The Australian e-Health Research Centre, CSIRO, Floreat, Australia.
School of Human Sciences, The University of Western Australia, Crawley, Australia.
Dentomaxillofac Radiol. 2022 Feb 1;51(2):20210296. doi: 10.1259/dmfr.20210296. Epub 2021 Oct 13.
This study aimed to evaluate an automated detection system to detect and classify permanent teeth on orthopantomogram (OPG) images using convolutional neural networks (CNNs).
In total, 591 digital OPGs were collected from patients older than 18 years. Three qualified dentists performed individual teeth labelling on images to generate the ground truth annotations. A three-step procedure, relying upon CNNs, was proposed for automated detection and classification of teeth. Firstly, U-Net, a type of CNN, performed preliminary segmentation of tooth regions or detecting regions of interest (ROIs) on panoramic images. Secondly, the Faster R-CNN, an advanced object detection architecture, identified each tooth within the ROI determined by the U-Net. Thirdly, VGG-16 architecture classified each tooth into 32 categories, and a tooth number was assigned. A total of 17,135 teeth cropped from 591 radiographs were used to train and validate the tooth detection and tooth numbering modules. 90% of OPG images were used for training, and the remaining 10% were used for validation. 10-folds cross-validation was performed for measuring the performance. The intersection over union (IoU), F1 score, precision, and recall ( sensitivity) were used as metrics to evaluate the performance of resultant CNNs.
The ROI detection module had an IoU of 0.70. The tooth detection module achieved a recall of 0.99 and a precision of 0.99. The tooth numbering module had a recall, precision and F1 score of 0.98.
The resultant automated method achieved high performance for automated tooth detection and numbering from OPG images. Deep learning can be helpful in the automatic filing of dental charts in general dentistry and forensic medicine.
本研究旨在评估一种基于卷积神经网络（CNN）的自动检测系统，以检测和分类全景片（OPG）图像中的恒牙。
共收集 591 例 18 岁以上患者的数字化 OPG。3 名合格牙医对图像进行单独的牙齿标记，生成地面实况注释。提出了一个三步骤的程序，依赖于卷积神经网络，用于自动检测和分类牙齿。首先，U-Net，一种类型的 CNN，对全景图像上的牙齿区域或感兴趣区域（ROI）进行初步分割。其次，Faster R-CNN，一种先进的目标检测架构，在 U-Net 确定的 ROI 内识别每个牙齿。第三，VGG-16 架构将每个牙齿分类为 32 个类别，并分配一个牙齿编号。总共从 591 张射线照片裁剪出 17135 颗牙齿，用于训练和验证牙齿检测和牙齿编号模块。90%的 OPG 图像用于训练，其余 10%用于验证。使用 10 折交叉验证来衡量性能。交并比（IoU）、F1 分数、精度和召回率（敏感性）用于评估产生的 CNNs 的性能。
ROI 检测模块的 IoU 为 0.70。牙齿检测模块的召回率为 0.99，精度为 0.99。牙齿编号模块的召回率、精度和 F1 得分为 0.98。
所产生的自动化方法在 OPG 图像中实现了自动检测和编号的高性能。深度学习在一般牙科和法医学中自动归档牙科图表方面可能会有所帮助。
