Development of an Artificial Intelligence Model to Identify a Dental Implant from a Radiograph

Kim

J Periodontal Implant Sci

et al. 2022

Purpose The aim of this study was to evaluate and compare the accuracy performance of dental professionals in the classification of different types of dental implant systems (DISs) using panoramic radiographic images with and without the assistance of a deep learning (DL) algorithm. Methods Using a self-reported questionnaire, the classification accuracy of dental professionals (including 5 board-certified periodontists, 8 periodontology residents, and 31 dentists not specialized in implantology working at 3 dental hospitals) with and without the assistance of an automated DL algorithm were determined and compared. The accuracy, sensitivity, specificity, confusion matrix, receiver operating characteristic (ROC) curves, and area under the ROC curves were calculated to evaluate the classification performance of the DL algorithm and dental professionals. Results Using the DL algorithm led to a statistically significant improvement in the average classification accuracy of DISs (mean accuracy: 78.88%) compared to that without the assistance of the DL algorithm (mean accuracy: 63.13%, P <0.05). In particular, when assisted by the DL algorithm, board-certified periodontists (mean accuracy: 88.56%) showed higher average accuracy than did the DL algorithm, and dentists not specialized in implantology (mean accuracy: 77.83%) showed the largest improvement, reaching an average accuracy similar to that of the algorithm (mean accuracy: 80.56%). Conclusions The automated DL algorithm classified DISs with accuracy and performance comparable to those of board-certified periodontists, and it may be useful for dental professionals for the classification of various types of DISs encountered in clinical practice.

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Deep learning improves implant classification by dental professionals: a multi-center evaluation of accuracy and efficiency

Kim

J Periodontal Implant Sci

et al. 2022

“…Accurate image classification by CNNs using dental panoramic radiographs can be more difficult than intraoral radiography [24]. Furthermore, although there were 3, 4 and 6 types of implant classifications in several previous studies [24,25,27,28], our research features 12 types of implant brand classifications, and many types could be classified. The high classification accuracy under these conditions is very meaningful.…”

Section: Discussionmentioning

confidence: 82%

“…There have been several reports on dental implant branding studies using deep learning [24][25][26][27][28]. All of these studies were single-task, with a classification analysis performance of 0.935-0.98 for accuracy, 0.907-0.98 for recall, and 0.918-0.971 for AUC.…”

Section: Discussionmentioning

confidence: 99%

Multi-Task Deep Learning Model for Classification of Dental Implant Brand and Treatment Stage Using Dental Panoramic Radiograph Images

et al. 2021

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.

“…For instance, machine-learning algorithms and computer automation provided considerably good performance in detecting dental caries in periapical radiographs, according to Lee et al [ 22 , 23 , 24 , 25 ]. Studies [ 26 , 27 , 28 , 29 ] also utilized machine-learning methods to find the most significant factors predicting implant systems and prognosis. It is also reported that dentists have become dependent on computer applications to gain insights for clinical decision making [ 30 , 31 , 32 ].…”

Section: Introductionmentioning

confidence: 99%

Diagnosis of Tooth Prognosis Using Artificial Intelligence

et al. 2022

The accurate diagnosis of individual tooth prognosis has to be determined comprehensively in consideration of the broader treatment plan. The objective of this study was to establish an effective artificial intelligence (AI)-based module for an accurate tooth prognosis decision based on the Harvard School of Dental Medicine (HSDM) comprehensive treatment planning curriculum (CTPC). The tooth prognosis of 2359 teeth from 94 cases was evaluated with 1 to 5 levels (1—Hopeless, 5—Good condition for long term) by two groups (Model-A with 16, and Model-B with 13 examiners) based on 17 clinical determining factors selected from the HSDM-CTPC. Three AI machine-learning methods including gradient boosting classifier, decision tree classifier, and random forest classifier were used to create an algorithm. These three methods were evaluated against the gold standard data determined by consensus of three experienced prosthodontists, and their accuracy was analyzed. The decision tree classifier indicated the highest accuracy at 0.8413 (Model-A) and 0.7523 (Model-B). Accuracy with the gradient boosting classifier and the random forest classifier was 0.6896, 0.6687, and 0.8413, 0.7523, respectively. Overall, the decision tree classifier had the best accuracy among the three methods. The study contributes to the implementation of AI in the decision-making process of tooth prognosis in consideration of the treatment plan.