Yazar "Ozen, Duygu Celik" seçeneğine göre listele
Listeleniyor 1 - 14 / 14
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Automated Mesiodens Detection with Deep-Learning-Based System Using Cone-Beam Computed Tomography Images(Wiley-Hindawi, 2023) Syed, Ali Zakir; Ozen, Duygu Celik; Abdelkarim, Ahmed Z.; Duman, Suayip Burak; Bayrakdar, Ibrahim Sevki; Duman, Sacide; Celik, OzerThe detection of mesiodens supernumerary teeth is crucial for appropriate diagnosis and treatment. The study aimed to develop a convolutional neural network (CNN)-based model to automatically detect mesiodens in cone-beam computed tomography images. A datatest of anonymized 851 axial slices of 106 patients' cone-beam images was used to process the artificial intelligence system for the detection and segmentation of mesiodens. The CNN model achieved high performance in mesiodens segmentation with sensitivity, precision, and F1 scores of 1, 0.9072, and 0.9513, respectively. The area under the curve (AUC) was 0.9147, indicating the model's robustness. The proposed model showed promising potential for the automated detection of mesiodens, providing valuable assistance to dentists in accurate diagnosis.Öğe Automatic maxillary sinus segmentation and pathology classification on cone-beam computed tomographic images using deep learning(Bmc, 2024) Altun, Oguzhan; Ozen, Duygu Celik; Duman, Suayip Burak; Dedeoglu, Numan; Bayrakdar, Ibrahim Sevki; Eser, Gozde; Celik, OzerBackgroundMaxillofacial complex automated segmentation could alternative traditional segmentation methods to increase the effectiveness of virtual workloads. The use of DL systems in the detection of maxillary sinus and pathologies will both facilitate the work of physicians and be a support mechanism before the planned surgeries.ObjectiveThe aim was to use a modified You Only Look Oncev5x (YOLOv5x) architecture with transfer learning capabilities to segment both maxillary sinuses and maxillary sinus diseases on Cone-Beam Computed Tomographic (CBCT) images.MethodsData set consists of 307 anonymised CBCT images of patients (173 women and 134 males) obtained from the radiology archive of the Department of Oral and Maxillofacial Radiology. Bilateral maxillary sinuses CBCT scans were used to identify mucous retention cysts (MRC), mucosal thickenings (MT), total and partial opacifications, and healthy maxillary sinuses without any radiological features.ResultsRecall, precision and F1 score values for total maxillary sinus segmentation were 1, 0.985 and 0.992, respectively; 1, 0.931 and 0.964 for healthy maxillary sinus segmentation; 0.858, 0.923 and 0.889 for MT segmentation; 0.977, 0.877 and 0.924 for MRC segmentation; 1, 0.942 and 0.970 for sinusitis segmentation.ConclusionThis study demonstrates that maxillary sinuses can be segmented, and maxillary sinus diseases can be accurately detected using the AI model.Öğe Comparative Evaluation of Temporomandibular Joint Parameters in Unilateral and Bilateral Cleft Lip and Palate Patients Using Cone-Beam CT: Focus on Growing vs. Non-Growing Subjects(Mdpi, 2024) Abdelkarim, Ahmed Z.; Almeshari, Ahmed A.; Ozen, Duygu Celik; Khalifa, Ayman R.; Rezallah, Nader N.; Duman, Suayip Burak; Khurana, SonamBackground: Morphological differences in the temporomandibular joint (TMJ) are crucial for the treatment of patients with cleft lip and palate (CLP). This study aims to evaluate and compare the TMJ parameters in patients with unilateral and bilateral CLP across growing and non-growing age groups using cone-beam computed tomography (CBCT). Methods: CBCT records from 57 patients (23 males and 34 females) aged 6-50 years with a diagnosed unilateral or bilateral CLP were analyzed. Patients were categorized into four groups: growing unilateral (UGCLP), growing bilateral (BGCLP), non-growing unilateral (UNGCLP), and non-growing bilateral (BNGCLP). Measurements of TMJ parameters, including the mandibular fossa, articular eminence inclination, joint spaces, and roof thickness of the glenoid fossa, were conducted using CBCT images. Results: Significant differences were observed in the anterior joint space (AJS) and the roof of the glenoid fossa (RGF) between growing and non-growing unilateral cleft patients. Additionally, significant discrepancies were found in the articular eminence angle when comparing the cleft and non-cleft sides within the unilateral growing group. No significant differences were observed in TMJ parameters between the right and left sides among bilateral cleft patients. Conclusions: The study highlights distinct TMJ morphological differences between growing and non-growing patients with CLP, emphasizing the importance of age-specific considerations in the treatment planning and growth monitoring of these patients.Öğe Comparison of stimulated and unstimulated salivary gland parenchyma using fractal analysis of ultrasonographic images(Springer, 2025) Dedeoglu, Numan; Altun, Oguzhan; Ozen, Duygu Celik; Eser, GozdeObjective To compare the fractal analysis data of ultrasonography (USG) images of the submandibular and parotid glands before and after parenchymal stimulation to assess for any changes. Methods The study was conducted by taking 240 USG images of bilateral parotid and submandibular glands of 30 patients before and after stimulation. Patients chewed gum for stimulating their salivary glands. Fractal analysis was performed on the USG images, and the data obtained were statistically compared. Results The fractal analysis value of the USG images of the parotid gland was 1.45, both before and after stimulation, indicating no statistically significant difference (p = 0.866). In the submandibular gland, this value was the same before and after stimulation (fractal analysis = 1.42), showing no statistically significant difference (p = 0.748). Parotid and submandibular glands were compared. USG fractal analysis values before and after stimulation and the overall values were statistically significantly different between the different salivary glands (p < 0.05). Conclusion According to fractal analysis, there was no change in the parenchyma of the submandibular and parotid glands despite the stimulation. Submandibular and parotid glands could be distinguished by fractal analysis.Öğe Convolutional Neural Network Performance for Sella Turcica Segmentation and Classification Using CBCT Images(Mdpi, 2022) Duman, Suayip Burak; Syed, Ali Z.; Ozen, Duygu Celik; Bayrakdar, Ibrahim Sevki; Salehi, Hassan S.; Abdelkarim, Ahmed; Celik, OzerThe present study aims to validate the diagnostic performance and evaluate the reliability of an artificial intelligence system based on the convolutional neural network method for the morphological classification of sella turcica in CBCT (cone-beam computed tomography) images. In this retrospective study, sella segmentation and classification models (CranioCatch, Eskisehir, Turkiye) were applied to sagittal slices of CBCT images, using PyTorch supported by U-Net and TensorFlow 1, and we implemented the GoogleNet Inception V3 algorithm. The AI models achieved successful results for sella turcica segmentation of CBCT images based on the deep learning models. The sensitivity, precision, and F-measure values were 1.0, 1.0, and 1.0, respectively, for segmentation of sella turcica in sagittal slices of CBCT images. The sensitivity, precision, accuracy, and F1-score were 1.0, 0.95, 0.98, and 0.84, respectively, for sella-turcica-flattened classification; 0.95, 0.83, 0.92, and 0.88, respectively, for sella-turcica-oval classification; 0.75, 0.94, 0.90, and 0.83, respectively, for sella-turcica-round classification. It is predicted that detecting anatomical landmarks with orthodontic importance, such as the sella point, with artificial intelligence algorithms will save time for orthodontists and facilitate diagnosis.Öğe Five-year change of panoramic radiomorphometric indices and fractal dimension values in type 2 diabetes patients(Springer, 2024) Dedeoglu, Numan; Eser, Gozde; Ozen, Duygu Celik; Altun, OguzhanObjectivesDiabetes mellitus is a chronic disease characterized by dysregulation of glucose metabolism, with characteristic long-term complications accompanied by changes in bone quality. The purpose of this study is to compare the results with a control group by performing radiomorphometric analyses on panoramic radiographs obtained 5 years apart to examine changes in the mandibular bone cortex and microstructures of type 2 diabetes mellitus (T2DM) patients.MethodsTwo panoramic radiographs that were taken 5 years (mean 5.26 +/- 0.134) apart from 52 patients with T2DM (n:26) and a control group (n:26) were used. A total of 104 images were evaluated. Analyses were done from the condyle (FD1), angulus (FD2), distal second premolar apex (FD3), and anterior to the mental foramen (FD4) for fractal dimension (FD) in the mandible. Symphysis index (SI), anterior index (AI), molar index (MI), posterior index (PI), and panoramic mandibular index (PMI) measurements were taken for cortical analysis. Three-way ANOVA, three-way robust ANOVA, two-way ANOVA, and two-way robust ANOVA tests were used for statistical analysis (p < 0.05).ResultsAfter a 5-year period, there was a significant decrease in all FD measures of the mandible in both T2DM and control groups (p < 0.05). This resulted in a statistical difference in the main effect of time. After a 5-year period, no significant difference in mandibular cortical measures was identified between the T2DM and control groups (p > 0.05).ConclusionAccording to panoramic radiography, the mandibular trabecular structure deteriorated after 5 years, whereas cortical values remained the same. It concluded that T2DM had no effect on these results.Öğe In-vitro Diagnosis of Approximal Caries in Teeth Periapical Radiography with Different Exposure Parameters(Pera Yayincilik Hizmetleri, 2023) Altun, Oguzhan; Ozen, Duygu Celik; Dedeoglu, Numan; Duman, Suayip Burak; Eser, Gozde; Topaloglu, Edanur; Ozemre, BegumObjective: The aim of this study was to evaluate periapical radiographs of enamel caries, dentin caries, and deep caries with exposed pulp and intact teeth obtained in vitro using photo-stimulated phosphor plates (PSP) under different exposure parameters. Methods: 3 non-carious extracted molars were selected. The obtained molars were embedded in the wax created from pink wax by ensuring approximal contact and a base was created. 14 different imaging protocols were used with 60 kVp, 4 mA 0.02-0.1 second and 70 kVp 7 mA, 0.25-1.25 second exposure parameters. Intact teeth were imaged with these various imaging protocols. Artificial cavities were then created for enamel caries, dentin caries and deep caries with exposed pulp and imaged according to the same protocols. The images were evaluated by 3 clinicians who were blind to the exposure protocol and caries status. Inter-observer agreement with actual situations was examined with Kappa statistics. Results: In the low-dose group, the kappa values of observer 1, observer 2, and observer 3 were 0.905, 0.952, 0.952, respectively. The kappa values of observer 1, observer 2, and observer 3 in the ultralow-dose group were 0.833, 1, 1, and the kappa values of observer 1, observer 2, and observer 3 in the high-dose group were 1, 1, 0.833, respectively. The results obtained in all groups showed a statistically significant-excellent agreement (p<0.001). Conclusion: Approximal caries can be diagnosed with intraoral radiography obtained with low radiation doses with PSP in dentistry. Thus, patients could be exposed to less ionizing radiation.Öğe Introduction to Large Language Models and the Application of Generative Artifical Intelligence in Dental Education and Clinical Practice(W.B. Saunders, 2026) Syed, Ali; Duman, Suayip Burak; Ozen, Duygu Celik; Bayrakdar, Ibrahim Sevki; Mupparapu, Mel[No abstract available]Öğe Investigation of the Effect of Unilateral Maxillary Sinus Hypoplasia on Temporomandibular Joint Morphology(Pera Yayincilik Hizmetleri, 2026) Ozemre, Begum; Duman, Suayip Burak; Ozen, Duygu Celik; Altun, OguzhanObjective: Maxillary sinus hypoplasia is frequently discovered by accident and is typically asymptomatic. This study aims to assess how temporomandibular joint (TMJ) morphology is affected by unilateral maxillary sinus hypoplasia. Methods: For this study, cone beam computed tomography (CBCT) images in the radiology archive of the Department of Oral, Dental, and Maxillofacial Radiology, Faculty of Dentistry, & Idot;n & ouml;n & uuml; University, were retrospectively reviewed. The study included 77 patients (51 female, 26 male) aged 18-73 years with unilateral maxillary sinus hypoplasia. The patients' articular eminence angles, glenoid fossa root thickness, joint spaces, ramus lengths, condyle sizes, and condyle shapes were evaluated and compared bilaterally. Results: Condylar dimensions, joint spaces, articular eminence inclinations, glenoid fossa roof thickness, ramus length, and condyle shape did not significantly differ (p>0.05) between the hypoplastic and normal maxillary sinus sides. Conclusion: The study's findings show that maxillary sinus hypoplasia has no discernible impact on TMJ morphology; hence, this anatomical variation does not result in appreciable morphological alterations in the joint structure.Öğe Morphometric and morphological evaluation of mastoid emissary canal using cone-beam computed tomography(Sage Publications Ltd, 2023) Temiz, Mustafa; Ozen, Duygu Celik; Duman, Suayip Burak; Bayrakdar, Ibrahim Sevki; Kazan, Orhan; Jagtap, Rohan; Altun, OguzhanObjectives:This study aimed to determine mastoid emissary canal's (MEC) and mastoid foramen (MF) prevalence and morphometric characteristics on cone-beam computed tomography (CBCT) images to underline its clinical significance and discuss its surgical consequences. Methods:In the retrospective analysis, two oral and maxillofacial radiologists analyzed the CBCT images of 135 patients (270 sides). The biggest MF and MEC were measured in the images evaluated in MultiPlanar Reconstruction (MPR) views. The MF and MEC mean diameters were calculated. The mastoid foramina number was recorded. The prevalence of MF was studied according to gender and side of the patient. Results:The overall prevalence of MEC and MF was 119 (88.1%). The prevalence of MEC and MF is 55.5% in females and 44.5% in males. MEC and MF were identified as bilateral in 80 patients (67.20%) and unilateral in 39 patients (32.80%). The mean diameter of MF was 2.4 +/- 0.9 mm. The mean height of MF was 2.3 +/- 0.9. The mean diameter of the MEC was 2.1 +/- 0.8, and the mean height of the MEC was 2.1 +/- 0.8. There is a statistical difference between the genders (p = 0.043) in foramen diameter. Males had a significantly larger mean diameter of MF in comparison to females. Conclusion:MEC and MF must be evaluated thoroughly if the surgery is contemplated. Radiologists and surgeons should be aware of mastoid emissary canal morphology, variations, clinical relevance, and surgical consequences while operating in the suboccipital and mastoid areas to avoid unexpected and catastrophic complications. CBCT may be a reliable imaging diagnostic technique.Öğe Prelacrimal recess morphology in unilateral cleft lip and palate: A cone-beam computed tomography study with surgical implications(Churchill Livingstone, 2025) Cetiner, Yunus; Ozen, Duygu Celik; Duman, Suayip BurakCleft lip and palate(CLP) is a deformity that affects the anatomical structure of the nose and the maxillary sinus (MS). In the management of MS pathologies, the prelacrimal recess approach(PLRA), a minimally invasive technique within endoscopic sinus surgery, holds significant importance. This study aims to evaluate the morphometric characteristics of the nasolacrimal duct(NLD) and the prelacrimal recess(PLR), as well as the feasibility of the prelacrimal recess approach(PLRA), in patients with unilateral cleft lip and palate(UCLP) using cone-beam computed tomography(CBCT). CBCT images of both the cleft and non-cleft sides of 60 patients with UCLP were retrospectively analyzed. Morphometric measurements related to the anatomy of the NLD and the PLR were performed and statistically compared.In these patients, the mediolateral diameter of the NLD was found to be significantly narrower on the cleft side(5.10 f 1.29 mm) compared to the non-cleft side(5.74 f 1.28 mm)(p = 0.03). The mediolateral thickness of the PLR was also significantly thinner on the cleft side(1.89 f 1.46 mm) than on the non-cleft side(2.91 f 1.95 mm)(p = 0.01). However, no significant difference was observed in the anteroposterior length of the PLR between the cleft side(5.08 f 2.54 mm) and the non-cleft side (4.64 f 2.67 mm)(p = 0.35).The prelacrimal recess and nasolacrimal canal on the cleft side may be affected in patients with UCLP. CBCT serves as a valuable tool in identifying these anatomical variations, which are frequently associated with congenital deformities such as UCLP and should be carefully considered during surgical planning.Öğe Radiographic Data Segmentation as a Tool in Machine Learning and Deep Learning Artificial Intelligence Algorithms(W.B. Saunders, 2026) Syed, Ali Z.; Ozen, Duygu Celik; Duman, Suayip Burak; Bayrakdar, Ibrahim Sevki; Mupparapu, Mel[No abstract available]Öğe Second mesiobuccal canal segmentation with YOLOv5 architecture using cone beam computed tomography images(Springer, 2024) Duman, Suayip Burak; Ozen, Duygu Celik; Bayrakdar, Ibrahim Sevki; Baydar, Oguzhan; Abu Alhaija, Elham S.; Yigit, Dilek Helvacioglu; Celik, OezerThe objective of this study is to use a deep-learning model based on CNN architecture to detect the second mesiobuccal (MB2) canals, which are seen as a variation in maxillary molars root canals. In the current study, 922 axial sections from 153 patients' cone beam computed tomography (CBCT) images were used. The segmentation method was employed to identify the MB2 canals in maxillary molars that had not previously had endodontic treatment. Labeled images were divided into training (80%), validation (10%) and testing (10%) groups. The artificial intelligence (AI) model was trained using the You Only Look Once v5 (YOLOv5x) architecture with 500 epochs and a learning rate of 0.01. Confusion matrix and receiver-operating characteristic (ROC) analysis were used in the statistical evaluation of the results. The sensitivity of the MB2 canal segmentation model was 0.92, the precision was 0.83, and the F1 score value was 0.87. The area under the curve (AUC) in the ROC graph of the model was 0.84. The mAP value at 0.5 inter-over union (IoU) was found as 0.88. The deep-learning algorithm used showed a high success in the detection of the MB2 canal. The success of the endodontic treatment can be increased and clinicians' time can be preserved using the newly created artificial intelligence-based models to identify variations in root canal anatomy before the treatment.Öğe Segmentation of Cemento-Osseous Dysplasias Using an Artificial Intelligence Algorithm(Elsevier, 2026) Ozen, Duygu Celik; Altun, Oguzhan; Duman, Suayip Burak; Bayrakdar, Ibrahim SevkiIntroduction and Aims: In recent years, artificial intelligence (AI) has emerged as a powerful tool in medical imaging and in the analysis of complex bone pathologies such as cementoosseous dysplasias. The aim of this study is to perform segmentation of cemento-osseous lesions using AI algorithms on cone beam computed tomography (CBCT) images and to evaluate the diagnostic performance of a diagnostic AI model designed for the diagnosis of cemento-osseous dysplasias. Methods: In this study, cone beam computed tomography (CBCT) images taken for various reasons in radiology archive Department of Oral and Maxillofacial Radiology were retrospectively reviewed. As a result of radiographic evaluation, images recorded in the archive with at diagnosis of cemento-osseous dysplasias were determined. Fifty DICOM images were uploaded to the 3D slicer software, and cemento-osseous dysplasias were polygonally labeled and saved in Neuroimaging Informatics Technology Initiative (NIfTI) format. The nnU-Net v2-based automated algorithm for lesion segmentation was developed using the CranioCatch (CranioCatch, Eski,sehir) software program using the PyTorch library in the Python framework (v3.6.1; Python Software Foundation). 80% of the data was used for training, 10% for validation and 10% for testing. The results were evaluated according to the criteria of precision, sensitivity, Dice Coefficient, Jaccard Index. Results: The precision, sensitivity, Dice Coefficient and Jaccard Index for the segmentation of cemento-osseous dysplasias were 0.805, 0.889, 0.839, and 0.730, respectively. Conclusions: The model we used achieved successful results in cemento-osseous dysplasias segments. The results of this planned study are promising in terms of providing a guidance for physicians in diagnosis. Clinical Relevance: Automated segmentation of cemento-osseous lesions, where radiological images play a critical role in both diagnosis and follow-up, has the potential to enable precise and consistent definition of lesion boundaries and standardize the follow-up process, enabling more reliable data for long-term studies. (c) 2025 The Authors. Published by Elsevier Inc. on behalf of FDI World Dental Federation. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/)
