Picture languages in medical pattern knowledge representation and understanding

Abstract

In the paper, there will be presented the new way of application of structural methods of pattern recognition, in the form of picture languages, for creation of knowledge representation for medical pattern analysis and understanding. Specialist medical databases storing data in visual form constitute a large group among multimedia databases; those patterns originate from numerous diagnostic examinations of practically all organs of the human body. One of the main problems in the fast accessing and interpretation of such visual information is the way of transformation of these visual data into a form enabling intelligent analysis and understanding of medical meaning of these patterns. The basic problems leading to achieve this goal is the method of representation and indexing the important objects constituting the data contents. In the paper we describe some examples presenting ways of applying picture languages techniques in the creation of intelligent cognitive knowledge representation for selected class of medical images. © Springer-Verlag Berlin Heidelberg 2005.