Advances in syntactic imaging techniques for perception of medical images

With the advances in pattern recognition technology, information systems ha ve been applied to medical databases throughout the world. The most importa nt problems in such access are how the pathological lesions can be efficien tly recognized and how information in the respective databases can be summa rized to enable intelligent selection of interesting cases of illness based on visual queries. The main goal of this paper is a presentation of the po ssibilities of the application of structural graph grammar-based methods of computer medical image analysis to the recognition and creation of a seman tic description of the symptoms of lesions in the forms of local stenoses o f the lumen of coronary arteries., and to the detection of pathological sig ns in upper parts of the ureter ducts and renal calyxes. An analysis of the correct morphology of these structures is possible owing to the applicatio n of sequence and graph methods from the group of syntactic methods of patt ern recognition. In the analysis of coronary artery images, the main object ive is computer-aided early diagnosis of the different forms of cardiac isc haemic diseases. In the analysis of kidney radiograms the main goal is the recognition of local irregularities in ureter lumens. and examination of th e morphology of the renal pelvis and calyxes. The approach presented also a llows the problem of image semantic indexing to be solved for feature-based retrieval in a specialist medical database.