Content-based medical image retrieval(CBMIR) has been one of the most vivid research areas in medical image process. This paper attempts to provide a comprehensive survey of the typical CBMIR systems, including low-level image feature extraction, retrieval objective, and application areas, and also discuss some existing deficiencies such as poor portability, limitations of 2D image retrieval and imperfect retrieval performance evaluation methods. Based on these analysis, a multistage and multi -features medical image.retrieval system framework has been designed, which not only combines text-based with content-based retrieval, but also integrates local-based ROI features with global image feature, as well as 2D features with 3D features. It aims to improve the accuracy rate of medical image retrieval effectively and meet the needs of different users.[Chinese Medical Equipment Journal,2011,33(3):86-88]%分析了国内外一些典型医学图像检索(CBMIR)系统及其关键技术,包括底层特征提取方法、检索目标以及系统的应用对象等,并对CBMIR系统存在的问题,如可移植性差、二维图像检索的局限性等进行了讨论,提出了多级多特征的CBMIR系统框架.该框架将文本与内容相结合、纹理与形状相结合、全局与ROI相结合、二维图像与三维图像相结合,旨在提高检索准确度,并满足不同用户的检索需求.
展开▼
