Yazar "Teke, Fatih" seçeneğine göre listele
Listeleniyor 1 - 5 / 5
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Artificial Intelligence-Based Detection and Numbering of Dental Implants on Panoramic Radiographs(Wiley, 2025) Balel, Yunus; Sagtas, Kaan; Teke, Fatih; Kurt, Mehmet AliObjectivesThis study aimed to develop an artificial intelligence (AI)-based deep learning model for the detection and numbering of dental implants in panoramic radiographs. The novelty of this model lies in its ability to both detect and number implants, offering improvements in clinical decision support for dental implantology.Materials and MethodsA retrospective dataset of 32 585 panoramic radiographs, collected from patients at Sivas Cumhuriyet University between 2014 and 2024, was utilized. Two deep-learning models were trained using the YOLOv8 algorithm. The first model classified the regions of the jaw to number the teeth and identify implant regions, while the second model performed implant segmentation. Performance metrics including precision, recall, and F1-score were used to evaluate the model's effectiveness.ResultsThe implant segmentation model achieved a precision of 91.4%, recall of 90.5%, and an F1-score of 93.1%. For the implant-numbering task, precision ranged from 0.94 to 0.981, recall from 0.895 to 0.956, and F1-scores from 0.917 to 0.966 across various jaw regions. The analysis revealed that implants were most frequently located in the maxillary posterior region.ConclusionsThe AI model demonstrated high accuracy in detecting and numbering dental implants in panoramic radiographs. This technology offers the potential to reduce clinicians' workload and improve diagnostic accuracy in dental implantology. Further validation across more diverse datasets is recommended to enhance its clinical applicability.Clinical RelevanceThis AI model could revolutionize dental implant detection and classification, providing fast, objective analyses to support clinical decision-making in dental practices.Öğe Deep Learning-Based Classification on Optical Coherence Tomography Images for Prediction of Retinal Damage(Institute of Electrical and Electronics Engineers Inc., 2024) Teke, Fatih; Kaynar, Oğuz; Görmez, YasinOptical coherence tomography (OCT) imaging has become a valuable tool in the diagnosis and management of various eye diseases. However, the classification of multi-class eye diseases using OCT images can be challenging, especially in the presence of data imbalance where the distribution of samples across different disease classes is uneven. In this study, we explored the effectiveness of the VGG16 and InceptionV3 artificial intelligence models in predicting eye diseases, including Drusen, CNV, and DME, using SD-OCT images with data imbalance. The VGG16 and InceptionV3 models, known for their exceptional performance in image classification tasks, achieved an impressive accuracy of 99%. We employed additional metrics, including precision, recall, and F1-score, to assess the model's performance for each eye disease class. The results revealed a well-balanced performance across all classes, demonstrating the model's ability to accurately predict both majority and minority classes. These findings highlight the potential of the VGG16 and InceptionV3 models as a valuable tool in assisting clinicians in diagnosing and managing multi-class eye diseases based on OCT images, even in the presence of data imbalance. However, further research and validation on larger and diverse datasets are necessary to establish the model's reliability and generalize its use in clinical practice. In conclusion, our study demonstrates the successful application of the VGG16 and InceptionV3 artificial intelligence models in multi-class eye disease prediction using SD-OCT images. The model's ability to handle data imbalance signifies its potential as a valuable tool for clinicians, ultimately leading to improved diagnosis and treatment of eye health conditions. Further research and validation efforts are necessary to establish the model's reliability and suitability for integration into clinical practice. © 2024 IEEE.Öğe Derin öğrenme yöntemleri ile tomografi görüntülerinden kapalı açılı glokom göz hastalığının sınıflandırılması(Sivas Cumhuriyet Üniversitesi, 2024) Teke, Fatih; Kaynar, OğuzBu çalışmada bir derin yapay zekâ modelinin kullanılması yoluyla kapalı açılı glokomun saptanması ve sınıflandırılmasına yeni ve gelişmiş bir yaklaşım sunulmaktadır. Giriş verileri olarak Ön Segment Optik Koherens Tomografi (AS-OCT) görüntülerini kullanarak geliştirilen model, %95'lik yüksek bir genel doğruluk sergilemiştir. Metodoloji, kapalı açılı glokomun yüksek derecede hassasiyetle otomatik olarak tanımlanmasına ve sınıflandırılmasına olanak tanıyan en son teknolojiye sahip derin öğrenme tekniklerinin entegrasyonunu içermektedir. Bu araştırmanın bulguları, oftalmik teşhislerde yapay zekânın uygulanmasına ilişkin giderek artan literatüre katkıda bulunmayı ve oküler patoloji alanında daha iyi klinik karar verme ve hasta sonuçları için umut verici çıkarımlar sunmayı hedeflemektedir. Sınıflandırma için toplamda 1600 adet AS-OCT görüntüsü ile geliştirilen model performans değerleri, peripapiller OCT görüntülerinin, glokomun peripapiller tabaka haritalarında oldukça iyi bir sonuç verdiğini ve glokomun erken safhada yakalanması için kullanılmasını desteklemektedir. Geliştirilen yöntem ile AS-OCT görüntülerinin kapalı açılı glokom tespitinde ve teşhisinde doktorlara yardımcı olması amaçlanmaktadır.Öğe Detection and Classification of Closed Angle Glaucoma Using Optical Coherence Tomography Images(Institute of Electrical and Electronics Engineers Inc., 2023) Teke, Fatih; Kaynar, Oguz; Gormez, YasinGlaucoma is one of the 3 most important optic nerve diseases that cause vision loss in the world. There are 4 types of glaucoma that develops due to the destruction of the optic nerve, and one of them is closed-angle glaucoma. Closed-angle glaucoma causes an increase in intraocular pressure with the obstruction of drainage channels due to age and triggers glaucoma. In this study, disease classification was made using anterior segment optical coherence tomography (AS-OCT) images of closed-angle glaucoma samples. A total of 1200 ASOCT images were trained with convolutional networks for classification. It supports the use of peripapillary OCT images for the early diagnosis of glaucoma, with a test accuracy of 97.5%, which gives a very good result in peripapillary layer maps of glaucoma. With the developed method, AS-OCT images are aimed to help doctors in the detection and diagnosis of glaucoma © 2023 IEEE.Öğe Perceptions of Dentists Towards Artificial Intelligence: Validation of a New Scale(Cumhuriyet University Faculty of Dentistry, 2024) Buldur, Burak; Teke, Fatih; AliKurt, Mehmet; Sagtas, KaanObjective: To enhance the effectiveness and efficiency of using artificial intelligence (AI) in healthcare, it is crucial to comprehend the perceptions of healthcare professionals and individuals regarding AI. This study aimed to: (i) develop and conduct psychometric analyses of a new measurement tool, the AI Perceptions Scale (AIPS); and (ii) identify and compare sub-dimensions of perceptions of AI and its sub-dimensions, specifically in the dental profession. Materials and Methods: The study used a cross-sectional and correlational design involving 543 dentists. The data collection tools used were a socio-demographic form, the AIPS, and the Dental Profession Perceptions Scale (DPPS). Construct validity was assessed using exploratory and confirmatory factor analysis. Multivariate analysis of variance was utilized to test the difference between AIPS scores among groups. Results: The AIPS contained 26 items measured on a 5-point Likert response scale and demonstrated excellent internal and test-retest reliability. Exploratory and confirmatory factor analyses of the AIPS identified six factors that categorized perceptions of AI, including 'Human', 'Security', 'Accessibility', 'Vocational', 'Technology', and 'Cost'. The six-factor solution of the AIPS model demonstrated a good fit for the data. AIPS scores varied depending on gender, working place, occupational experience, the need to use AI, and the frequency of AI use in dental practice. The total AIPS score had the strongest correlation with the "human" factor and the weakest correlation with the "accessibility" factor. Statistically significant correlations were observed between the AIPS score and DPPS total, as well as each of its three sub-scales. Conclusions: This study developed a new scale, the AI Perceptions Scale (AIPS), to evaluate perceptions of AI in healthcare. The perceptions of dentists towards AI were categorized into six distinct factors. The AIPS scale was found to be a reliable and valid measurement tool indicatin that it can be effectivel used in future research. © (2024), (Cumhuriyet University Faculty of Dentistry). All rights reserved.
