Korean Academy of Oral and Maxillofacial Implantology (KAOMI) Implant Research Institute, Seoul, Korea.
Department of Advanced General Dentistry, Yonsei University College of Dentistry, Seoul, Korea.
Sci Rep. 2023 Mar 24;13(1):4862. doi: 10.1038/s41598-023-32118-1.
This study aimed to evaluate the accuracy of automated deep learning (DL) algorithm for identifying and classifying various types of dental implant systems (DIS) using a large-scale multicenter dataset. Dental implant radiographs of pos-implant surgery were collected from five college dental hospitals and 10 private dental clinics, and validated by the National Information Society Agency and the Korean Academy of Oral and Maxillofacial Implantology. The dataset contained a total of 156,965 panoramic and periapical radiographic images and comprised 10 manufacturers and 27 different types of DIS. The accuracy, precision, recall, F1 score, and confusion matrix were calculated to evaluate the classification performance of the automated DL algorithm. The performance metrics of the automated DL based on accuracy, precision, recall, and F1 score for 116,756 panoramic and 40,209 periapical radiographic images were 88.53%, 85.70%, 82.30%, and 84.00%, respectively. Using only panoramic images, the DL algorithm achieved 87.89% accuracy, 85.20% precision, 81.10% recall, and 83.10% F1 score, whereas the corresponding values using only periapical images achieved 86.87% accuracy, 84.40% precision, 81.70% recall, and 83.00% F1 score, respectively. Within the study limitations, automated DL shows a reliable classification accuracy based on large-scale and comprehensive datasets. Moreover, we observed no statistically significant difference in accuracy performance between the panoramic and periapical images. The clinical feasibility of the automated DL algorithm requires further confirmation using additional clinical datasets.
本研究旨在评估使用大规模多中心数据集的自动化深度学习（DL）算法识别和分类各种类型牙科植入系统（DIS）的准确性。从五所大学牙科医院和十所私人牙科诊所收集了植入术后的牙科植入物射线照片，并由国家信息社会局和韩国口腔颌面种植学会进行了验证。该数据集共包含 156965 张全景和根尖射线照片，包含 10 个制造商和 27 种不同类型的 DIS。计算准确性、精度、召回率、F1 评分和混淆矩阵来评估自动化 DL 算法的分类性能。基于准确性、精度、召回率和 F1 评分，对 116756 张全景和 40209 张根尖射线照片的自动化 DL 性能指标分别为 88.53%、85.70%、82.30%和 84.00%。仅使用全景图像，DL 算法的准确率为 87.89%、精度为 85.20%、召回率为 81.10%、F1 评分为 83.10%，而仅使用根尖图像的相应值分别为 86.87%、精度为 84.40%、召回率为 81.70%、F1 评分为 83.00%。在研究限制范围内，自动化 DL 基于大规模和综合数据集显示出可靠的分类准确性。此外，我们观察到全景和根尖图像之间的准确性性能没有统计学上的显著差异。自动化 DL 算法的临床可行性需要使用额外的临床数据集进一步确认。
