结合判别式深度置信网络的乳腺图像微钙化簇区域检测  

Detection of microcalcification clusters regions in mammograms combining discriminative deep belief networks

作　　者：宋立新[1] 魏雪芹 王乾[2] 王玉静[1] SONG Lixin;WEI Xueqin;WANG Qian;WANG Yujing(School of Electrical and Electronic Engineering,Harbin University of Science and Technology,Harbin 150080,P.R.China;School of Computer Science and Technology,Harbin University of Science and Technology,Harbin 150080,P.R.China)

机构地区：[1]哈尔滨理工大学电气与电子工程学院,哈尔滨150080 [2]哈尔滨理工大学计算机科学与技术学院,哈尔滨150080

出　　处：《生物医学工程学杂志》2021年第2期268-275,共8页Journal of Biomedical Engineering

基　　金：国家自然科学基金资助项目(51805120);黑龙江省自然科学基金资助项目(F200912)。

摘　　要：为了克服乳腺图像微钙化簇检测中假阳性率高、泛化性差等缺点,本文提出了一种结合判别式深度置信网络(DDBNs)自动快速定位乳腺X线图像中微钙化簇区域的方法。首先,对乳腺区域进行提取及增强,将增强后的乳腺区域进行子块重叠分割和小波滤波;之后,构建用于乳腺子块特征提取和分类的DDBNs模型,将预训练后的DDBNs转换成使用softmax分类器的深度神经网络(DNN),并通过反向传播对网络进行微调;最后,输入待检乳腺X线图像,完成可疑病灶区域的定位。通过对乳腺摄影筛查数据库(DDSM)中的105幅含有微钙化点的图像进行实验验证,本文方法获得了99.45%的真阳性率和1.89%的假阳性率,且检测一幅2888×4680大小图像的时间约16 s。实验结果表明:该算法在保证较高真阳性率的同时有效地降低了假阳性率,检测到的微钙化簇区域与专家标记区域具有高度一致性,为乳腺X线图像中微钙化簇区域的自动检测提供了新的研究思路。In order to overcome the shortcomings of high false positive rate and poor generalization in the detection of microcalcification clusters regions,this paper proposes a method combining discriminative deep belief networks(DDBNs)to automatically and quickly locate the regions of microcalcification clusters in mammograms.Firstly,the breast region was extracted and enhanced,and the enhanced breast region was segmented to overlapped sub-blocks.Then the sub-block was subjected to wavelet filtering.After that,DDBNs model for breast sub-block feature extraction and classification was constructed,and the pre-trained DDBNs was converted to deep neural networks(DNN)using a softmax classifier,and the network is fine-tuned by back propagation.Finally,the undetected mammogram was inputted to complete the location of suspicious lesions.By experimentally verifying 105 mammograms with microcalcifications from the Digital Database for Screening Mammography(DDSM),the method obtained a true positive rate of 99.45%and a false positive rate of 1.89%,and it only took about 16 s to detect a 2888×4680 image.The experimental results showed that the algorithm of this paper effectively reduced the false positive rate while ensuring a high positive rate.The detection of calcification clusters was highly consistent with expert marks,which provides a new research idea for the automatic detection of microcalcification clusters area in mammograms.

关 键 词：微钙化簇 判别式深度置信网络 特征提取 深度神经网络 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] R737.9[自动化与计算机技术—计算机科学与技术]