基于深度语义模型的乳腺X线图像检索  

Mammogram Retrieval Based on Deep Semantic Model

作　　者：邹佩 王颖[1] 李洁[1] ZOU Pei;WANG Ying;LI Jie(School of Electronic Engineering,Xidian University,Xi'an,710071,China)

机构地区：[1]西安电子科技大学电子工程学院,西安710071

出　　处：《数据采集与处理》2020年第3期400-410,共11页Journal of Data Acquisition and Processing

基　　金：国家自然科学基金(61571343)资助项目。

摘　　要：图像特征是基于内容的图像检索(Content-based image retrieval,CBIR)的关键,大部分使用的手工特征难以有效地表示乳腺肿块的特征,底层特征与高层语义之间存在语义鸿沟。为了提高CBIR的检索性能,本文采用深度学习来提取图像的高层语义特征。由于乳腺X线图像的深度卷积特征在空间和特征维度上存在一定的冗余和噪声,本文在词汇树和倒排文件的基础上,对深度特征的空间和语义进行优化,构建了两种不同的深度语义树。为了充分发挥深度卷积特征的识别能力,根据乳腺图像深度特征的局部特性对树节点的权重进行细化,提出了两种节点加权方法,得到了更好的检索结果。本文从乳腺X线图像数据库(Digital database for screening mammography,DDSM)中提取了2200个感兴趣区域(Region of interest,ROIs)作为数据集,实验结果表明,该方法能够有效提高感兴趣肿块区域的检索精度和分类准确率,并且具有良好的可扩展性。Image feature is the key to content-based image retrieval(CBIR).Most of the used manual features are difficult to effectively represent the features of the breast mass,and there is a semantic gap between the underlying features and the high-level semantics.In order to improve the retrieval performance of CBIR,this paper uses deep learning to extract the high-level semantic features of images.Because the deep convolution features of mammograms have some redundancies and noises in the spatial and feature dimensions,this paper optimizes the spatial and semantic features of depth features based on the vocabulary tree and inverted files,and constructs two different depth semantic trees.In order to fully exert the discriminative power of deep convolution features,the weight of tree nodes is refined according to the local characteristics of breast image depth features,and two node weighting methods are proposed to obtain better retrieval results.In this paper,2200 regions of interest(ROIs)are extracted from the digital database for screening mammography(DDSM)as datasets.The experimental results show that the proposed method can effectively improve the retrieval accuracy and the classification accuracy of the mass region of interest,and has good scalability.

关 键 词：乳腺肿块 乳腺X线图像 基于内容的图像检索 深度学习 深度语义树 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]