联合图像高级语义特征和内容低级特征的医学图像检索  

Medical Image Retrieval by High Level Semantic Features and Low Level Content Features of Image

作　　者：谢天文[1] 汤伟军[2] 赵秋枫[2] 赵家骜[1] 

机构地区：[1]复旦大学远程医学中心,上海200032 [2]复旦大学华山医院放射科,上海200040

出　　处：《生物医学工程学杂志》2009年第6期1237-1240,共4页Journal of Biomedical Engineering

摘　　要：基于内容的图像检索是利用图像的低级特征来检索相似性图像,在医学图像数据库检索中有着广泛的需求,而医学图像除了包含内容信息外还包含大量的语义信息。我们提出了联合医学数字成像和通信(Digital imaging and communications in medicine,DICOM)特征与图像内容低级特征的方法来检索相似的医学图像,方法是首先从医学图像数据库中提取图像的DICOM头信息的语义信息,以便进行图像的预筛选,然后提取经预筛选后的图像和样例图像的纹理特征(双树复小波),相比两者得到与样例图像相似的图像。实验结果显示联合高级语义(DI-COM特征)和低级特征(纹理)的方法能提高检索的效能。Content-based image retrieval aims at searching the similar images using low level features, and medical image retrieval needs it for the retrieval of similar images. Medical images contain not only a lot of content data, but also a lot of semantic information. This paper presents an approach by combining digital imaging and communications in medicine （DICOM） features and low level features to perform retrieval on medical image databases. At the first step, the semantic information is extracted from DICOM header for the pre-filtering of the images, and then dual-tree complex wavelet transfrom（DT-CWT） features of pre-filtered images and example images are extracted to retrieve similar images. Experimental results show that by combining the high level semantics （DICOM features） and low level content features （texture） the retrieval time is reduced and the performance of medical image retrieval is increased.

关 键 词：基于内容的图像检索 医学数字成像和通信 双树复小波 医学图像 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]