and Cone Beam Computed Tomography (CBCT) offers detailed 3D imaging for this purpose. However, manual segmentation on CBCT scans is time-consuming and subject to inter-observer variability. This study aimed to develop a deep learning model based on nnU-Net v2 for the automatic segmentation of impacted canines and to evaluate its performance using both classification and segmentation metrics.MethodsA total of 159 CBCT scans containing impacted canines were retrospectively collected and annotated using web-based segmentation software. Model training was performed using the nnU-Net v2 architecture with a learning rate of 0.00001 for 1000 epochs. The performance of the model was evaluated using recall and precision. In addition, segmentation performance was assessed using Dice Similarity Coefficient (DSC), 95% Hausdorff Distance (95% HD in mm), and Intersection over Union (IoU).ResultsThe nnU-Net v2 model achieved high performance in the detection and segmentation of impacted canines. The values obtained for recall and precision 0.90 and 0.82, respectively. The segmentation metrics were also favorable, with a DSC of 0.84, 95% HD of 7.07 mm, and IoU of 0.74, indicating good overlap between predicted and reference segmentations.ConclusionsThe results suggest that the nnU-Net v2-based deep learning model can effectively and autonomously segment impacted canines in CBCT volumes. Its strong performance highlights the potential of artificial intelligence to improve diagnostic efficiency in dentomaxillofacial radiology.
  • Küçük Resim Yok
    Öğe
    Development of a YOLOv8-based deep learning model for detecting and segmenting dental restorations and dental applications in panoramic radiographs of mixed dentition
    (Springernature, 2025) Kuran, Alican; Gulsen, Ibrahim Tevfik; Kizilay, Fatma Nur; Gulsen, Emine; Asar, Mustafa Enes; Ozudogru, Semanur; Unal, Turkan
    Background The objective of this study was to develop a deep learning (DL) model for the detection and segmentation of six types of dental restorations and applications in panoramic radiographs of paediatric patients with mixed dentition.Material and methods A total of 2,033 panoramic radiographs were labelled for six different dental restorations. The dataset was divided into three parts: 80% for training, 10% for validation, and 10% for testing. The YOLOv8 model was trained for 500 epochs with a learning rate of 0.01. The success of the model was evaluated using sensitivity, precision and F1 score metrics.Results The YOLOv8 multiclass-DL model achieved high performance, with an overall F1 score of 0.89, supported by a sensitivity of 0.85 and precision of 0.93. Among the evaluated restoration types, dental fillings achieved the highest F1-score of 0.97, followed by stainless steel crowns with 0.94, space maintainers with 0.93, pulpotomies with 0.90, and root canal fillings with 0.84. The lowest performance was observed in the detection of dental brackets, which reached an F1-score of only 0.46.Conclusion YOLOv8-based DL models demonstrate a high level of success in detecting and segmenting dental restorations in panoramic radiographs of patients in the mixed dentition period.
  • Küçük Resim Yok
    Öğe
    Fabricated modified compomer bearing CF/SBA-15 nanomaterials: Physicochemical and antibacterial properties
    (Elsevier Sci Ltd, 2026) Kizilay, Fatma Nur; Aydinbelge, Mustafa; Demirbuga, Sezer; Kolcakoglu, Kevser; Ildiz, Nilay; Dayan, Serkan
    Objectives While compomers are widely used in pediatric dentistry, their antibacterial potential and fluoride release remain limited. This study aimed to evaluate the antibacterial and mechanical properties of compomers modified with different concentrations of calcium fructoborate-loaded mesoporous silica (CF@SBA-15) nanoparticles. Methods CF was synthesized via the Miljkovi & cacute; method and loaded into SBA-15. The resulting CF@SBA-15 nanomaterial was incorporated into a compomer at 0.5 % (Group 1) and 1.0 % (Group 2) by weight. Surface roughness, microhardness, and degree of conversion (DC) were evaluated. Characterization was performed using FT-IR, SEM-EDX, and TGA analyses. Boron release was quantified at 1, 24, 72, and 96 h using ICP-MS. Antibacterial activity against Streptococcus mutans and Lactobacillus casei was assessed by the direct contact test (DCT). Statistical significance was set at p < 0.05. Results Surface roughness and microhardness values increased significantly with higher CF@SBA-15 concentrations (p < 0.001), with Group 2 exhibiting the highest mean values. DC was significantly higher in both experimental groups than in the control (p = 0.009). Boron release demonstrated a progressive, concentration-dependent pattern, with Group 2 showing greater cumulative release (p = 0.009). Both nanoparticle-modified groups exhibited significantly stronger antibacterial effects compared with the control (p < 0.01). Conclusions Incorporating CF@SBA-15 nanoparticles into compomers enhanced antibacterial efficacy while preserving the essential physicochemical integrity of the material.
  • Küçük Resim Yok
    Öğe
    Prenatal hormonal signature (2D:4D) and dental maturation in childhood: a prospective study
    (Elsevier Ireland Ltd, 2025) Unal, Turkan; Kizilay, Fatma Nur; Gulsen, Emine
    Background The second-to-fourth digit ratio (2D:4D) is a stable anthropometric marker thought to reflect prenatal androgen-estrogen balance. Although 2D:4D has been linked to developmental timing, its association with dental maturation remains unclear. This study evaluated whether 2D:4D relates to dental development in children and assessed its potential as a complementary biomarker. Methods In this study, 300 healthy children (150 girls, 150 boys; 6-12 years) were enrolled. Bilateral 2D:4D was measured with digital calipers (0.01 mm accuracy). Dental age was determined from panoramic radiographs using Demirjian's method. Analyses included t-tests/ANOVA, Pearson correlations, and multiple linear regression with chronological age, sex, body mass index (BMI), and 2D:4D as covariates. Hand-specific and sex-stratified comparisons were pre-specified; multiple testing was controlled using the Benjamini-Hochberg false-discovery rate (FDR) procedure, with significance set at q < 0.05 (false discovery rate-adjusted p-value). Results Mean chronological age was 9.10 +/- 1.99 years, dental age 9.09 +/- 2.03 years, and BMI 16.51 +/- 1.89 kg/m(2). 2D:4D showed clear sex differences (higher in girls, p < 0.001). Chronological and dental ages were strongly correlated (r = 0.976, p < 0.001). In the overall sample, dental age correlated weakly with 2D:4D (right: r = 0.155, p = 0.007; left: r = 0.135, p = 0.019). Sex-stratified analyses indicated a positive but non-significant trend in girls (right: r = 0.135, p = 0.099; left: r = 0.110, p = 0.181) and no association in boys (all p > 0.05). In multivariable models, chronological age was the strongest predictor (p < 0.001); 2D:4D contributed independently (beta = 0.12-0.16, p < 0.001), while BMI was not significant. Conclusions 2D:4D shows a weak association with dental maturation at the population level. Within-sex analyses reveal a non-significant positive trend in girls and no association in boys. As a simple, non-invasive measure, 2D:4D may provide supportive information alongside radiographic methods; confirmation in larger, longitudinal, sex-specific cohorts is warranted.