IGIbrahim Tevfik Gulsen

Ibrahim Tevfik Gulsen

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Ibrahim Tevfik Gulsen has a total of 37 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • The role of prenatal factors in molar incisor hypomineralization: Could the 2D:4D ratio be a biomarker?

    by Emine Gülşen, Türkan Ünal, Fatma Nur Kızılay, İbRahim Tevfik Gülşen

  • Open Access

    Deep learning detection of ectopic canines and molars in mixed dentition

    by Emine Gülşen, Fatma Nur Kızılay, Enes Mustafa Aşar, İbRahim Tevfik Gülşen, Semanur Özüdoğru, Türkan Ünal, Alican Kuran, Bayram Kendigelen, Mehmet Uğurlu, İbRahim Şevki Bayrakdar, et al.

    Ectopic eruption (EE) during the mixed dentition is a significant dental anomaly that requires early detection to prevent complications that may impact function, aesthetics, and health. Advances in artificial intelligence point to the need for automated methods to detect ectopic canines and molars. This study aimed to develop a DL model to automatically detect EE of canines and molars on panoramic radiographs. This retrospective study utilised a dataset of panoramic radiographs from pediatric patients in the mixed dentition stage. EE of canines and molars was defined using angular and positional criteria. Images were annotated by calibrated specialists and divided into training, validation, and test sets. Performance was evaluated using precision, recall, F1-score, Dice coefficient, and mean average precision (mAP). For ectopic canines, precision was 0.786, recall 0.771, F1-score 0.778, Dice coefficient 0.768, and mAP 0.793. For ectopic molars, precision was 0.812, recall 0.650, F1-score 0.722, Dice coefficient 0.757, and mAP 0.719. These results indicate more consistent detection performance for ectopic canines than for molars. DL demonstrated effective diagnostic capability for detecting EE on panoramic radiographs. This tool has potential to improve early diagnosis, support pediatric dental treatment planning, and enhance radiology education.


  • Open Access

    Comparison of Play Dough and Bread Dough with Ballistic Gel as Soft Tissue Simulator: An Ex-Vivo Study with Sheep’s Head as the Gold Standard

    by Tansu Çimen, Yunus Yiğit Saka, İbRahim Tevfik Gülşen, Mehmet Numan Köse, Samed Satır

    Objective: This study aims to test the usability of bread dough, play dough, and ballistic gel in soft tissue simulations by comparing them with a sheep’s head as the gold standard. Cone beam computed tomography (CBCT) images of the sheep’s head was obtained as the gold standard. Methods: The sheep’s head was re-covered with ballistic gel, play dough, and bread dough, respectively. Two different CBCT images (protocol A – FOV: 8 × 15 cm, 90 kVp, 6.3 mA, 4.5 s, 0.35 mm voxel size, 574 mGy·cm²; protocol B – FOV: 13 × 15 cm, 90 kVp, 5 mA, 8.1 s, 0.30 mm voxel size, 823 mGy·cm²) were obtained from the gold standard and each simulation model. The Hounsfield unit (HU) feature in the software of the CBCT was used to evaluate gray values. Pearson Correlation Coefficient was used to examine the relationship between variables that comply with normal distribution, and Spearman’s rho Correlation Coefficient was used to examine the relationship between variables that do not comply with normal distribution. The significance level was taken as p < 0.05. Results: The highest positively significant correlation with the gold standard in the mandible was with bread dough (r = 0.944, p < 0.001), while in the maxilla it was with play dough (r = 0.879, p < 0.001). The highest positive significant correlation with the gold standard in gray values selected from teeth and bone was with ballistic gel (r = 0.762, p = 0.004; r = 0.638, p = 0.008, respectively), while in pulp it was with play dough (r = 0.874, p < 0.001). A very high, positive, and significant correlation was found between protocols A and B of all simulation models. The highest positive significant correlation of the gold standard protocol A was found with the ballistic gel simulation protocol B (r = 0.893, p < 0.001). Conclusion: Play-dough can be an alternative soft tissue simulator to ballistic gel, especially in ex vivo studies on pulp morphology.


  • Open Access

    Clinical management of epidermolysis bullosa: case reports of five siblings

    by Э. Гюльсен, C. O. Sariyldiz, İ. T. Gülşen, D. A. Maharani, M. Goncharuk-Khomyn, İ. Yavuz, M. Callea, C. Yavuz, Д. О. Сарийылдыз, И. Т. Гюльсен, et al.

    INTRODUCTION. Epidermolysis bullosa (EB) is a rare, inherited disorder characterized by mucocutaneous fragility, leading to blistering and ulceration following minimal trauma. Among its major subtypes, EB simplex (EBS) is the most common, typically presenting with milder clinical manifestations. AIM. This case series aims to document the clinical and radiographic findings of five siblings diagnosed with EBS, emphasizing the role of dental professionals in diagnosis, management, and improving patient quality of life. MATERIALS AND METHODS. Five siblings with no prior EB diagnosis underwent clinical, radiographic, and genetic assessments. Intraoral and extraoral examinations were conducted to evaluate mucosal involvement, dental anomalies, and associated systemic manifestations. Genetic analysis confirmed EBS Type 2 (KRT5 mutation) in all cases. RESULTS. None of the cases exhibited significant oral mucosal bullae or erosions. However, hyperkeratotic lesions, nail dystrophy, and perioral bullous formations were observed in all patients. Two siblings presented with bilateral sensorineural hearing loss. Panoramic radiographs revealed missing teeth, likely due to cariesrelated extractions, highlighting challenges in oral hygiene maintenance. Dental management focused on atraumatic treatment approaches, preventive care, and dietary counseling. CONCLUSIONS. Dentists play a crucial role in the early detection and multidisciplinary management of EB. Comprehensive oral assessments can aid in subtype identification and guide tailored treatment strategies. Patient education, preventive measures, and regular follow-ups are essential to improving long-term oral health outcomes and overall quality of life for individuals with EB.

  • Open Access

    A bibliometric analysis of the literature from the past to the present on the use of artificial intelligence in orthodontics and orthognathic surgery

    by İbRahim Tevfik Gülşen, Ruşen Erdem, Yavuz Selim Genç, Emine Gülşen

    Aims: This study aims to investigate the publication characteristics of academic work centred around artificial intelligence (AI) in orthodontics and orthognathic surgery in detail. Methods: In this analysis, the VOSviewer software and the Bibliometrix Biblioshiny R-package were employed for the purposes of bibliometric investigation and data visualisation. Results: Between 1991 and 2024, 842 articles were published, averaging 12.33 citations per article. China topped the list with 200 articles, succeeded by the U.S. with 183 and South Korea with 121. Seoul National University authored the highest number of publications (47), succeeded by Peking University (36) and the University of North Carolina (34). Seoul National University (807) and the Catholic University of Leuven (567) ranked highest in citation impact. Jacobs Reinhilde was the most prolific author, with 22 publications, and alongside Dinggang Shen and Adriaan Van Gerven, had the greatest citation counts of 544, 491, and 476, respectively. The most used keywords were “artificial intelligence,” “deep learning,” “machine learning,” “orthodontics,” “convolutional neural network,” “orthognathic surgery,” “dentistry,” “cephalometry,” “CBCT,” and “cephalometric analysis.” Conclusion: This bibliometric analysis illustrates that AI has swiftly become an expanding research subject in orthodontics and orthognathic surgery, attracting considerable interest from the scientific community. The thorough investigation indicates that AI is essential, especially in cephalometric evaluations, diagnostic procedures, and treatment strategies.

  • Open Access

    A bibliometric analysis of the literature on the use of artificial intelligence in pediatric dentistry

    by Emine Gülşen, İbRahim Tevfik Gülşen, Turkan Mahyaddinova

    Aims: This study aims to conduct a bibliometric analysis of the scientific literature on the use of artificial intelligence (AI) in pediatric dentistry to evaluate publication trends, citation impact, key contributors, and research themes. Methods: A comprehensive literature search was conducted in the Web of Science (WoS) database up to February 8, 2025. The search included AI-related terms combined with pediatric dentistry keywords. A total of 78 relevant articles were identified and analyzed. VOSviewer software was used for bibliometric mapping, including co-authorship, co-citation, and keyword analysis. Results: The number of publications on AI in pediatric dentistry has increased significantly since 2020, peaking in 2024, followed by a decline in 2025. The analysis identified key research topics, including diagnostic imaging, early childhood caries detection, dental age estimation, and orthodontic assessments. Despite the growth in research output, AI applications in pediatric dentistry remain significantly underdeveloped compared to other dental fields. Citation impact was relatively low, with the most referenced article receiving 83 citations. Conclusion: AI is gaining attention in pediatric dentistry; however, its adoption is still in the early stages. Further research is needed to validate AI models, enhance clinical integration, and expand interdisciplinary collaboration. Addressing data limitations and improving real-world applicability will be crucial for AI’s long-term impact on pediatric dental care.


  • Open Access

    Utilization of artificial intelligence in pediatric dentistry: a comprehensive literature review

    by Emine Gülşen, İbRahim Tevfik Gülşen

    Artificial intelligence (AI) refers to the creation of computer systems capable of performing tasks that typically necessitate human intelligence. Several dental specializations, such as pediatric dentistry, increasingly utilize artificial intelligence and its components, including machine learning and deep learning. The advancement of AI in healthcare is associated with the development of AI applications designed to assist medical practitioners in diagnosing patients and determining optimal treatment strategies. Artificial Intelligence refers to the ability of machines to acquire knowledge and utilize that information to perform various cognitive functions, such as language processing, learning, reasoning, and decision-making—essentially emulating human behavior. This article provides an overview of the various applications of AI that are advantageous to pediatric dentistry.


  • Open Access

    The application of ultrasonography to the masticatory system: A bibliometric analysis

    by İbRahim Tevfik Gülşen, Ruşen Erdem, Yavuz Selim Genç, Emine Gülşen

    Aim: This review aimed to summarize the current knowledge on ultrasound use in the masticatory system and establish a scientific foundation for future research. Methods: A literature search of the Web of Science database was completed in August 2024, following preliminary scans and searches conducted before August 2, 2024, to refine the approach. A total of 205 studies were included in the meta-analysis. Bibliometric analysis and data visualization were performed using VOSviewer and the R package Bibliometrix (Biblioshiny). Results: The first study on this topic was published in 1991. The highest number of publications and citations occurred in 2023. Turkey was the top producer of articles, whereas Japan had the greatest impact. The Universidade Estadual de Campinas published the most papers, and the Academic Center for Dentistry, Amsterdam, was the most cited institution. Stavros Kiliaridis emerged as the most prolific author, and Oral Surgery, Oral Medicine, Oral Pathology and Oral Radiology (OOOO Journal) was the most productive journal. Conclusions: This study conducted a comprehensive bibliometric analysis and visualization of research on ultrasound use in the masticatory system using literature from the Web of Science Core Collection database covering 1991 to 2024. The current focal areas and future research avenues were identified. This research also clarified the historical foundations and prevailing trends in ultrasound application within this field, offering a nuanced perspective for scholars.

  • Open Access

    A Bibliometric Analysis of the Field of Artificial Intelligence in Cariology

    by İbrahim Tevfik Gülşen, Ruşen Erdem, Yavuz Selim Genç, Gülbeddin Yalınız

    Background: The aim of this study is to examine the development trends and dynamics of research on the use of artificial intelligence in dental caries diagnosis, to identify the strengths and limitations of the existing literature, and to guide future research. Methods: A literature search was conducted using the Web of Science database, covering articles published before 3 June 2024. Pilot searches were conducted and 883 studies were reached. After the specified scanning and filtering processes, the study was carried out on 270 publications. In the bibliometric analysis, the Biblioshiny R package as well as the features of Web of Science and VOSviewer software were used for visualizations. Microsoft Excel was used to tabulate the data. Results: There is a general increase in the number of articles published each year. A total of 3081 citations were made to publications on the use of artificial intelligence in cariology. The average number of citations per article was found to be 11.41, and the H index was 29. The most cited country was Germany (581 citations), and the most influential author was Falk Schwendicke. On the basis of institutions, the highest contribution was made by Charite University Medicine Berlin (19 articles, 475 citations). Conclusion: Since 2008, and particularly since 2018, the utilisation of artificial intelligence (AI) in the investigation of dental caries and oral and dental diseases has garnered increasing interest. Artificial Intelligence (AI) can be said to be a groundbreaking discovery that will be increasingly applied in various branches of dentistry.

  • Open Access

    Artificial intelligence system for automatic maxillary sinus segmentation on cone beam computed tomography images

    by Ibrahim Sevki Bayrakdar, Nermin Sameh Elfayome, Reham Ashraf Hussien, Ibrahim Tevfik Gulsen, Alican Kuran, Ihsan Gunes, Alwaleed Al-Badr, Ozer Celik, Kaan Orhan

    Objectives: The study aims to develop an artificial intelligence (AI) model based on nnU-Net v2 for automatic maxillary sinus (MS) segmentation in cone beam computed tomography (CBCT) volumes and to evaluate the performance of this model. Methods: In 101 CBCT scans, MS were annotated using the CranioCatch labelling software (Eskisehir, Turkey) The dataset was divided into 3 parts: 80 CBCT scans for training the model, 11 CBCT scans for model validation, and 10 CBCT scans for testing the model. The model training was conducted using the nnU-Net v2 deep learning model with a learning rate of 0.00001 for 1000 epochs. The performance of the model to automatically segment the MS on CBCT scans was assessed by several parameters, including F1-score, accuracy, sensitivity, precision, area under curve (AUC), Dice coefficient (DC), 95% Hausdorff distance (95% HD), and Intersection over Union (IoU) values. Results: F1-score, accuracy, sensitivity, precision values were found to be 0.96, 0.99, 0.96, 0.96, respectively for the successful segmentation of maxillary sinus in CBCT images. AUC, DC, 95% HD, IoU values were 0.97, 0.96, 1.19, 0.93, respectively. Conclusions: Models based on nnU-Net v2 demonstrate the ability to segment the MS autonomously and accurately in CBCT images.