[1]顾广娟,宋立新,王立,等.基于SVM和形态学的乳腺X线影像MROI提取技术[J].哈尔滨理工大学学报,2009,(06):47-51.
 GU Guang-juan,SONG Li-xin,WANG Li.A MROI Extracting Technique in Mammograms Based on SVM and Morphology[J].哈尔滨理工大学学报,2009,(06):47-51.
点击复制

基于SVM和形态学的乳腺X线影像MROI提取技术()
分享到:

《哈尔滨理工大学学报》[ISSN:1007-2683/CN:23-1404/N]

卷:
期数:
2009年06期
页码:
47-51
栏目:
电气与电子工程
出版日期:
2009-12-25

文章信息/Info

Title:
A MROI Extracting Technique in Mammograms Based on SVM and Morphology
作者:
顾广娟; 宋立新; 王立;
哈尔滨理工大学电气与电子工程学院; 黑龙江省医院;
Author(s):
GU Guang-juan1; SONG Li-xin1; WANG Li2
1.School of Electric and Electronic Engineering; Harbin University of Science and Technology; Harbin 150040; China; 2.Heilongjiang Provice Hospital; Harbin 150036; China
关键词:
乳腺X线影像 微钙化点感兴趣区域(MROI) 支持向量机(SVM) 数学形态学 纹理特征
Keywords:
mammogram micro-calcification region of interest(MROI) support vector machine(SVM) morphology texture feature
分类号:
TP391.41
文献标志码:
A
摘要:
针对目前乳腺X线影像微钙化点感兴趣区域的提取方法复杂,效果不理想,保留微钙化区域的能力及排除非病变区域的能力差等方面的问题.依据微钙化点区域和非微钙化点区域的特征差异,提出了利用支持向量机来对乳腺组织子块是否是微钙化点区域进行分类,引入微钙化点的检测方法,利用形态学对含微钙化点的可疑区域进行检测,最后判断微钙化点簇,完成提取.实验证明,该方法操作简单,检出率较高,且假阳性得到明显降低,可大幅提高后期辅助诊断的效率.
Abstract:
To solve the problem that the methods for extraction of micro-calcification region of interest in mammograms are complicated,but the results are not perfect at present,and the abilities of retaining micro-calcification region and discarding normal region need to be improved,according to the features differences between micro-calcification region and normal region,the paper presents a methed to classify breast tissue sub-blocks which are whether micro-calcification region or normal region by support vector m...

备注/Memo

备注/Memo:
黑龙江省教育厅科学技术研究项目(11511086)
更新日期/Last Update: 2010-04-13