基于张量积扩散与纹理元相似的医学图像检索  

Medical image retrieval with diffusion on tensor product graph and similarity of textons

作　　者：黄碧娟[1,2] 唐奇伶[2] 刘海华[2] 唐文峰[1] 

机构地区：[1]中南民族大学生物医学工程学院,武汉430074 [2]医学信息分析及肿瘤诊疗湖北省重点实验室(中南民族大学),武汉430074

出　　处：《计算机应用》2016年第3期815-819,共5页journal of Computer Applications

基　　金：国家自然科学基金重大研究计划培育项目(GZY13019);中央高校基金资助项目(CZZ14003)~~

摘　　要：针对医学图像检索中相似性表达的自身困难,以及噪声影响的问题,提出一种通过张量积图进行扩散,利用其他数据点的上下信息改进基于纹理元的成对相似性度量的方法。首先,采用纹理元的统计方法进行医学图像特征描述和提取,并通过对纹理元相似性加权,得到图像的成对相似性;然后,利用张量积图沿着数据点的内在流形进行相似性的传播,实现全局的相似性度量。在Image CLEFmed 2009上的实验结果表明,该算法与基于Gabor的检索算法相比,其类平均精度提高了32%,与基于尺度不变特征转换(SIFT)的检索算法相比,其类平均精度提高了19%,能良好地应用于医学图像检索。Concerning the difficulty of its similarity to the expression and the effects of noise in medical image retrieval,a diffusion-based approach on a tensor product graph was proposed to improve the texton-based pairwise similarity metric by context information of other database objects. Firstly,medical image features were described and extracted by texton-based statistical method,and then the pairwise similarities were obtained with weights determined by the similarities between textons.A global similarity metric was achieved by utilizing the tensor product graph to propagate the similarity information along the intrinsic structure of the data manifold. Experimental results of Image CLEFmed 2009 database show that,the proposed algorithm improves the performance by an average class accuracy of 32% and 19% compared with the Gabor-based retrieval algorithm and the Scale-Invariant Feature Transform（ SIFT）-based retrieval algorithm respectively,which can be applied to medical image retrieval.

关 键 词：医学图像检索 纹理元 张量积图 扩散 相似性 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]