肿块边缘环状特征提取及语义融合分析
首发时间:2016-05-19
摘要:有效的特征提取方法是获取精确分类结果的关键。由于现有的乳腺肿块区域特征提取和分析方法大多依据自然图像的统计特性,没有充分利用肿块的生物特性和扩散方式,本文提出了一种基于各向异性边缘环状区域的乳腺肿块特征提取方法和基于语义相似度的乳腺肿块特征融合方法,突出了肿块边缘信息在良恶性分类中的重要性,使提取的特征既包含图像的语义信息,又包含图像的空间信息,降低了算法复杂度,提高了运算效率。实验结果表明,本文提出的特征提取和特征融合方法能够有效地表达乳腺肿块图像的空间结构和语义信息,具有较高的分类性能,为计算机辅助诊断系统的研究提供了新的思路。
For information in English, please click here
Marginal ring feature extraction and semantic fusion analysis for mass
Abstract:Effective feature extraction method is the key to obtain accurate classification results. Because most of existing feature extraction methods for breast mass are based on the statistical characteristics of natural images, without the biological characteristics and diffusion ways of the mass, we propose a feature extraction method based on anisotropy Marginal ring feature extraction method and a feature fusion method based on semantic similarity, which highlight the importance of edge information in the mass classification and make the extracted feature contains both the semantic and spatial information of the image. Moreover, the algorithm complexity is reduced and operation efficiency is improved. Our experiment results show that the proposed feature extraction and fusion methods can express spatial structure and semantic information of mass effectively. The methods we proposed improve the classification accuracy and provide a new way for the research of CAD system.
Keywords: image processing feature extraction feature fusion Mammogram
论文图表:
引用
No.4689849114892014****
同行评议
共计0人参与
勘误表
肿块边缘环状特征提取及语义融合分析
评论
全部评论0/1000