AI model to detect contact relationship between maxillary sinus and posterior teeth

• DOI: 10.1016/j.heliyon.2024.e31052
• Publication Date: 2024-05-10T15:48:25Z
• Authors: Wanghui Ding; Yindi Jiang; Gaozhi Pang; Ziang Liu; Yuefan Wu; Jianhua Li; Fuli Wu
• Keywords: Social sciences (General); H1-99; Artificial intelligence; Q1-390; Science (General); Oral diagnosis; Radiology; Deep learning/machine learning; Decision-making; Research Article

To establish a novel deep learning networks (MSF-MPTnet) based on panoramic radiographs (PRs) for automatic assessment of relationship between maxillary sinus floor (MSF) and maxillary posterior teeth (MPT), and to compare accuracy of MSF-MPTnet, dentists and radiologists identifying contact relationship.A total of 1035 PRs and 1035 Cone-beam computed tomographys （CBCT）images were collected from January 2018 to April 2022. The relationships were classified into class I and II by CBCT. Class I represents non-contact group, and class II represents contact group. 350 PRs were randomly selected as test dataset and accuracy of MSF-MPTnet, dentists, and radiologists was compared.The intraclass correlation coefficient of dentists was 0.460-0.690 and it was 0.453-0.664 for radiologists. Sensitivity and accuracy of MSF-MPTnet were 0.682-0.852and 0.890-0.951, indicating that the output performance of MSF-MPTnet was reliable. Accuracy of maxillary premolars and molars were 79.7%-90.3 %, 76.2%-89.2 % and 72.9%-88.3 % in MSF-MPTnet model, dentists and radiologists. Accuracy of class I relationship in the MSF-MPTnet model (67.7%-94.6 %) was higher than that of dentists (56.5%-84.6 %) in maxillary first premolars and right second premolar, and accuracy of class I relationship in the MSF-MPTnet model is also higher than radiologists (40.0%-78.1 %) in all teeth positions (p < 0.05).MSF-MPTnet model could increase detecting accuracy of the relationship between MSF and MPT, minimize pseudo contact relationship and reduce frequency of CBCT use.