Demet Süer Tümen

Prof. Dr. Demet Süer Tümen

Department of Orthodontics, Faculty of Dentistry, Dicle University, Diyarbakır, Turkey (Türkiye)
orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
2 April 2025 in Diagnostics
Verified
Journal Article
Open access
Demet Süer TümenDemet Süer Tümen
Demet Süer Tümen
Mehmet NergizMehmet Nergiz
Mehmet Nergiz
Background/Objectives: Accurate skeletal classification is essential for orthodontic diagnosis. This study evaluates the effectiveness of federated convolutional neural network (CNN) models for skeletal classification using cephalometric images from the ISBI and Dicle datasets. This research aims to evaluate the effectiveness of federated learning (FL) for orthodontic skeletal classification by comparing its performance against centralized learning (CL) and local learning (LL). The objective is to determine whether FL can achieve competitive performance while preserving data privacy and enabling collaborative model training across multiple institutions. Methods: The DenseNet121 model and its augmented versions, incorporating channel attention, spatial attention, squeeze and excitation, and spatial pyramid pooling blocks, are proposed and adapted for the study. Models are evaluated on the ISBI and Dicle datasets using accuracy, sensitivity, and specificity metrics, with performance gains benchmarked across CL, LL, and FL frameworks. Results: Accuracy improvements exceed 26% compared to the baseline model on FL framework. The DenseNet121_SA model, augmented with spatial pyramid pooling blocks, achieves a 20.86% performance gain over LL settings on the ISBI dataset. Similarly, the DenseNet121_SA model, augmented with spatial attention, and DenseNet121_SA_SE model, augmented with spatial attention and squeeze and excitation, obtain 16.58% and 15.22% by not sacrificing performance loss with respect to CL. The inclusion of the Dicle dataset provides additional validation for the models. Conclusions: Federated CNN models exhibit significant promise for orthodontic skeletal classification. These models demonstrate the potential of FL to enhance collaborative model training while preserving data privacy. This approach represents a step forward in leveraging precise orthodontic diagnostics technology by enabling a data-secure collaborative artificial intelligence among various orthodontic clinics.

30 September 2021 in International Dental Research
Verified
Journal Article
Open access
PDF file
Demet Süer TümenDemet Süer Tümen
Demet Süer Tümen
OHOrhan Hamamcı
Orhan Hamamcı
Aim: The aim of this study was to provide intrusion of upper incisors with applying Connecticut Intrusion Arch (CIA) and Miniscrew and to evaluate the dental and skeletal cephalometric effects of these intrusion methods on individuals with deep bite caused by supraocclusion of upper incisors. Methodology: The study includes 40 adults, without making sexual distinction, who have at least 4 mm deep bite caused by supraocclusion of upper incisors. Two study groups each consisting 20 individuals formed as CIA and Miniscrew groups. Skeletal, dental, soft tissue measurements were done on lateral cephalograms and apical root resorption measurements were done on standard periapical radiographs that were taken from upper four incisor teeth. Statistically, Paired Student’s t-test was used in intragroup comparements and independent Student’s t-test was used in the investigation of differences between groups. Nevertheless, the concern of variables that seen as risk factors with the amount of resorption was investigated with Pearson correlation analysis. Results: Successful intrusion of four upper incisor teeth with CIA and Mini screw methods and in-significant difference was determined between two methods. Protrusion of upper and lower incisor teeth decrease in interincisal angle and overbite and increase in overjet was stated by intrusion at both of the methods. The decline of the mesiobuccal cusp of the upper first molar was observed in the CIA method. In soft tissue evaluation, decrease of upper lip length, upper lip thickness and distance of upper and lower lip to the Rickett’s plane was observed. Conclusion: The methods used for intrusion showed to cause similar ratio of root resorption. How to cite this article: Süer Tümen D, Hamamcı O. Comparison of cephalometric changes resulting from different upper incisor intrusion methods. Int Dent Res 2021;11(Suppl.1):177-94. https://doi.org/10.5577/intdentres.2021.vol11.suppl1.26 Linguistic Revision: The English in this manuscript has been checked by at least two professional editors, both native speakers of English.

25 December 2025 in Meandros Medical and Dental Journal
Verified
Journal Article
Closed access
YÜYazgı Ay Ünüvar
Yazgı Ay Ünüvar
ÖÜÖzge Ünlüoğlu
Özge Ünlüoğlu
Demet Süer TümenDemet Süer Tümen
Demet Süer Tümen
EKEmre Köse
Emre Köse
Objective: This retrospective study aimed to evaluate and compare external apical root resorption between patient treated with clear aligners and those treated with fixed orthodontic appliances. Materials and Methods: This retrospective research comprised 40 patients treated at the Department of Orthodontics, Aydın Adnan Menderes University, between 2018 and 2024, and who met the inclusion criteria. Patients were categorized into two groups: clear aligner therapy (13 females, 7 males) and fixed orthodontic treatment (13 females, 7 males). Panoramic radiographs taken before and after treatment were analyzed using the modified classification system developed by Sharpe et al., and root resorption levels were assessed in the incisors, premolars, and molars of both jaws. Results: The average age of the patients was 18.8 ± 5.5 years in the clear aligner group and 15.4 ± 1.8 years in the fixed appliance group. Findings indicated that root resorption was typically mild in the two groups. Although the overall resorption scores were higher in the fixed appliance group, no statistically meaningful differences were detected in tooth-based comparisons (p>0.05). The most pronounced trend was detected in the maxillary lateral incisors (p=0.080). Conclusion: No meaningful difference in root resorption was detected between fixed orthodontic appliances and clear aligners. However, the fixed appliance group showed a slight tendency toward higher resorption. These results suggest that clear aligner therapy may represent a biologically safe alternative to fixed orthodontic treatment. Keywords: Root resorption, clear aligner, orthodontic appliance, panoramic radiography

17 June 2024
Verified
Book Chapter
Closed access
Demet Süer TümenDemet Süer Tümen
Demet Süer Tümen
Artificial intelligence (AI) has emerged as a transformative technology with significant implications across various fields, including orthodontics. This paper explores the multifaceted applications of AI in orthodontics, highlighting its potential to enhance diagnostic accuracy, treatment planning, and patient outcomes. AI technologies, including machine learning (ML) and deep learning, facilitate automated analysis of complex data, aiding in precise diagnosis and efficient treatment strategies. Key applications discussed include AI-assisted patient monitoring, cephalometric analysis, extraction decision-making, prediction of un-erupted teeth sizes, diagnosis of impacted teeth, and bone age determination. The integration of AI in orthodontics promises to improve clinical decision-making, reduce human error, and personalize treatment plans, ultimately leading to better patient care. Despite being in the early stages, AI demonstrates substantial promise in revolutionizing orthodontic practices, paving the way for more accurate, efficient, and predictable treatment outcomes.

18 September 2026 in Scientific Reports
Verified
Journal Article
Open access
PDF file
Demet Süer TümenDemet Süer Tümen
Demet Süer Tümen
ÖÜÖzge Ünlüoğlu
Özge Ünlüoğlu
YÜYazgı Ay Ünüvar
Yazgı Ay Ünüvar
EKEmre Köse
Emre Köse
Alveolar bone characteristics have been suggested as potential contributors to maxillary canine impaction; however, the relationship between trabecular bone microarchitecture and impaction pattern remains unclear. This study aimed to compare alveolar trabecular microarchitecture between impacted and non-impacted sides in unilateral maxillary canine impaction using cone-beam computed tomography (CBCT)-based fractal dimension (FD) analysis and to evaluate its association with impaction pattern. This retrospective observational study included 90 individuals: 45 patients with unilateral impacted maxillary canines and 45 controls. The impaction group was subdivided into palatal (n = 31) and buccal (n = 14) impactions. FD analysis was performed on standardized regions of interest using the box-counting method. A linear mixed-effects model was used to assess the effects of group, side, and their interaction. A significant main effect of group was observed (p < 0.001), whereas no significant effect of side or group × side interaction was detected (p > 0.05). The palatal impaction group demonstrated significantly higher FD values compared with both the buccal impaction and control groups (p < 0.01), while no significant difference was found between the control and buccal impaction groups. These findings indicate that trabecular bone microarchitecture varies according to impaction pattern. The absence of a side effect suggests that palatal impaction is associated with broader maxillary structural characteristics rather than localized adaptations. CBCT-based fractal analysis provides a non-invasive, reproducible approach for assessing trabecular complexity, offering potential insights for individualized orthodontic risk assessment.