期刊
JOURNAL OF DENTAL SCIENCES
卷 18, 期 3, 页码 1301-1309出版社
ELSEVIER TAIWAN
DOI: 10.1016/j.jds.2023.03.020
关键词
Convolutional neural networks (CNN); YOLO; Tooth position; Tooth shape; Bone level
This study proposes a new deep learning ensemble model based on deep Convolutional Neural Network algorithms to predict tooth position, detect shape, detect remaining interproximal bone level, and detect radiographic bone loss using periapical and bitewing radiographs. The DL-trained ensemble model shows an accuracy of approximately 90% for periapical radiographs, and achieves high accuracy in tooth position detection, tooth shape detection, peri-odontal bone level detection, and radiographic bone loss detection. The AI model outperforms dentists in accuracy, indicating its strong potential to enhance clinical professional performance and build more efficient dental health services.
Background/purpose: Artificial Intelligence (AI) can optimize treatment ap-proaches in dental healthcare due to its high level of accuracy and wide range of applications. This study seeks to propose a new deep learning (DL) ensemble model based on deep Convolu-tional Neural Network (CNN) algorithms to predict tooth position, detect shape, detect re-maining interproximal bone level, and detect radiographic bone loss (RBL) using periapical and bitewing radiographs.Materials and methods: 270 patients from January 2015 to December 2020, and all images were deidentified without private information for this study. A total of 8000 periapical radio-graphs with 27,964 teeth were included for our model. AI algorithms utilizing the YOLOv5 model and VIA labeling platform, including VGG-16 and U-Net architecture, were created as a novel ensemble model. Results of AI analysis were compared with clinicians' assessments.Results: DL-trained ensemble model accuracy was approximately 90% for periapical radio-graphs. Accuracy for tooth position detection was 88.8%, tooth shape detection 86.3%, peri-odontal bone level detection 92.61% and radiographic bone loss detection 97.0%. AI models were superior to mean accuracy values from 76% to 78% when detection was performed by den-tists. Conclusion: The proposed DL-trained ensemble model provides a critical cornerstone for radio-graphic detection and a valuable adjunct to periodontal diagnosis. High accuracy and reli-ability indicate model's strong potential to enhance clinical professional performance and build more efficient dental health services.& COPY; 2023 Association for Dental Sciences of the Republic of China. Publishing services by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons. org/licenses/by-nc-nd/4.0/).
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据