Automatic assessment of root numbers of vertical mandibular third molar using a deep learning model based on attention mechanism
10.13591/j.cnki.kqyx.2024.11.006
- VernacularTitle:基于注意力机制的深度学习网络自动识别垂直位下颌第三磨牙牙根数目的研究
- Author:
Chunsheng SUN
1
,
2
,
3
;
Xiubin DAI
;
Manting ZHOU
;
Qiuping JING
;
Chi ZHANG
;
Shengjun YANG
;
Dongmiao WANG
Author Information
1. 南京医科大学附属口腔医院口腔颌面外科,江苏 南京(210029)
2. 口腔疾病研究与防治国家级重点实验室培育建设点(南京医科大学),江苏 南京(210029)
3. 江苏省口腔转化医学工程研究中心,江苏 南京(210029)
- Keywords:
mandibular third molar;
panoramic radiography;
CBCT;
deep learning;
attention mechanism
- From:
STOMATOLOGY
2024;44(11):831-836
- CountryChina
- Language:Chinese
-
Abstract:
Objective To develop a deep learning network based on attention mechanism to identify the number of the vertical man-dibular third molar(MTM)roots(single or double)on panoramic radiographs in an automatic way.Methods The sample consisted of 1 045 patients with 1 642 MTMs on paired panoramic radiographs and Cone-beam computed tomography(CBCT)and were randomly grouped into the training(80%),the validation(10%),and the test(10%).The evaluation of CBCT was defined as the ground truth.A deep learning network based on attention mechanism,which was named as RN-MTMnet,was trained to judge if the MTM on pano-ramic radiographs had one or two roots.Diagnostic performance was evaluated by accuracy,sensitivity,specificity,and positive predict value(PPV),and the receiver operating characteristic(ROC)curve with the area under the ROC curve(AUC).Its diagnostic perform-ance was compared with dentists'diagnosis,Faster-RCNN,CenterNet,and SSD using evaluation metrics.Results On CBCT images,single-rooted MTM was observed on 336(20.46%)sides,while two-rooted MTM was 1 306(79.54%).The RN-MTMnet achieved an accuracy of 0.888,a sensitivity of 0.885,a specificity of 0.903,a PPV of 0.976,and the AUC value of 0.90.Conclusion RN-MTM-net is developed as a novel,robust and accurate method for detecting the numberof MTM roots on panoramic radiographs.
