基于多尺度路径聚合的儿童龋齿检测算法  

Child Caries Detection Algorithm Based on Multi-Scale Path Aggregation

作　　者：李彦甫 兰海月 薛婧帆 郭锦林 黄睿洁 朱江平 Li Yanfu;Lan Haiyue;Xue Jingfan;Guo Jinlin;Huang Ruijie;Zhu Jiangping(National Key Laboratory of Fundamental Science on Synthetic Vision,Sichuan University,Chengdu 610065,Sichuan,China;West China School/Hospital of Stomatology,Sichuan University,Chengdu 610041,Sichuan,China;College of Computer Science,Sichuan University,Chengdu 610065,Sichuan,China)

机构地区：[1]四川大学视觉合成图形图像技术国防重点学科实验室,四川成都610065 [2]四川大学华西口腔医学院,四川成都610041 [3]四川大学计算机学院,四川成都610065

出　　处：《中国激光》2024年第15期162-172,共11页Chinese Journal of Lasers

基　　金：国家自然科学基金(62101364,61901287);四川省中央引导地方科技发展计划(22ZYD0111);中国博士后科学基金(2021M692260);四川省重大科技专项(2021YFG0195,2022YFG0053)。

摘　　要：龋齿是一种常见的口腔疾病,在儿童人群中的发病率较高。为了解决这个问题,本课题组制作了手机等移动设备拍摄的口腔图像数据集,其中包含多角度拍摄的口腔图像,同时采用翻转、拼接、色域转换等数据增强策略对数据进行处理,以提升数据的丰富性和多样性。本课题组提出了CR-PANet龋齿检测模型,该模型采用PANet的多尺度路径聚合架构,并对特征提取模块、检测头等结构进行了改进。实验结果表明:CR-PANet模型在测试数据集上的mAP@50指标达到了88.2%,每秒处理帧数达到了169,可以满足实时检测口腔图像中牙病区域的要求,有望实现患者自检或辅助医生检测。Objective Dental caries is a common oral disease affecting the hard tissues of teeth,typically resulting from bacterial infections.This in turn leads to chronic damage.It is prevalent during childhood with symptoms such as the discoloration,deformation,and structural deterioration of teeth.According to China s fourth epidemiological survey,71.9%of five-year-olds experience dental caries in deciduous teeth,and 34.5%of 12-year-olds experience it in permanent teeth.Hence,it is a widespread oral disease among children.Challenges,such as the lack of cooperation from children during tooth brushing and oral examinations,a scarcity of pediatric dentists,and low awareness among parents and pediatricians,often result in the delayed diagnosis and treatment at early stages.Furthermore,variability in diagnostic skills among doctors can result in different diagnoses for the same patient.Therefore,aiding in the identification of dental caries and enhancing diagnostic accuracy are essential for effective clinical diagnosis.Although deep learning-based object detection algorithms have made some progress in detecting dental diseases,they still do not adequately meet the needs for accuracy and speed in diagnosis and identification.Additionally,since detection typically relies on professional medical imaging,it prevents patients from performing self-checks using more accessible devices such as smartphones.Methods To address these issues,in this study,a dataset comprising oral images acquired using mobile devices,such as smartphones,was created.Compared to the uniform features of oral images captured with professional equipment,these images inevitably varied in aspects such as lighting intensity and shooting angle,making it challenging for the target detection model to fit during training.To overcome these difficulties,in this study,a caries detection algorithm was proposed based on multiscale path aggregation and robust data augmentation methods were proposed.First,architecture of a path aggregation network(PANet)was adopted in the

关 键 词：口腔图像 龋齿检测 深度学习 多尺度特征融合 早期儿童龋齿 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]