Akademik Veri Yönetim Sistemi
Quintessence international (Berlin, Germany : 1985), cilt.0, sa.0, 2023 (SCI-Expanded)
Objectives: This study aimed to develop an artificial intelligence (AI) model that can able automatic tooth numbering, frenulum attachments, gingival overgrowth areas, and gingival inflammation signs on intraoral photographs and to evaluate the performance of this model. Method and materials: A total of 654 intraoral photographs were used in the study (n=654). All photographs were reviewed by 3 periodontists, and all teeth, frenulum attachment, gingival overgrowth areas, and gingival inflammation signs on photographs were labeled using the segmentation method in a web-based labeling software. In addition, tooth numbering was carried out according to the FDI system. An AI model was developed with the help of YOLOv5x architecture with labels of 16795 teeth, 2493 frenulum attachments, 1211 gingival overgrowth areas, and 2956 gingival inflammation signs. The confusion matrix system and ROC analysis were used to statistically evaluate the success of the developed model. Results: The sensitivity, precision, F1 score, and AUC for tooth numbering were found as 0.990, 0.784, 0.875, and 0.989; were found as 0.894, 0.775, 0.830, and 0.827 for frenulum attachment; were found as 0.757, 0.675, 0.714, and 0.774 for gingival overgrowth area, and were found as 0.737, 0.823, 0.777, and 0.802 for gingival inflammation sign, respectively. Conclusion: The results of the present study have shown that AI systems can be successfully used to interpret intraoral photographs. These systems have the potential to accelerate the digital transformation in the clinical and academic functioning of dentistry with the automatic determination of anatomical structures and dental conditions from intraoral photographs