Position Weighted Convolutional Neural Network for Unbalanced Children Caries Diagnosis

doi:10.1109/ACCESS.2023.3294617

	Position Weighted Convolutional Neural Network for Unbalanced Children Caries Diagnosis
	Zhou, Xiaojie 1; Feng, Xueou 2; Li, Qingming 2; Yin, Qiyue2 ; Yang, Jun 3; Yu, Guoxia 1,4; Shi, Qing 5
发表期刊	IEEE ACCESS
ISSN	2169-3536
	2023
卷号	11 页码:77034-77044
通讯作者	Yu, Guoxia(yuguoxia@bch.com.cn)
摘要	Panoramic radiograph is one of the most widely used inspection tools for dentists making caries diagnosis, especially for teeth that are hard to be diagnosed through visual inspection. Recently, several deep learning methods, e.g., based on convolutional neural network (CNN) or transformer network, have been proposed for automatic caries diagnosis on dental panoramic radiographs, and promising results have been achieved. However, current approaches use all the teeth equally when training their models, which results in performance degeneration because of unbalanced classification difficulties for different tooth positions. The objective of this study is to introduce a position weighted CNN to alleviate the above problem for more accurate caries diagnosis. The position weighted module evaluates and revises the output of a specially designed CNN to incorporate position information. In addition, a novel data augmentation method is used to balance data with uneven decayed and normal teeth, which is one of the reasons leading to unbalanced classification difficulty. To verify the proposed method, a children panoramic radiograph database is collected and labeled with more than 6,000 teeth. The proposed approach outperforms the state-of-the-art caries diagnosis methods with the accuracy, precision, recall, F1 and area-under-the-curve being 0.8859, 0.8875, 0.8932, 0.8903 and 0.9315, respectively. Specially, the proposed model displays higher diagnosis performance compared with two attending doctors with more than five-year clinical experience but with different diagnosis patterns, showing a potential tool for assisting dentists.
关键词	Caries diagnosis CNN transformer position embedding panoramic radiograph
DOI	10.1109/ACCESS.2023.3294617
收录类别	SCI
语种	英语
资助项目	Respiratory Research Project of National Clinical Research Center for Respiratory Diseases[HXZX-20210402] ; National Natural Science Foundation of China[81800925]
项目资助者	Respiratory Research Project of National Clinical Research Center for Respiratory Diseases ; National Natural Science Foundation of China
WOS研究方向	Computer Science ; Engineering ; Telecommunications
WOS类目	Computer Science, Information Systems ; Engineering, Electrical & Electronic ; Telecommunications
WOS记录号	WOS:001041936300001
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/53829
专题	复杂系统认知与决策实验室
通讯作者	Yu, Guoxia
作者单位	1.Capital Med Univ, Beijing Childrens Hosp, Natl Ctr Childrens Hlth, Dept Stomatol, Beijing 100045, Peoples R China 2.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 3.Tsinghua Univ, Dept Automat, Beijing 100084, Peoples R China 4.Capital Med Univ, Beijing Childrens Hosp, Natl Ctr Childrens Hlth, Dept Stomatol,Natl Clin Res Ctr Resp Dis, Beijing 100045, Peoples R China 5.Capital Med Univ, Beijing Stomatol Hosp, Beijing 100050, Peoples R China
推荐引用方式 GB/T 7714	Zhou, Xiaojie,Feng, Xueou,Li, Qingming,et al. Position Weighted Convolutional Neural Network for Unbalanced Children Caries Diagnosis[J]. IEEE ACCESS,2023,11:77034-77044.
APA	Zhou, Xiaojie.,Feng, Xueou.,Li, Qingming.,Yin, Qiyue.,Yang, Jun.,...&Shi, Qing.(2023).Position Weighted Convolutional Neural Network for Unbalanced Children Caries Diagnosis.IEEE ACCESS,11,77034-77044.
MLA	Zhou, Xiaojie,et al."Position Weighted Convolutional Neural Network for Unbalanced Children Caries Diagnosis".IEEE ACCESS 11(2023):77034-77044.