使用卷积神经网络算法在牙片上检测牙齿编号、系带附着、牙龈增生和牙龈炎症征象：一项回顾性研究。

Detection of tooth numbering, frenulum attachment, gingival overgrowth, and gingival inflammation signs on dental photographs using convolutional neural network algorithms: a retrospective study.

出版信息

Quintessence Int. 2023 Sep 19;54(8):680-693. doi: 10.3290/j.qi.b4157183.

DOI:10.3290/j.qi.b4157183

Abstract

OBJECTIVES

This study aimed to develop an artificial intelligence (AI) model that can determine 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 three 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 16,795 teeth, 2,493 frenulum attachments, 1,211 gingival overgrowth areas, and 2,956 gingival inflammation signs. The confusion matrix system and ROC (receiver operator characteristic) analysis were used to statistically evaluate the success of the developed model.

RESULTS

The sensitivity, precision, F1 score, and AUC (area under the curve) for tooth numbering were 0.990, 0.784, 0.875, and 0.989; for frenulum attachment these were 0.894, 0.775, 0.830, and 0.827; for gingival overgrowth area these were 0.757, 0.675, 0.714, and 0.774; and for gingival inflammation sign 0.737, 0.823, 0.777, and 0.802, respectively.

CONCLUSION

The results of the present study show 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.

摘要

目的

本研究旨在开发一种人工智能 (AI) 模型，能够自动确定口腔内照片中的牙齿编号、系带附着、牙龈过度生长区域和牙龈炎症迹象，并评估该模型的性能。

方法与材料

本研究共使用了 654 张口腔内照片（n = 654）。所有照片均由三位牙周病医生进行审阅，并使用基于网络的标注软件中的分割方法对照片上的所有牙齿、系带附着、牙龈过度生长区域和牙龈炎症迹象进行标注。此外，还按照 FDI 系统进行牙齿编号。在 YOLOv5x 架构的帮助下开发了一个 AI 模型，该模型包含 16795 颗牙齿、2493 个系带附着、1211 个牙龈过度生长区域和 2956 个牙龈炎症迹象的标签。使用混淆矩阵系统和 ROC（接收器操作特征）分析对开发模型的成功进行了统计评估。

结果

牙齿编号的灵敏度、精度、F1 评分和 AUC（曲线下面积）分别为 0.990、0.784、0.875 和 0.989；系带附着的灵敏度、精度、F1 评分和 AUC 分别为 0.894、0.775、0.830 和 0.827；牙龈过度生长区域的灵敏度、精度、F1 评分和 AUC 分别为 0.757、0.675、0.714 和 0.774；牙龈炎症迹象的灵敏度、精度、F1 评分和 AUC 分别为 0.737、0.823、0.777 和 0.802。