The validity of an artificial intelligence application for assessment of orthodontic treatment need from clinical images |
| |
| Affiliation: | 1. Assistant Professor of Orthodontics, Department of Orthodontics, Faculty of Dental Medicine, Future University, Egypt;2. Oral Technology, University of Bonn, Germany;3. DigiBrain4 Inc., Chicago, IL, United States;4. Associate Professor of Oral and Maxillofacial Surgery, Department of Oral and Craniofacial Health Sciences, College of Dental Medicine, University of Sharjah, United Arab Emirates;5. Assistant Professor of Oral Surgery, Department of Oral and Maxillofacial Surgery, Faculty of Dentistry, Suez Canal University, Egypt;6. Professor of Orthodontics, Department of Orthodontics, College of Dentistry, University of Illinois at Chicago, United States;7. Assistant Professor of Orthodontics, Department of Orthodontics, College of Dentistry, University of Illinois at Chicago, United States;8. Department of Orthodontics, Faculty of Dentistry, Tanta University, Egypt;9. Professor and Head of Oral Technology Department, University of Bonn, Germany;10. Professor, Chair and Graduate Program Director, Department of Orthodontics, H Hamdan Bin Mohammed College of Dental Medicine, Mohammed Bin Rashid University of Medicine and Health Sciences, Dubai, United Arab Emirates;11. Adjunct Faculty, Department of Orthodontics, Faculty of Dental Medicine, Future University, Egypt |
| |
| Abstract: | Aim: To assess the validity of a Convolutional Neural Network (CNN) digital model to detect and localize orthodontic malocclusions from intraoral clinical images. Materials and methods: The sample of this study consisted of the intraoral images of 700 Subjects. All images were intraoral clinical images, in one of the following views: Left Occlusion, Right Occlusion, Front Occlusion, Upper Occlusal, and Lower Occlusal. The following malocclusion conditions were localized: crowding, spacing, increased overjet, cross bite, open bite, deep bite. The images annotations were repeated by the same investigator (S.T) with a one week interval (ICC ≥ 0.9). The CNN model used for this research study was the “You Only Look Once” model. This model can detect and localize multiple objects or multiple instances of the same object in each image. It is a fully convolutional deep neural network; 24 convolutional layers followed by 2 fully connected layers. This model was implemented using the TensorFlow framework freely available from Google. Results: The created CNN model was able to detect and localize the malocclusions with an accuracy of 99.99%, precision of 99.79%, and a recall of 100%. Conclusions: The use of computational deep convolutional neural networks to identify and localize orthodontic problems from clinical images proved valid. The built AI engine accurately detected and localized malocclusion from different views of intra-oral clinical images. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
