Graph image language techniques supporting radiological, hand image interpretations

This paper will present a new approach to the interpretation of complex X-ray images, an approach taking advantage of artificial intelligence and soft computing. The tasks of the analysis and the interpretation of the cognitive meaning of selected medical diagnostic images are made possible owing to the application of graph image languages based on EDG-type grammars. The subject of this paper will be to present the wide range of semantic interpretation possibilities of hand and wrist radiogrammes using language formalisms. The objective of the analysis conducted is to detect pathological lesions of the in-born or of the acquired character as well as bone morphology lesions and bone dislocation as seen in bone defects. The application of graph formalisms, based on EDG languages, allows us to make an effective classification of its meaning with polynomial complexity.