Nonlinear processing and semantic content analysis in medical imaging

Abstract

Traditional approach to automated analysis of medical data is mostly based on statistical or theoretical-decision methods of pattern recognition. Using such methods, we can obtain many valuable items, e.g. tracking of patients moving, control of medical treatment etc. But in medical informatics are still many problems not solvable by computers and reserved for human medical staff. Such problems can be solved by development of scientific research towards machine intelligence. We try to show how computer can understand medical date instead of simple processing, and analysis. Sometimes it may be useful to make semantic content analysis leading to automatic understanding of medical data e.g. for intelligent helping of diagnosis process or for semantic based searching in medical databases. We present the application of cognitive-based approach for intelligent semantic analysis allowing automatically describe important diagnostic features of analyzed images. This approach is based on a special kind of image description languages and grammar formalism. During the linguistic analysis of medical patterns, we can solve problem of generalization of features of selected image and obtaining semantic content description of the image. Most important part of this analysis depends on the cognitive resonance process, when features of real image are compared with some kind of expectations taken from the knowledge base containing knowledge regarding pathological cases, originating from medical practice.