基于视觉显著性特征的乳腺肿块检测方法
发布时间:2018-11-23 19:05
【摘要】:提出基于视觉显著性特征的乳腺钼靶X射线肿块检测方法:首先从局部显著性、全局显著性和稀少性三方面计算显著图,利用显著图加权增强目标;然后根据前景目标数迭代确定分割阈值对加权后图像阈值分割;最后将分割后的前景区域视为疑似肿块区域,利用融合显著性特征及基于中心-轮廓距离的肿块形态特征识别肿块。本文利用MIAS数据库中多幅的乳腺X线图像进行实验验证,结果表明,本文提出的方法能够准确地分割肿块区域,肿块识别准确性较高。
[Abstract]:A method for mammography detection of mammary mammography masses based on visual saliency was proposed. Firstly, salience maps were calculated from three aspects: local saliency, global saliency and sparsity, and weighted enhancement targets by saliency maps. Then the weighted image threshold is determined according to the foreground target number iteration. Finally, the segmented foreground area is regarded as the suspected mass area, and the fusion salient feature and the mass morphological feature based on centro-contour distance are used to identify the mass. In this paper, many mammographic images in MIAS database are used for experimental verification. The results show that the method proposed in this paper can segment the area of mass accurately, and the accuracy of mass recognition is high.
【作者单位】: 辽宁石油化工大学信息与控制工程学院;辽宁工程技术大学电子与信息工程学院;
【基金】:辽宁省教育厅科学研究一般项目(L2012112)资助项目
【分类号】:R737.9;TP391.41
本文编号:2352439
[Abstract]:A method for mammography detection of mammary mammography masses based on visual saliency was proposed. Firstly, salience maps were calculated from three aspects: local saliency, global saliency and sparsity, and weighted enhancement targets by saliency maps. Then the weighted image threshold is determined according to the foreground target number iteration. Finally, the segmented foreground area is regarded as the suspected mass area, and the fusion salient feature and the mass morphological feature based on centro-contour distance are used to identify the mass. In this paper, many mammographic images in MIAS database are used for experimental verification. The results show that the method proposed in this paper can segment the area of mass accurately, and the accuracy of mass recognition is high.
【作者单位】: 辽宁石油化工大学信息与控制工程学院;辽宁工程技术大学电子与信息工程学院;
【基金】:辽宁省教育厅科学研究一般项目(L2012112)资助项目
【分类号】:R737.9;TP391.41
【参考文献】
相关期刊论文 前1条
1 裴晓敏;李文娜;;超像素优化Snake模型的乳腺X线图像胸肌分割[J];光电子·激光;2015年08期
【二级参考文献】
相关期刊论文 前8条
1 南柄飞;穆志纯;;基于SLIC0融合纹理信息的超像素分割方法[J];仪器仪表学报;2014年03期
2 汪源源;原宗良;唐三;;利用自适应纹理分布的活动形状分割前列腺磁共振图像[J];光学精密工程;2013年09期
3 王春瑶;陈俊周;李炜;;超像素分割算法研究综述[J];计算机应用研究;2014年01期
4 张胜君;;基于相关向量机的乳腺X线图像结构扭曲检测[J];光电子.激光;2013年04期
5 祝世平;郭智超;高洁;马丽;;基于Snake活动轮廓模型的视频跟踪分割方法[J];光电子.激光;2013年01期
6 石锐;黄向娟;;基于改进Snake模型的肺部图像分割[J];计算机工程与应用;2014年15期
7 李艳凤;陈后金;杨娜;张胜君;;基于解剖学特征的乳腺X线图像胸肌分割[J];自动化学报;2013年08期
8 ;Automatic pectoral muscle boundary detection in mammograms based on Markov chain and active contour model[J];Journal of Zhejiang University-Science C(Computer & Electronics);2010年02期
,本文编号:2352439
本文链接:https://www.wllwen.com/yixuelunwen/zlx/2352439.html