Person: NAMDAR PEKİNER, FİLİZ MEDİHA
Loading...
Email Address
Birth Date
Research Projects
Organizational Units
Job Title
Last Name
NAMDAR PEKİNER
First Name
FİLİZ MEDİHA
Name
16 results
Search Results
Now showing 1 - 10 of 16
Publication Metadata only A deep learning apprroach to detection of oral cancer lesions from intra oral patient images(2023-10-07) KESER, GAYE; NAMDAR PEKİNER, FİLİZ MEDİHA; KESER G., NAMDAR PEKİNER F. M., BAYRAKDAR İ. Ş., ÇELİK Ö., ORHAN K.Publication Metadata only Assessment of oral mucosal diseases in patients applying to a faculty of dentistry(2023-11-10) KESER, GAYE; NAMDAR PEKİNER, FİLİZ MEDİHA; Yülek H., KESER G., NAMDAR PEKİNER F. M.Publication Metadata only Kronik travma sonucu gelişen skuamöz hücreli karsinom: Olgu sunumu(2023-10-07) ÜNAL, SUAY YAĞMUR; KESER, GAYE; NAMDAR PEKİNER, FİLİZ MEDİHA; ÜNAL S. Y., KESER G., NAMDAR PEKİNER F. M.Publication Open Access Accuracy of Dental and Chronological Age Estimation in A Sample Turkish Caucasion Children: Comparison of Demirjian’s and Willems Methods(2023-09-01) NAMDAR PEKİNER, FİLİZ MEDİHA; İzgi E., Namdar Pekiner F. M.Objective: The purpose of this study is to apply Demirjian’s and Willems’ methodologies and to define whether there are any discrepancies in predicting dental age versus chronological age in a sample Turkish Caucasian children. Methods: A total of 150 Turkish Caucasian children with known chronological age and gender were chosen. The chronological age was determined by subtracting the date of birth from the date of the radiograph, and it was expressed as a number with two decimal places. Each age group was determined to have a minimum sample size of 12 and a maximum sample size of 27. All panoramic radiographs were scored according to the criteria of Demirjian’s and Willems methodologies with Onyx Ceph 3.1.54 software. Results: The dental ages of the cases ranged from 4.82 to 15.66 years calculated by the Demirjian’s method, with an average of 9.47±2.27 years, while the Willems method of the cases ranged from 4.13 to 14.34 years calculated by the Demirjian’s method, with an average of 8.87±2.24 years. According to Demirjian’s method, in the developmental evaluation of dental age, 45.3% of boys were found to have a statistically higher chronological age than girls (p<.05), while no statistically significant difference was found between dental age and chronological age in developmental evaluation according to Willems method (p>.05). Conclusion: The Willems method was shown to be more accurate in determining dental age in Turkish children. Further studies on large population groups and diverse ethnicities are required to increase the reliability and repeatability of the results. Keywords: Dental age, chronological age, Demirjian’s method, Willems methodPublication Metadata only Oral squamous cell carcinoma of buccal mucosa: a case report(2023-10-07) KESER, GAYE; NAMDAR PEKİNER, FİLİZ MEDİHA; Yülek H., KESER G., NAMDAR PEKİNER F. M., OLGAÇ N. V.Publication Metadata only Ağız tabanı mukozası ve hastalıkları(İstanbul Medikal Yayıncılık, 2022-08-01) NAMDAR PEKİNER, FİLİZ MEDİHA; Namdar Pekiner F. M.Publication Metadata only KAYSERİ MAHKEMELER VEZNESİ - Kayseri 2. Tüketici Mahkemesi-2020/382 Esas-FİLİZ MEDİHA NAMDAR PEKİNER(2023-06-01) NAMDAR PEKİNER, FİLİZ MEDİHA; Namdar Pekiner F. M.Publication Open Access Plaut-vincent stomatitis: A case report(2023-12-01) ÜNAL, SUAY YAĞMUR; KESER, GAYE; NAMDAR PEKİNER, FİLİZ MEDİHA; Ünal S. Y., Keser G., Namdar Pekiner F. M.Necrotizing ulcerative stomatitis or Plaut-Vincent’s Stomatitis is a complication of necrotizing ulcerative gingivitis that extends beyond the gingiva and is involved in other parts of the oral mucosa, with Fusiform bacillus, Borrelia vincenti and other anaerobic microorganisms being the most common associated bacteria. It starts with sore throat, bad smell in the mouth, bleeding gums in young adults with poor oral hygiene and decreased immune resistance. In this case, clinical findings of Plaut-Vincent Stomatitis belonging to a male patient are presented. In a 22-yearold male patient, erythematous, ulcers with irregular margins and grayish-white fibrin were observed in the soft tissue of the right third molar region of the mandible and in the buccal mucosa. The patient has halitosis, difficulty in swallowing, pain in the oropharynx, and lymphadenopathy. In the treatment of infected tissues, improvement was observed after systemic antibiotics and hydrogen peroxide mouthwash were applied for 6-7 days. PlautVincent Stomatitis is frequently seen in young adults and poor oral hygiene, smoking, emotional stress, alcohol consumption and malnutrition are stated as etiological factors that predispose to this disease. Detection of ulcerated lesions in soft tissue examination is important in diagnosis and treatment.Publication Open Access A deep learning approach to automatic tooth detection and numbering in panoramic radiographs: An artificial intelligence study(2023-12-01) KESER, GAYE; NAMDAR PEKİNER, FİLİZ MEDİHA; MERTOĞLU D., KESER G., BAYRAKDAR İ. Ş., NAMDAR PEKİNER F. M., ÇELİK Ö., ORHAN K.Objective: n this study, in order to test the usability of artificial intelligence technologies in dentistry, which are becoming widespread and expanding day by day, and to investigate ways to benefit more from artificial intelligence technologies; a tooth detection and numbering study was performed on panoramic radiographs using a deep learning software. Methods: A radiographic dataset containing 200 anonymous panoramic radiographs collected from individuals over the age of 18 was assessed in this retrospective investigation. The images were separated into three groups: training (80%), validation (10%), and test (10%), and tooth numbering was performed with the DCNN artificial intelligence software. Results: The D-CNN system has been successful in detecting and numbering teeth. of teeth. The predicted precision, sensitivity, and F1 score were 0.996 (98.0%), 0.980 (98.0%), and 0.988 (98.8%), respectively. Conclusion: The precision, sensitivity and F1 scores obtained in our study were found to be high, as 0.996 (98.0%), 0.980 (98.0%) and 0.988 (98.8%), respectively. Although the current algorithm based on Faster R-CNN shows promising results, future studies should be done by increasing the number of data for better tooth detection and numbering results.Publication Open Access A deep learning algorithm for classification of oral lichen planus lesions from photographic images: a retrospective study(2023-02-01) NAMDAR PEKİNER, FİLİZ MEDİHA; KESER, GAYE; Keser G., Bayrakdar İ. Ş., Namdar Pekiner F. M., Çelik Ö., Orhan K.IntroductionDeep learning methods have recently been applied for the processing of medical images, and they have shown promise in a variety of applications. This study aimed to develop a deep learning approach for identifying oral lichen planus lesions using photographic images.Material and MethodsAnonymous retrospective photographic images of buccal mucosa with 65 healthy and 72 oral lichen planus lesions were identified using the CranioCatch program (CranioCatch, Eskişehir, Turkey). All images were re-checked and verified by Oral Medicine and Maxillofacial Radiology experts. This data set was divided into training (n =51; n=58), verification (n =7; n=7), and test (n =7; n=7) sets for healthy mucosa and mucosa with the oral lichen planus lesion, respectively. In the study, an artificial intelligence model was developed using Google Inception V3 architecture implemented with Tensorflow, which is a deep learning approach.ResultsAI deep learning model provided the classification of all test images for both healthy and diseased mucosa with a 100% success rate.ConclusionIn the healthcare business, AI offers a wide range of uses and applications. The increased effort increased complexity of the job, and probable doctor fatigue may jeopardize diagnostic abilities and results. Artificial intelligence (AI) components in imaging equipment would lessen this effort and increase efficiency. They can also detect oral lesions and have access to more data than their human counterparts. Our preliminary findings show that deep learning has the potential to handle this significant challenge.