Yazar "Abdelkarim, Ahmed Z." seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • Küçük Resim Yok
    Öğe
    Automated Mesiodens Detection with Deep-Learning-Based System Using Cone-Beam Computed Tomography Images
    (Wiley-Hindawi, 2023) Syed, Ali Zakir; Ozen, Duygu Celik; Abdelkarim, Ahmed Z.; Duman, Suayip Burak; Bayrakdar, Ibrahim Sevki; Duman, Sacide; Celik, Ozer
    The detection of mesiodens supernumerary teeth is crucial for appropriate diagnosis and treatment. The study aimed to develop a convolutional neural network (CNN)-based model to automatically detect mesiodens in cone-beam computed tomography images. A datatest of anonymized 851 axial slices of 106 patients' cone-beam images was used to process the artificial intelligence system for the detection and segmentation of mesiodens. The CNN model achieved high performance in mesiodens segmentation with sensitivity, precision, and F1 scores of 1, 0.9072, and 0.9513, respectively. The area under the curve (AUC) was 0.9147, indicating the model's robustness. The proposed model showed promising potential for the automated detection of mesiodens, providing valuable assistance to dentists in accurate diagnosis.
  • Küçük Resim Yok
    Öğe
    Detecting white spot lesions on post-orthodontic oral photographs using deep learning based on the YOLOv5x algorithm: a pilot study
    (Bmc, 2024) Ozsunkar, Pelin Senem; Ozen, Duygu CelIk; Abdelkarim, Ahmed Z.; Duman, Sacide; Ugurlu, Mehmet; Demir, Mehmet Ridvan; Kuleli, Batuhan
    Background Deep learning model trained on a large image dataset, can be used to detect and discriminate targets with similar but not identical appearances. The aim of this study is to evaluate the post-training performance of the CNN-based YOLOv5x algorithm in the detection of white spot lesions in post-orthodontic oral photographs using the limited data available and to make a preliminary study for fully automated models that can be clinically integrated in the future.Methods A total of 435 images in JPG format were uploaded into the CranioCatch labeling software and labeled white spot lesions. The labeled images were resized to 640 x 320 while maintaining their aspect ratio before model training. The labeled images were randomly divided into three groups (Training:349 images (1589 labels), Validation:43 images (181 labels), Test:43 images (215 labels)). YOLOv5x algorithm was used to perform deep learning. The segmentation performance of the tested model was visualized and analyzed using ROC analysis and a confusion matrix. True Positive (TP), False Positive (FP), and False Negative (FN) values were determined.Results Among the test group images, there were 133 TPs, 36 FPs, and 82 FNs. The model's performance metrics include precision, recall, and F1 score values of detecting white spot lesions were 0.786, 0.618, and 0.692. The AUC value obtained from the ROC analysis was 0.712. The mAP value obtained from the Precision-Recall curve graph was 0.425.Conclusions The model's accuracy and sensitivity in detecting white spot lesions remained lower than expected for practical application, but is a promising and acceptable detection rate compared to previous study. The current study provides a preliminary insight to further improved by increasing the dataset for training, and applying modifications to the deep learning algorithm.Clinical revelance Deep learning systems can help clinicians to distinguish white spot lesions that may be missed during visual inspection.
  • Küçük Resim Yok
    Öğe
    Nasopharynx evaluation in children of unilateral cleft palate patients and normal with cone beam computed tomography
    (Sage Publications Ltd, 2023) Temiz, Mustafa; Duman, Suayip Burak; Abdelkarim, Ahmed Z.; Bayrakdar, Ibrahim Sevki; Syed, Ali Z.; Eser, Gozde; Celik Ozen, Duygu
    Objective:This study aimed to examine the morphological characteristics of the nasopharynx in unilateral Cleft lip/palate (CL/P) children and non-cleft children using cone beam computed tomography (CBCT). Methods:A retrospective study consisted of 54 patients, of which 27 patients were unilateral CL/P, remaining 27 patients have no CL/P. Eustachian tubes orifice (ET), Rosenmuller fossa (RF) depth, presence of pharyngeal bursa (PB), the distance of posterior nasal spine (PNS)-pharynx posterior wall were quantitatively evaluated. Results:The main effect of the CL/P groups was found to be effective on RF depth-right (p < 0.001) and RF depth-left (p < 0.001). The interaction effect of gender and CL/P groups was not influential on measurements. The cleft-side main effect was found to be effective on RF depth-left (p < 0.001) and RF depth-right (p = 0002). There was no statistically significant relationship between CL/P groups and the presence of bursa pharyngea. Conclusions:Because it is the most common site of nasopharyngeal carcinoma (NPC), the anatomy of the nasopharynx should be well known in the early diagnosis of NPC.