Accuracy of one-step automated orthodontic diagnosis model using a convolutional neural network and lateral cephalogram images with different qualities obtained from nationwide multi-hospitals
임선진, 김성철, 김인환, 박재우, 조진형, 홍미희, 강경화, 김민지, 김수정, 김윤지, 김영호, 임성훈, 성상진, 김남국, 백승학,
소속 상세정보
임선진 ( Yim Sun-Jin ) - Seoul National University School of Dentistry Department of Orthodontics
김성철 ( Kim Sung-Chul ) - University of Ulsan College of Medicine Asan Medical Center Department of Biomedical Engineering
김인환 ( Kim In-Hwan ) - University of Ulsan College of Medicine Asan Medical Center Department of Biomedical Engineering
박재우 ( Park Jae-Woo ) - Private practice
조진형 ( Cho Jin-Hyoung ) - Chonnam National University School of Dentistry Department of Orthodontics
홍미희 ( Hong Mi-Hee ) - Kyungpook National University School of Dentistry Department of Orthodontics
강경화 ( Kang Kyung-Hwa ) - Wonkwang University School of Dentistry Department of Orthodontics
김민지 ( Kim Min-Ji ) - Ewha Womans University College of Medicine Department of Orthodontics
김수정 ( Kim Su-Jung ) - Kyung Hee University School of Dentistry Department of Orthodontics
김윤지 ( Kim Yoon-Ji ) - University of Ulsan College of Medicine Asan Medical Center Department of Orthodontics
김영호 ( Kim Young-Ho ) - Ajou University School of Medicine Department of Orthodontics
임성훈 ( Lim Sung-Hoon ) - Chosun University School of Dentistry Department of Orthodontics
성상진 ( Sung Sang-Jin ) - University of Ulsan College of Medicine Asan Medical Center Department of Orthodontics
김남국 ( Kim Nam-Kug ) - University of Ulsan College of Medicine Asan Medical Center Department of Convergence Medicine
백승학 ( Baek Seung-Hak ) - Seoul National University School of Dentistry Department of Orthodontics
Abstract
Objective: The purpose of this study was to investigate the accuracy of one-step automated orthodontic diagnosis of skeletodental discrepancies using a convolutional neural network (CNN) and lateral cephalogram images with different qualities from nationwide multi-hospitals.
Methods: Among 2,174 lateral cephalograms, 1,993 cephalograms from two hospitals were used for training and internal test sets and 181 cephalograms from eight other hospitals were used for an external test set. They were divided into three classification groups according to anteroposterior skeletal discrepancies (Class I, II, and III), vertical skeletal discrepancies (normodivergent, hypodivergent, and hyperdivergent patterns), and vertical dental discrepancies (normal overbite, deep bite, and open bite) as a gold standard. Pre-trained DenseNet-169 was used as a CNN classifier model. Diagnostic performance was evaluated by receiver operating characteristic (ROC) analysis, t-stochastic neighbor embedding (t-SNE), and gradientweighted class activation mapping (Grad-CAM).
Results: In the ROC analysis, the mean area under the curve and the mean accuracy of all classifications were high with both internal and external test sets (all, > 0.89 and > 0.80). In the t-SNE analysis, our model succeeded in creating good separation between three classification groups. Grad-CAM figures showed differences in the location and size of the focus areas between three classification groups in each diagnosis.
Conclusions: Since the accuracy of our model was validated with both internal and external test sets, it shows the possible usefulness of a one-step automated orthodontic diagnosis tool using a CNN model. However, it still needs technical improvement in terms of classifying vertical dental discrepancies.
키워드
One-step automated orthodontic diagnosis; Convolutional neural networks; Lateral cephalogram; Multi-center study
원문 및 링크아웃 정보
등재저널 정보