Sultan Uzun

Sultan Uzun

Auto-generated profile, based on publicly available information

Sultan Uzun

Department of Oral and Maxillofacial Radiology, Faculty of Dentistry, Bilecik Şeyh Edebali University, Bilecik, Turkey

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 April 2023 in European Annals of Dental Sciences
Verified
Journal Article
Closed access
AAAli Altındağ
Ali Altındağ
SUSultan Uzun
Sultan Uzun
IBIBRAHIM SEVKI BAYRAKDAR
IBRAHIM SEVKI BAYRAKDAR
ÖÇÖzer Çeli̇k
Özer Çeli̇k
Purpose: This study aims to examine the diagnostic performance of detecting pulp stones with a deep learning model on bite-wing radiographs. Material and Methods: 2203 radiographs were scanned retrospectively. 1745 pulp stones were marked on 1269 bite-wing radiographs with the CranioCatch labeling program (CranioCatch, Eskişehir, Turkey) in patients over 16 years old after the consensus of two experts of Maxillofacial Radiologists. This dataset was divided into 3 grou as training (n = 1017 (1396 labels), validation (n = 126 (174 labels)) and test (n = 126) (175 labels) sets, respectively. The deep learning model was developed using Mask R-CNN architecture. A confusion matrix was used to evaluate the success of the model. Results: The results of precision, sensitivity, and F1 obtained using the Mask R-CNN architecture in the test dataset were found to be 0.9115, 0.8879, and 0.8995, respectively. Discussion- Conclusion: Deep learning algorithms can detect pulp stones. With this, clinicians can use software systems based on artificial intelligence as a diagnostic support system. Mask R-CNN architecture can be used for pulp stone detection with approximately 90% sensitivity. The larger data sets increase the accuracy of deep learning systems. More studies are needed to increase the success rates of deep learning models.

18 December 2024 in BMC Oral Health
Verified
Journal Article
Open access
PDF file
GMGuldane Magat
Guldane Magat
SUSultan Uzun
Sultan Uzun
Knowledge of root and canal morphology is a prerequisite for effective nonsurgical and surgical endodontic treatments. The aim of this cone beam computed tomography (CBCT) study was to evaluate the root canal morphology of permanent canines in a Turkish subpopulation using two classification systems. A total of 2,000 canine teeth were examined. The number of roots was identified, and root canal configurations were classified according to Vertucci’s classification and a new system for classifying root and canal morphology. Fisher’s exact test was used for statistical analysis, and the level of significance was set at 0.05 (p = 0.05). The canal configuration type I was the most common in all canines, while type III was the second most common. According to the new system, the code 1C1−1 was the most common, whilst 1C1 (A1) codes were the second most common for all canines. In this study, more than 10% morphology that did not fit the Vertucci classification was detected. In the categorization of accessory canals based on the new classification, the most common type in all canines was 1C1,1 (A1). Age had an effect only on the morphology of the left maxillary canine (p < 0.05). Canines in the Turkish subpopulation showed a relatively high degree of variation in root and canal anatomical variations. Clinicians should be aware of where canals converge or diverge to avoid missing canals. The new system for classifying canal morphology describes root and canal configurations more accurately and practically compared to the Vertucci classification.

29 April 2026 in BMC Medical Education
Verified
Journal Article
Open access
AAAli Altındağ
Ali Altındağ
SUSultan Uzun
Sultan Uzun
ÖAÖmer Altındağ
Ömer Altındağ
KOKaan Orhan
Kaan Orhan
Applications of artificial intelligence (AI) in medicine and dentistry have been increasing in recent years. Understanding the educational readiness, learning needs, and perceptions of AI among dental students and professionals is essential for curriculum development. This study aimed to evaluate the level of knowledge, sources of information, attitudes, and educational preparedness regarding AI among dental students’ and dentists. A cross-sectional, anonymous online survey was conducted among 501 participants (332 females, 169 males), including undergraduate dental students, postgraduate/doctoral students, and practicing dentists. The 28-item questionnaire assessed demographics, AI knowledge, attitudes toward AI, and views on AI education. Descriptive statistics were used to summarize the data; Mann–Whitney U, Kruskal–Wallis, and chi-square tests were applied for group comparisons, while binary logistic regression and Spearman correlation analyses were used to examine predictors and associations related to AI learning and curriculum support. More than half of the participants (53.7%) reported only superficial knowledge of AI, while 4.8% reported no knowledge. Formal university-based education was the primary source of AI information for only 3% of respondents, whereas social media constituted the main source for 64.7%. Despite limited structured educational exposure, attitudes toward AI were predominantly positive. Over 70% of participants agreed that AI should be included as an educational component supporting diagnostic reasoning and learning processes, while agreement with statements suggesting that AI would replace dentists within the next 30 years was low. Significant differences in AI perceptions were observed according to age and gender (p ≤ 0.001), whereas professional experience showed limited influence on overall attitudes. Willingness to learn and apply AI-based systems was moderately correlated with perceived clinical benefit (ρ = 0.524, p < 0.001) and the perceived need to integrate AI into dental education (ρ = 0.553, p < 0.001). Despite limited formal education, dental professionals view AI as a supportive tool rather than a replacement. Given that social media was the primary source of AI information while formal university-based education was minimal, these findings highlight a clear need for structured curricular integration. These findings necessitate the integration of AI literacy into both university curricula and lifelong learning frameworks to ensure professional continuity. The online version contains supplementary material available at 10.1186/s12909-026-09264-x.

29 December 2024 in Clinical and Experimental Health Sciences
Verified
Journal Article
Closed access
GMGuldane Magat
Guldane Magat
SUSultan Uzun
Sultan Uzun
Objectives: The objective of this study is to assess condyle morphology through panoramic radiographs and investigate the impact of variables such as bruxism, age, gender, education level, chewing habits, and income level on the morphology of the condyle. Methods: Condyle morphology was assessed across four categories (bird's beak, diagonal diamond, crooked fingers, and oval) in panoramic radiographs featuring 200 patients in this study. Bruxism, age, gender, education level, chewing habits, and income level were classified based on the responses provided in the questionnaires by the individuals in the study. Results: Among the 100 bruxist patients, 3 exhibited awake, 41 displayed sleep, and 56 manifested both awake and sleep bruxism. Significant differences were observed in the morphology of the left condyle (p < .05). In the 26-40 age group, there was an increase in the appearance of bird's beak, diagonal diamond, and crooked fingers, while the oval condyle's appearance decreased (p < .05). Males showed a greater prevalence of bird beak appearance (p < .05). A rise in education level correlated with increased occurrences of bird beak, diagonal diamond, and crooked finger appearances (p < .05). In the presence of bruxism, there was a statistically higher prevalence of bird's beak and diagonal diamond-shaped condyles (p < .05). Conclusion: The outcomes of this study on condyle morphology are influenced by bruxism, age, gender, and education level. Individuals experiencing both awake and sleep bruxism exhibit a more pronounced impact on condyle morphology. To ascertain a genuine causal relationship, prospective cohort studies are imperative.

21 April 2025 in BMC Oral Health
Verified
Journal Article
Open access
PDF file
SUSultan Uzun
Sultan Uzun
ZBZehra Irem Ozturk Barut
Zehra Irem Ozturk Barut
BEBuket Eren
Buket Eren
GMGuldane Magat
Guldane Magat
MKMehmet Hakan Kurt
Mehmet Hakan Kurt
The aim of this study is to investigate the effects of different occlusion types based on the Eichner classification index on the quantitative features of the masseter muscle by using USG and to evaluate whether these features differ according to age and gender in Turkish subpopulation. The thickness and elasticity values of the masseter muscle were performed. Images were acquired bilaterally in the resting position and maximum intercuspidation. The significance level was set as p = 0.05. Measurements of 120 people showed that the thickness of the right masseter muscle was lower in women compared to men, both when relaxed and when contracted. The thickness of the left masseter muscle was also lower in women when it was contracted. This difference is significant (P < 0.01). The thickness of the right and left masseter muscles at rest in individuals aged 55 and over was significantly less than those in the 18–35 age range (P < 0.01). The thicknesses of the right and left masseter muscles at rest were lower in individuals in the Eichner C3 category, while in the contracted state, they were lower in individuals in the B3 and B4 categories. Clinicians should consider these variations in demographic and dental status when designing dental and orthodontic interventions. Taking these factors into account can improve chewing ability and customize treatments better, which may lead to better results for patients of different backgrounds. Clinical trial number: Not applicable.

12 November 2025 in Frontiers in Physiology
Verified
Journal Article
Open access
PDF file
SUSultan Uzun
Sultan Uzun
GMGuldane Magat
Guldane Magat
CECengiz Evli
Cengiz Evli
Introduction: Accurate evaluation of the spheno-occipital synchondrosis (SOS) is important for growth assessment, early detection of craniofacial anomalies, and reliable forensic age estimation. Methods: This study applied three deep learning models—YOLOv5, YOLOv8, and YOLOv11—to cone-beam computed tomography (CBCT) sagittal images from 1,661 individuals aged 6–25 years, aiming to automate SOS fusion stage classification. Model performance was compared in terms of detection accuracy and processing speed. Results: All models achieved high accuracy, with a mean average precision (mAP) of 0.995 in complete fusion (Stage 3). YOLOv8 demonstrated the most consistent balance of precision and recall, while YOLOv11 achieved the fastest inference time (27 ms). YOLOv5 excelled in specific stages with perfect F1-scores. Discussion: These findings demonstrate that YOLO-based AI models can provide precise, rapid, and reproducible SOS assessments, offering valuable support for both clinical decision-making and forensic investigations.