Browsing by Author "Bayrakdar, Ibrahim Sevki"

Now showing 1 - 2 of 2

A Deep Learning Approach for Detecting Periapical Lesions on Panoramic Radiographic Images
(College of Physicians & Surgeons Pakistan, 2025) Pekiner, Mert Yagiz; Yulek, Hakan; Talmac, Ayse Gul Oner; Keser, Gaye; Pekiner, Filiz Namdar; Bayrakdar, Ibrahim Sevki
Objective: To assess the performance of a deep learning method for detecting the segmentation of periapical lesions on dental panoramic radiographs. Methodology: The deep learning model, YOLOv5, based on the YOLO algorithm for periapical lesion segmentation, was further developed using 1,500 anonymised panoramic radiographs. The radiographs were obtained from the Radiology Archive at the aforementioned University. For apical lesion segmentation, YOLOv5 with the PyTorch model was utilised. The dataset was divided into training (n = 1,200 radiographs / 2,628 labels), validation (150 radiographs / 325 labels), and test (n = 150 radiographs / 368 labels) sets. The model's effectiveness was measured using the confusion matrix. Sensitivity (recall), precision, and F1 scores provided quantitative assessments of the model's predictive capabilities. Results: The sensitivity, precision, and F1 score performance values of the YOLOv5 deep learning algorithm were 0.682, 0.784, and 0.729, respectively. Conclusion: Periapical lesions on panoramic radiography can be reliably identified using deep learning algorithms. Dental healthcare is being revolutionised by artificial intelligence and deep learning methods, which are advantageous to both the system and practitioners. While the current YOLO-based system yields encouraging findings, additional data should be gathered in future research to improve detection outcomes.
Artificial Intelligence-Assisted Detection of Soft Tissue Calcifications and Ossifications in CBCT
(Elsevier Inc., 2026) Cin, Lokman; Duman Tepe, Rabia; Cansiz, Erol; Özcan, Ilknur; Bayrakdar, Ibrahim Sevki; Cakir Karabas, Hulya
Objectives This study aimed to integrate soft tissue calcifications and ossifications (STCO) detected on cone beam computed tomography (CBCT) into an artificial intelligence (AI) system and assess its diagnostic accuracy in both single-class and multi-class classification. Study Design CBCT images from 287 patients were retrospectively reviewed. STCOs were identified in axial, coronal, and sagittal planes, with segmentation performed in the axial plane. The AI model was trained to detect arterial calcifications, phleboliths, tonsilloliths, styloid ligament ossification, osteoma cutis, antroliths, laryngeal cartilage calcifications, sialoliths, lymph node calcifications, and rhinoliths as well as a single combined class. Data were split into training (80%), testing (10%), and validation (10%) sets, and performance was evaluated using sensitivity, precision, and F1-score. Results In the single-class model, sensitivity, precision, and F1-score were 0.98, 0.91, and 0.94, respectively. In the multi-class model, these values were 0.88, 0.80, and 0.84. Conclusion The AI system achieved high accuracy in detecting STCOs, with superior results in single-class classification. AI-assisted CBCT evaluation may improve diagnostic efficiency, facilitate multidisciplinary collaboration, and support clinical decision-making. © 2025 Elsevier Inc.