In this study, we used panoramic X-ray images to classify and clarify the accuracy of different dental implant brands via deep convolutional neural networks (CNNs) with transfer-learning strategies. For objective labeling, 8859 implant images of 11 implant systems were used from digital panoramic radiographs obtained from patients who underwent dental implant treatment at Kagawa Prefectural Central Hospital, Japan, between 2005 and 2019. Five deep CNN models (specifically, a basic CNN with three convolutional layers, VGG16 and VGG19 transfer-learning models, and finely tuned VGG16 and VGG19) were evaluated for implant classification. Among the five models, the finely tuned VGG16 model exhibited the highest implant classification performance. The finely tuned VGG19 was second best, followed by the normal transfer-learning VGG16. We confirmed that the finely tuned VGG16 and VGG19 CNNs could accurately classify dental implant systems from 11 types of panoramic X-ray images.

It is necessary to accurately identify dental implant brands and the stage of treatment to ensure efficient care. Thus, the purpose of this study was to use multi-task deep learning to investigate a classifier that categorizes implant brands and treatment stages from dental panoramic radiographic images. For objective labeling, 9767 dental implant images of 12 implant brands and treatment stages were obtained from the digital panoramic radiographs of patients who underwent procedures at Kagawa Prefectural Central Hospital, Japan, between 2005 and 2020. Five deep convolutional neural network (CNN) models (ResNet18, 34, 50, 101 and 152) were evaluated. The accuracy, precision, recall, specificity, F1 score, and area under the curve score were calculated for each CNN. We also compared the multi-task and single-task accuracies of brand classification and implant treatment stage classification. Our analysis revealed that the larger the number of parameters and the deeper the network, the better the performance for both classifications. Multi-tasking significantly improved brand classification on all performance indicators, except recall, and significantly improved all metrics in treatment phase classification. Using CNNs conferred high validity in the classification of dental implant brands and treatment stages. Furthermore, multi-task learning facilitated analysis accuracy.

Pell and Gregory, and Winter’s classifications are frequently implemented to classify the mandibular third molars and are crucial for safe tooth extraction. This study aimed to evaluate the classification accuracy of convolutional neural network (CNN) deep learning models using cropped panoramic radiographs based on these classifications. We compared the diagnostic accuracy of single-task and multi-task learning after labeling 1330 images of mandibular third molars from digital radiographs taken at the Department of Oral and Maxillofacial Surgery at a general hospital (2014–2021). The mandibular third molar classifications were analyzed using a VGG 16 model of a CNN. We statistically evaluated performance metrics [accuracy, precision, recall, F1 score, and area under the curve (AUC)] for each prediction. We found that single-task learning was superior to multi-task learning (all p < 0.05) for all metrics, with large effect sizes and low p-values. Recall and F1 scores for position classification showed medium effect sizes in single and multi-task learning. To our knowledge, this is the first deep learning study to examine single-task and multi-task learning for the classification of mandibular third molars. Our results demonstrated the efficacy of implementing Pell and Gregory, and Winter’s classifications for specific respective tasks.

Attention mechanism, which is a means of determining which part of the forced data is emphasized, has attracted attention in various fields of deep learning in recent years. The purpose of this study was to evaluate the performance of the attention branch network (ABN) for implant classification using convolutional neural networks (CNNs). The data consisted of 10191 dental implant images from 13 implant brands that cropped the site, including dental implants as pretreatment, from digital panoramic radiographs of patients who underwent surgery at Kagawa Prefectural Central Hospital between 2005 and 2021. ResNet 18, 50, and 152 were evaluated as CNN models that were compared with and without the ABN. We used accuracy, precision, recall, specificity, F1 score, and area under the receiver operating characteristics curve as performance metrics. We also performed statistical and effect size evaluations of the 30-time performance metrics of the simple CNNs and the ABN model. ResNet18 with ABN significantly improved the dental implant classification performance for all the performance metrics. Effect sizes were equivalent to “Huge” for all performance metrics. In contrast, the classification performance of ResNet50 and 152 deteriorated by adding the attention mechanism. ResNet18 showed considerably high compatibility with the ABN model in dental implant classification (AUC = 0.9993) despite the small number of parameters. The limitation of this study is that only ResNet was verified as a CNN; further studies are required for other CNN models.

In this study, the accuracy of the positional relationship of the contact between the inferior alveolar canal and mandibular third molar was evaluated using deep learning. In contact analysis, we investigated the diagnostic performance of the presence or absence of contact between the mandibular third molar and inferior alveolar canal. We also evaluated the diagnostic performance of bone continuity diagnosed based on computed tomography as a continuity analysis. A dataset of 1279 images of mandibular third molars from digital radiographs taken at the Department of Oral and Maxillofacial Surgery at a general hospital (2014–2021) was used for the validation. The deep learning models were ResNet50 and ResNet50v2, with stochastic gradient descent and sharpness-aware minimization (SAM) as optimizers. The performance metrics were accuracy, precision, recall, specificity, F1 score, and area under the receiver operating characteristic curve (AUC). The results indicated that ResNet50v2 using SAM performed excellently in the contact and continuity analyses. The accuracy and AUC were 0.860 and 0.890 for the contact analyses and 0.766 and 0.843 for the continuity analyses. In the contact analysis, SAM and the deep learning model performed effectively. However, in the continuity analysis, none of the deep learning models demonstrated significant classification performance.