Evaluation of artificial intelligence model for crowding categorization and extraction diagnosis using intraoral photographs
Top Cited Papers
Open Access
- 30 March 2023
- journal article
- research article
- Published by Springer Nature in Scientific Reports
- Vol. 13 (1) , 1-10
Abstract
Determining the severity of dental crowding and the necessity of tooth extraction for orthodontic treatment planning are time-consuming processes and there are no firm criteria. Thus, automated assistance would be useful to clinicians. This study aimed to construct and evaluate artificial intelligence (AI) systems to assist with such treatment planning. A total of 3,136 orthodontic occlusal photographs with annotations by two orthodontists were obtained. Four convolutional neural network (CNN) models, namely ResNet50, ResNet101, VGG16, and VGG19, were adopted for the AI process. Using the intraoral photographs as input, the crowding group and the necessity of tooth extraction were obtained. Arch length discrepancy analysis with AI-detected landmarks was used for crowding categorization. Various statistical and visual analyses were conducted to evaluate the performance. The maxillary and mandibular VGG19 models showed minimum mean errors of 0.84 mm and 1.06 mm for teeth landmark detection, respectively. Analysis of Cohen’s weighted kappa coefficient indicated that crowding categorization performance was best in VGG19 (0.73), decreasing in the order of VGG16, ResNet101, and ResNet50. For tooth extraction, the maxillary VGG19 model showed the highest accuracy (0.922) and AUC (0.961). By utilizing deep learning with orthodontic photographs, dental crowding categorization and diagnosis of orthodontic extraction were successfully determined. This suggests that AI can assist clinicians in the diagnosis and decision making of treatment plans.Keywords
This publication has 45 references indexed in Scilit:
- The Future of Orthodontic Diagnostic RecordsSeminars in Orthodontics, 2011
- Orthodontic measurements on digital study models compared with plaster models: a systematic reviewOrthodontics & Craniofacial Research, 2010
- Computational Formulation of Orthodontic Tooth-Extraction DecisionsThe Angle Orthodontist, 2009
- Quality of clinical photographs taken by orthodontists, professional photographers, and orthodontic auxiliariesAmerican Journal of Orthodontics and Dentofacial Orthopedics, 2009
- Biometric study of tooth size in normal, crowded, and spaced permanent dentitionsAmerican Journal of Orthodontics and Dentofacial Orthopedics, 2007
- Factors influencing treatment time in orthodontic patientsAmerican Journal of Orthodontics and Dentofacial Orthopedics, 2006
- The Heritability of Malocclusion: Part 2. The Influence of Genetics in MalocclusionBritish Journal of Orthodontics, 1999
- Consistency of orthodontic extraction decisionsEuropean Journal of Orthodontics, 1996
- Consistency of orthodontic treatment decisions relative to diagnostic recordsAmerican Journal of Orthodontics and Dentofacial Orthopedics, 1991
- Linear arch dimension and tooth sizeAmerican Journal of Orthodontics, 1949