Yurdakurban Ebru, Bayırlı Ali Batuhan, Uytun Mehmetcan, Suçeken Öznur, Karasoy Onur, Özkaraca Osman, Topsakal Kübra Gülnur
Faculty of Dentistry, Department of Orthodontics, Muğla Sıtkı Koçman University, Muğla, Turkey.
Faculty of Dentistry, Department of Periodontology, Muğla Sıtkı Koçman University, Muğla, Turkey.
Clin Oral Investig. 2025 Jun 2;29(6):328. doi: 10.1007/s00784-025-06410-5.
The aim of this study was to develop convolutional neural network (CNN)-based systems to diagnose calculus, plaque, gingival hyperplasia and gingival inflammation in intraoral images from orthodontic patients.
A dataset of 1,000 lateral and frontal intraoral images from orthodontic patients was used to develop CNN-based models. Periodontology specialists annotated areas of dental calculus, plaque, gingival inflammation, and gingival hyperplasia on the teeth and gingiva. The dataset was divided into training (80%), validation (10%), and test (10%) sets for model development. The YOLOv8 and hybrid U-Net + ResNet50 models were examined. Their performance was evaluated on the basis of accuracy, precision, recall, F score, Tversky loss, intersection over union, mean average precision, Dice coefficient, and Cohen's kappa.
The mean classification accuracy was 0.96 for the YOLOv8 model and 0.93 for the U-Net + ResNet50 model. On the basis of the Dice coefficient, the models performed best in detecting gingival hyperplasia (YOLOv8: 0.78, U-Net + ResNet50: 0.79) and worst in detecting dental calculus (YOLOv8:0.48, U-Net + ResNet50:0.53). Cohen's kappa coefficient was highest for classifying gingival hyperplasia (YOLOv8: 0.785, U-Net + ResNet50: 0.790). The precision exceeded 0.72 across all the classifications, with the greatest precision in classifying gingival inflammation.
Deep learning-based systems can serve as decision support tools by offering rapid and objective evaluations of dental calculus, plaque, gingival inflammation, and gingival hyperplasia. Nonetheless, the definitive diagnostic conclusion should be based on the clinician's specialized expertise and professional judgment.
The integration of CNN-based diagnostic models into clinical workflows has the potential to facilitate early periodontal diagnosis and improve accessibility to periodontal assessments in orthodontic patients.
本研究旨在开发基于卷积神经网络（CNN）的系统，以诊断正畸患者口腔内图像中的牙结石、牙菌斑、牙龈增生和牙龈炎症。
使用一个包含1000张正畸患者口腔侧位和正位图像的数据集来开发基于CNN的模型。牙周病专家对牙齿和牙龈上的牙结石、牙菌斑、牙龈炎症和牙龈增生区域进行标注。该数据集被分为训练集（80%）、验证集（10%）和测试集（10%）用于模型开发。对YOLOv8和混合U-Net + ResNet50模型进行了检验。根据准确率、精确率、召回率、F分数、Tversky损失、交并比、平均精度均值、Dice系数和科恩卡帕系数对它们的性能进行评估。
YOLOv8模型的平均分类准确率为0.96，U-Net + ResNet50模型为0.93。基于Dice系数，模型在检测牙龈增生方面表现最佳（YOLOv8：0.78，U-Net + ResNet50：0.79），在检测牙结石方面表现最差（YOLOv8：0.48，U-Net + ResNet50：0.53）。在对牙龈增生进行分类时，科恩卡帕系数最高（YOLOv8：0.785，U-Net + ResNet50：0.790）。所有分类的精确率均超过0.72，在对牙龈炎症进行分类时精确率最高。
基于深度学习的系统可以通过对牙结石、牙菌斑、牙龈炎症和牙龈增生进行快速客观的评估，作为决策支持工具。尽管如此，最终的诊断结论仍应基于临床医生的专业知识和专业判断。
将基于CNN的诊断模型整合到临床工作流程中，有可能促进早期牙周诊断，并提高正畸患者获得牙周评估的机会。
