Department of Medical Imaging and Intervention, Chang Gung Memorial Hospital at Linkou, Taoyuan, Taiwan.
Department of Medical Imaging and Radiological Sciences, Chang Gung University, Taoyuan, Taiwan.
BMC Med Imaging. 2023 Aug 18;23(1):109. doi: 10.1186/s12880-023-01064-9.
Dental film mounting is an essential but time-consuming task in dental radiography, with manual methods often prone to errors. This study aims to develop a deep learning (DL) model for accurate automated classification and mounting of both intraoral and extraoral dental radiography.
The present study employed a total of 22,334 intraoral images and 1,035 extraoral images to train the model. The performance of the model was tested on an independent internal dataset and two external datasets from different institutes. Images were categorized into 32 tooth areas. The VGG-16, ResNet-18, and ResNet-101 architectures were used for pretraining, with the ResNet-101 ultimately being chosen as the final trained model. The model's performance was evaluated using metrics of accuracy, precision, recall, and F1 score. Additionally, we evaluated the influence of misalignment on the model's accuracy and time efficiency.
The ResNet-101 model outperformed VGG-16 and ResNet-18 models, achieving the highest accuracy of 0.976, precision of 0.969, recall of 0.984, and F1-score of 0.977 (p < 0.05). For intraoral images, the overall accuracy remained consistent across both internal and external datasets, ranging from 0.963 to 0.972, without significant differences (p = 0.348). For extraoral images, the accuracy consistently achieved the highest value of 1 across all institutes. The model's accuracy decreased as the tilt angle of the X-ray film increased. The model achieved the highest accuracy of 0.981 with correctly aligned films, while the lowest accuracy of 0.937 was observed for films exhibiting severe misalignment of ± 15° (p < 0.001). The average time required for the tasks of image rotation and classification for each image was 0.17 s, which was significantly faster than that of the manual process, which required 1.2 s (p < 0.001).
This study demonstrated the potential of DL-based models in automating dental film mounting with high accuracy and efficiency. The proper alignment of X-ray films is crucial for accurate classification by the model.
在口腔放射学中，牙片装片是一项必不可少但耗时的任务，手动方法往往容易出错。本研究旨在开发一种深度学习（DL）模型，用于准确地自动分类和装片口腔内和口腔外的牙科放射影像。
本研究共使用了 22334 张口腔内图像和 1035 张口腔外图像来训练模型。模型的性能在一个独立的内部数据集和来自两个不同机构的两个外部数据集上进行了测试。图像被分类为 32 个牙齿区域。VGG-16、ResNet-18 和 ResNet-101 架构用于预训练，最终选择 ResNet-101 作为最终训练的模型。使用准确度、精确度、召回率和 F1 评分等指标来评估模型的性能。此外，我们还评估了图像错位对模型准确性和时间效率的影响。
ResNet-101 模型优于 VGG-16 和 ResNet-18 模型，其准确度最高为 0.976，精确度为 0.969，召回率为 0.984，F1 得分为 0.977（p<0.05）。对于口腔内图像，内部和外部数据集的整体准确度保持一致，范围为 0.963 至 0.972，差异无统计学意义（p=0.348）。对于口腔外图像，所有机构的准确度均达到 1 的最高值。随着 X 射线胶片倾斜角度的增加，模型的准确度降低。当胶片正确对齐时，模型的准确度达到最高值 0.981，而当胶片严重错位（±15°）时，准确度最低为 0.937（p<0.001）。每张图像的图像旋转和分类任务所需的平均时间为 0.17 秒，明显快于手动过程（1.2 秒）（p<0.001）。
本研究表明，基于深度学习的模型在自动化牙科胶片装片方面具有很高的准确性和效率。X 射线胶片的正确对准对于模型的准确分类至关重要。
