Deep Learning for Staging Periodontitis Using Panoramic Radiographs
Oral Diseases · 2025-07 · 31 (7) · 2273-2281
DOI: 10.1111/odi.15269 ↗Kurz gefasst
Fachartikel in der Zeitschrift Oral Diseases, online erschienen am 30.01.2025. Verfasst von Xin Li und 9 weiteren Autor:innen. Beteiligte Einrichtung: School of Public Health, National Institute for Data Science in Health and Medicine, Capital Medical University, Beijing, China. Hauptthemen laut MEDLINE: Deep Learning, Radiography, Panoramic, Periodontitis, Alveolar Bone Loss. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 46 Literaturangaben. Gefördert von: the Beijing Municipal Health Commission, Beijing Municipal Science and Technology Commission, the Beijing Municipal Science and Technology Commission.
Abstract (Originalsprache)
Objectives
Utilizing a deep learning approach is an emerging trend to improve the efficiency of periodontitis diagnosis and classification. This study aimed to use an object detection model to automatically annotate the anatomic structure and subsequently classify the stages of radiographic bone loss (RBL). Materials and Methods In all, 558 panoramic radiographs were cropped to 7359 pieces of individual teeth. The detection performance of the model was assessed using mean average precision (mAP), root mean squared error (RMSE). The classification performance was evaluated using accuracy, precision, recall, and F 1 score. Additionally, receiver operating characteristic (ROC) curves and confusion matrices were presented, and the area under the ROC curve (AUC) was calculated.
Results
The mAP was 0.88 when the difference between the ground truth and prediction was 10 pixels, and 0.99 when the difference was 25 pixels. For all images, the mean RMSE was 7.30 pixels. Overall, the accuracy, precision, recall, F 1 score, and micro‐average AUC of the prediction were 0.72, 0.76, 0.64, 0.68, and 0.79, respectively.
Conclusions
The current model is reliable in assisting with the detection and staging of radiographic bone levels.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Public Health, National Institute for Data Science in Health and Medicine, Capital Medical University, Beijing, China.
- Hunan Key Laboratory of Oral Health Research, Hunan 3D Printing Engineering Research Center of Oral Care, Hunan Clinical Research Center of Oral Major Diseases and Oral Health, Academician Workstation for Oral-Maxilofac…
- Department of Implant Dentistry, Beijing Stomatological Hospital, Capital Medical University, Beijing, China.
- Beijing Tiantan Hospital, Capital Medical University, Beijing, China.
- Xiangya School of Stomatology, Central South University, Changsha, Hunan, China.
- Salivary Gland Disease Center and Beijing Key Laboratory of Tooth Regeneration and Function Reconstruction, Beijing Laboratory of Oral Health and Beijing Stomatological Hospital, Capital Medical University, Beijing, Chi…
ORCID-Profile: Songlin Wang
Förderung
- the Beijing Municipal Health Commission
- Beijing Municipal Science and Technology Commission
- the Beijing Municipal Science and Technology Commission
- the Beijing Municipal Education Commission
- Capital Medical University
- Chinese Academy of Medical Sciences
- National Natural Science Foundation of China
- Beijing Municipal Education Commission
Zitieren
APA
Li, X., Chen, K., Zhao, D., He, Y., Li, Y., Li, Z., Guo, X., Zhang, C., Li, W., & Wang, S. (2025). Deep Learning for Staging Periodontitis Using Panoramic Radiographs. Oral Diseases, 31(7), 2273-2281. https://doi.org/10.1111/odi.15269
Vancouver
Li X, Chen K, Zhao D, He Y, Li Y, Li Z, et al. Deep Learning for Staging Periodontitis Using Panoramic Radiographs. Oral Diseases. 2025;31(7):2273-2281. doi:10.1111/odi.15269
BibTeX
@article{Li2025,
author = {Li, Xin and Chen, Kejia and Zhao, Dan and He, Yongqi and Li, Yajie and Li, Zeliang and Guo, Xiangyu and Zhang, Chunmei and Li, Wenbin and Wang, Songlin},
title = {Deep Learning for Staging Periodontitis Using Panoramic Radiographs},
journal = {Oral Diseases},
year = {2025},
volume = {31},
number = {7},
pages = {2273--2281},
doi = {10.1111/odi.15269}
}
EUVIMED