A monohierarchical multiaxial classification code for medical images in content-based retrieval

Abstract

Large efforts have been made for general applications of content-based image retrieval (CBIR). Established CBIR-systems globally evaluate color, texture, and also shape for retrieval. In medical imaging, local image characteristics are fundamental for image interpretation, which is based on a large amount of a-priori knowledge. Therefore, CBIR is rather seldom applied to medical images. Successful approaches strongly focus on a certain imaging modality and restrict queries to a well-defined diagnostic background. With respect to a general image retrieval in medical applications (IRMA), the system needs to determine the kind of image dealing with at a very early stage of processing to enable knowledge modeling required in further processing steps. In particular, 1. the imaging modality including technical parameters, 2. the orientation of the image with respect to the body, 3. the body region examined, and 4. the biological system under evaluation must be determined in order to select appropriate local techniques for image analysis. These four aspects build the axes of a general classification code for medical images. All axes are monohierarchically structured into three or five levels. The code is applied within the IRMA-project for medical image retrieval but also applicable for a great variety of applications in medical imaging in general.