口腔疾病防治2024，Vol.32Issue(1)：43-49,7.DOI:10.12016/j.issn.2096-1456.2024.01.007
基于MobileNetV3网络的龋病和根尖周炎根尖片的诊断
MobileNetV3 network-based diagnosis of caries and periapical periodontitis from periapical films
摘要
Abstract
Objective To research the effectiveness of deep learning techniques in intelligently diagnosing dental caries and periapical periodontitis and to explore the preliminary application value of deep learning in the diagnosis of oral diseases.Methods A dataset containing 2 298 periapical films,including healthy teeth,dental caries,and peri-apical periodontitis,was used for the study.The dataset was randomly divided into 1 573 training images,233 valida-tion images,and 492 test images.By comparing various neural network models,the MobileNetV3 network model with better performance was selected for dental disease diagnosis,and the model was optimized by tuning the network hyper-parameters.The accuracy,precision,recall,and F1 score were used to evaluate the model's ability to recognize dental caries and periapical periodontitis.Class activation map was used to visualization analyze the performance of the net-work model.Results The algorithm achieved a relatively ideal intelligent diagnostic effect with precision,recall,and accuracy of 99.42%,99.73%,and 99.60%,respectively,and the F1 score was 99.57%for classifying healthy teeth,den-tal caries,and periapical periodontitis.The visualization of the class activation maps also showed that the network model can accurately extract features of dental diseases.Conclusion The tooth lesion detection algorithm based on the Mo-bileNetV3 network model can eliminate interference from image quality and human factors and has high diagnostic accu-racy,which can meet the needs of dental medicine teaching and clinical applications.关键词
牙科病变/龋病/根尖周炎/根尖片/智能诊断/图像处理/深度学习/MobileNetV3网络/类激活图/可视化分析Key words
dental disease/caries/periapical periodontitis/periapical film/intelligent diagnosis/image processing/deep learning/MobileNetV3 network/class activation map/visualization analysis分类
口腔医学引用本文复制引用
王凯欣,刘丰,曾令芳,刘超..基于MobileNetV3网络的龋病和根尖周炎根尖片的诊断[J].口腔疾病防治,2024,32(1):43-49,7.基金项目
国家自然科学基金面上项目(52172282)This study was supported by the grants from National Natural Science Foundation of China(No.52172282). （52172282）
