Faculty of Dentistry, Department of Pediatric Dentistry, Recep Tayyip Erdogan University, Rize, Turkey.
Faculty of Dentistry, Department of Oral and Dentomaxillofacial Radiology, Recep Tayyip Erdogan University, Rize, Turkey.
BMC Oral Health. 2024 Sep 3;24(1):1034. doi: 10.1186/s12903-024-04786-6.
This study aims to evaluate the performance of a deep learning system for the evaluation of tooth development stages on images obtained from panoramic radiographs from child patients.
The study collected a total of 1500 images obtained from panoramic radiographs from child patients between the ages of 5 and 14 years. YOLOv5, a convolutional neural network (CNN)-based object detection model, was used to automatically detect the calcification states of teeth. Images obtained from panoramic radiographs from child patients were trained and tested in the YOLOv5 algorithm. True-positive (TP), false-positive (FP), and false-negative (FN) ratios were calculated. A confusion matrix was used to evaluate the performance of the model.
Among the 146 test group images with 1022 labels, there were 828 TPs, 308 FPs, and 1 FN. The sensitivity, precision, and F1-score values of the detection model of the tooth stage development model were 0.99, 0.72, and 0.84, respectively.
In conclusion, utilizing a deep learning-based approach for the detection of dental development on pediatric panoramic radiographs may facilitate a precise evaluation of the chronological correlation between tooth development stages and age. This can help clinicians make treatment decisions and aid dentists in finding more accurate treatment options.
本研究旨在评估一种深度学习系统在评估儿童患者全景片上牙齿发育阶段方面的性能。
本研究共收集了 1500 张来自 5 至 14 岁儿童患者的全景片图像。使用基于卷积神经网络（CNN）的目标检测模型 YOLOv5 自动检测牙齿的钙化状态。使用 YOLOv5 算法对儿童患者的全景片图像进行训练和测试。计算真阳性（TP）、假阳性（FP）和假阴性（FN）的比例。使用混淆矩阵评估模型的性能。
在包含 1022 个标签的 146 个测试组图像中，有 828 个 TP、308 个 FP 和 1 个 FN。牙齿阶段发育模型的检测模型的灵敏度、精度和 F1 分数值分别为 0.99、0.72 和 0.84。
总之，在儿童全景片上使用基于深度学习的方法检测牙齿发育可以精确评估牙齿发育阶段与年龄之间的时间相关性。这有助于临床医生做出治疗决策，并帮助牙医找到更准确的治疗方案。
