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  

Automatic assessment of root numbers of vertical mandibular third molar using a deep learning model based on attention mechanism

作　　者：孙春生 戴修斌 周曼婷 景秋平 张驰 阳胜军[1,2,3] 王东苗 SUN Chunsheng;DAI Xiubin;ZHOU Manting;JING Qiuping;ZHANG Chi;YANG Shengjun;WANG Dongmiao(Department of Oral and Maxillofacial Surgery,The Affiliated Stomatological Hospital of Nanjing Medical University,Nanjing 210029,China)

机构地区：[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 [4]南京邮电大学自动化学院,江苏南京210023 [5]南京邮电大学通信与信息工程学院,江苏南京210023

出　　处：《口腔医学》2024年第11期831-836,共6页Stomatology

基　　金：江苏省卫健委科研项目(M2020021);江苏高校优势学科建设工程(PAPD,2018⁃87);江苏省科教能力提升工程——江苏省研究型医院(YJXYYJSDW4),江苏省医学创新中心(CXZX202227);江苏省口腔转化医学工程研究中心开放课题(GCZX2023⁃04);中国牙病防治基金会科研项目(JKLKMNLOL);江苏省重点研发计划(BE2023833)。

摘　　要：目的构建基于注意力机制的深度学习网络,利用曲面断层片实现垂直位下颌第三磨牙牙根数目(单根或双根)的自动识别。方法将1045例1642颗成人垂直位下颌第三磨牙病例同时拍摄曲面断层片和CBCT,随机分成训练组(80%)、验证组(10%)和测试组(10%)。分别使用曲面断层片和CBCT评估其牙根数目,分为单根和双根。构建基于注意力机制的深度学习网络模型(RN⁃MTMnet),以曲面断层片作为输入,以配对CBCT诊断作为金标准,自动定位垂直位下颌第三磨牙所在区域并判断其牙根数目(单根或双根)。RN⁃MTMnet模型性能使用正确率、灵敏度、特异度、阳性预测值,以及ROC曲线及对应AUC面积值衡量,并与Faster⁃RCNN、CenterNet及SSD等网络模型以及人工诊断相比较。结果经CBCT诊断,纳入病例单根336(20.46%)侧,双根1306(79.54%)侧。RN⁃MTMnet获得结果的正确率为0.888,灵敏度为0.885,特异度为0.903,阳性预测值为0.976,受试者工作曲线下面积为0.90。结论RN⁃MTMnet模型提升了曲面断层片诊断垂直位下颌第三磨牙牙根数目的性能。Objective To develop a deep learning network based on attention mechanism to identify the number of the vertical mandibular third molar(MTM)roots(single or double)on panoramic radiographs in an automatic way.Methods The sample consisted of 1045 patients with 1642 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 panoramic 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 performance was compared with dentistsdiagnosis,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 1306(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⁃MTMnet is developed as a novel,robust and accurate method for detecting the numberof MTM roots on panoramic radiographs.

关 键 词：下颌第三磨牙 曲面断层片 CBCT 深度学习 注意力机制 

分 类 号：R782.1[医药卫生—口腔医学]