A population-based study to assess two convolutional neural networks for dental age estimation
J Wang, J Dou, J Han, G Li, J Tao - BMC Oral Health, 2023 - Springer
J Wang, J Dou, J Han, G Li, J Tao
BMC Oral Health, 2023•SpringerBackground Dental age (DA) estimation using two convolutional neural networks (CNNs),
VGG16 and ResNet101, remains unexplored. In this study, we aimed to investigate the
possibility of using artificial intelligence-based methods in an eastern Chinese population.
Methods A total of 9586 orthopantomograms (OPGs)(4054 boys and 5532 girls) of the
Chinese Han population aged from 6 to 20 years were collected. DAs were automatically
calculated using the two CNN model strategies. Accuracy, recall, precision, and F1 score of …
VGG16 and ResNet101, remains unexplored. In this study, we aimed to investigate the
possibility of using artificial intelligence-based methods in an eastern Chinese population.
Methods A total of 9586 orthopantomograms (OPGs)(4054 boys and 5532 girls) of the
Chinese Han population aged from 6 to 20 years were collected. DAs were automatically
calculated using the two CNN model strategies. Accuracy, recall, precision, and F1 score of …
Background
Dental age (DA) estimation using two convolutional neural networks (CNNs), VGG16 and ResNet101, remains unexplored. In this study, we aimed to investigate the possibility of using artificial intelligence-based methods in an eastern Chinese population.
Methods
A total of 9586 orthopantomograms (OPGs) (4054 boys and 5532 girls) of the Chinese Han population aged from 6 to 20 years were collected. DAs were automatically calculated using the two CNN model strategies. Accuracy, recall, precision, and F1 score of the models were used to evaluate VGG16 and ResNet101 for age estimation. An age threshold was also employed to evaluate the two CNN models.
Results
The VGG16 network outperformed the ResNet101 network in terms of prediction performance. However, the model effect of VGG16 was less favorable than that in other age ranges in the 15–17 age group. The VGG16 network model prediction results for the younger age groups were acceptable. In the 6-to 8-year-old group, the accuracy of the VGG16 model can reach up to 93.63%, which was higher than the 88.73% accuracy of the ResNet101 network. The age threshold also implies that VGG16 has a smaller age-difference error.
Conclusions
This study demonstrated that VGG16 performed better when dealing with DA estimation via OPGs than the ResNet101 network on a wholescale. CNNs such as VGG16 hold great promise for future use in clinical practice and forensic sciences.
Springer
以上显示的是最相近的搜索结果。 查看全部搜索结果