摘要
全景X射线图像的龋齿分割是进行早期龋齿检测以及后续治疗的重要前提,为实现全景X射线图像中龋齿的精确自动分割,提出一种具有多尺度卷积和选择性核双注意力机制的半监督学习框架,该方法旨在利用大量未标注数据增强模型泛化能力,并缓解龋齿病灶区域边界模糊、对比度低等问题。框架设计上,采用教师-学生双网络结构,通过多尺度卷积注意力机制对学生网络多层解码器进行深度监督,提升对边界细节和类间相似区域的判别能力。同时,引入选择性核注意力机制融合教师网络的多级预测结果,根据像素不确定性自适应选择不同卷积核,生成精确的不确定性掩模图,引导学生网络优化学习。实验在数据集1和2上进行,结果显示,在265切片数据上联合使用双注意力机制较基线模型在Dice系数、查准率和灵敏度分别提升3.91%、2.14%和5.35%;在530切片数据上则提升1.39%、5.69%和12.34%,验证了方法在大规模数据下的稳定性和适应性。与传统全监督模型相比,所提出的方法在Dice系数、查准率和灵敏度上最高分别提升22.27%、17.64%和24.57%;相比最新半监督模型也分别提升最多14.54%、14.81%和11.96%。本研究不仅有效提升了龋齿分割性能,同时也为全景X射线图像处理提供了一种精确的分割方案。
Caries segmentation in panoramic X-ray images is an important prerequisite for early caries detection and subsequent treatment.In order to achieve accurate and automatic segmentation of caries in panoramic X-ray images,a semi-supervised learning framework with multi-scale convolution and selective kernel dual-attention mechanism is proposed.This framework aims to enhance the generalization capability of the model by leveraging a large amount of unlabeled data,while addressing challenges such as blurred lesion boundaries and low contrast in caries-affected regions.The framework adopts a teacher-student dual network architecture.It applies multi-scale convolutional attention to deeply supervise the multilayer decoder in the student network,thereby improving its ability to capture boundary details and distinguish between similar inter-class regions.Meanwhile,a selective kernel attention mechanism is introduced to fuse multi-level predictions from the teacher network,adaptively selecting convolution kernels based on pixel-level uncertainty to generate accurate uncertainty masks that guide the student′s learning process.Experiments conducted on the dataset 1 and dataset 2 demonstrate that,on 265 slices,the dual attention mechanism achieves improvements over the baseline model of 3.91%,2.14%,and 5.35%in Dice coefficient,precision,and sensitivity,respectively.And on 530 slices,the improvements reach 1.39%,5.69%,and 12.34%,verifying the method′s stability and adaptability on larger-scale data.Compared with traditional fully supervised models,the proposed method achieves the highest improvements in Dice coefficient,precision,and sensitivity,with increases of 22.27%,17.64%,and 24.57%,respectively.And compared with recent semi-supervised methods,it achieves improvements of up to 14.54%,14.81%,and 11.96%,respectively.This study not only significantly enhances caries segmentation performance but also provides an accurate and robust solution for panoramic X-ray images.
作者
薛钟毫
姜金刚
孙健鹏
潘洁
张嘉伟
Xue Zhonghao;Jiang Jingang;Sun Jianpeng;Pan Jie;Zhang Jiawei(Key Laboratory of Advanced Manufacturing and Intelligent Technology,Ministry of Education,Harbin University of Science and Technology,Harbin 150080,China;Robotics&its Engineering Research Center,Harbin University of Science and Technology,Harbin 150080,China;Peking University School of Stomatology,Beijing 100081,China)
出处
《仪器仪表学报》
北大核心
2025年第6期241-250,共10页
Chinese Journal of Scientific Instrument
基金
黑龙江省“优秀青年教师基础研究支持计划”项目(YQJH2024075)资助。
关键词
龋齿分割
半监督学习
双注意力机制
全景X射线图像
caries segmentation
semi-supervised learning
dual-attention mechanism
panoramic X-ray images
