Deep Learning for Staging Periodontitis Using Panoramic Radiographs.

IF 2.9 3区医学 Q1 DENTISTRY, ORAL SURGERY & MEDICINE

Oral diseases Pub Date : 2025-01-30 DOI:10.1111/odi.15269

Xin Li, Kejia Chen, Dan Zhao, Yongqi He, Yajie Li, Zeliang Li, Xiangyu Guo, Chunmei Zhang, Wenbin Li, Songlin Wang

{"title":"Deep Learning for Staging Periodontitis Using Panoramic Radiographs.","authors":"Xin Li, Kejia Chen, Dan Zhao, Yongqi He, Yajie Li, Zeliang Li, Xiangyu Guo, Chunmei Zhang, Wenbin Li, Songlin Wang","doi":"10.1111/odi.15269","DOIUrl":null,"url":null,"abstract":"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 F1 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, F1 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.","PeriodicalId":19615,"journal":{"name":"Oral diseases","volume":" ","pages":""},"PeriodicalIF":2.9000,"publicationDate":"2025-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Oral diseases","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1111/odi.15269","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"DENTISTRY, ORAL SURGERY & MEDICINE","Score":null,"Total":0}

引用次数: 0

Abstract

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 F1 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, F1 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.

查看原文本刊更多论文

求助全文

约1分钟内获得全文求助全文

来源期刊

Oral diseases 医学-牙科与口腔外科

CiteScore

7.60

自引率

5.30%

发文量

325

审稿时长

4-8 weeks

期刊介绍： Oral Diseases is a multidisciplinary and international journal with a focus on head and neck disorders, edited by leaders in the field, Professor Giovanni Lodi (Editor-in-Chief, Milan, Italy), Professor Stefano Petti (Deputy Editor, Rome, Italy) and Associate Professor Gulshan Sunavala-Dossabhoy (Deputy Editor, Shreveport, LA, USA). The journal is pre-eminent in oral medicine. Oral Diseases specifically strives to link often-isolated areas of dentistry and medicine through broad-based scholarship that includes well-designed and controlled clinical research, analytical epidemiology, and the translation of basic science in pre-clinical studies. The journal typically publishes articles relevant to many related medical specialties including especially dermatology, gastroenterology, hematology, immunology, infectious diseases, neuropsychiatry, oncology and otolaryngology. The essential requirement is that all submitted research is hypothesis-driven, with significant positive and negative results both welcomed. Equal publication emphasis is placed on etiology, pathogenesis, diagnosis, prevention and treatment.