A detailed description of a new approach to perceptual analysis and processing of medical images is given. Instead of traditional pattern recognition a new method of image analysis is presented, based on a syntactic description of the shapes selected on the image and graph-grammar parsing algorithms. This method of "Image Understanding" can be found as a model of mans' cognitive image understanding processes. The usefulness for the automatic understanding of the merit of medical images is demonstrated as well as the ability for giving useful diagnostic descriptions of the illnesses. As an application, the production of a content-based, automatically generated index for arranging and for searching medical images in multimedia medical databases is presented.

Inhalt

1. What is Image Understanding Technology and why do we need it?.- 1.1 Methods of Medical Image Acquisition.- 1.2. Analysis and interpretation of medical images.- 1.3. What new values can add to this scheme 'automatic understanding' ?.- 1.4. Areas of applications for the automatic understanding of images.- 1.4.1. T-formed area of applications for the automatic understanding of medical images.- 1.4.2. The Automatic understanding of medical images as a tool for the preliminary classification of imaging screening data.- 1.4.3. Automatic understanding in difficult medical problems.- 1.4.4. Automatic understanding of images as a tool for semantic searching in data bases and successful web crawling.- 2. A General Description of the Fundamental Ideas Behind Automatic Image Understanding.- 2.1. Fundamental assumptions.- 2.2. What does image understanding mean?.- 2.3. Linguistic description of images.- 2.4. The use of graph grammar to cognitive resonance.- 3. Formal Bases for the Semantic Approach to Medical Image Processing Leading to Image Understanding Technology.- 3.1 Fundamentals of syntactic pattern recognition methods.- 3.1.1 Definitions and basic formalisms associated with syntactic pattern recognition methods.- 3.1.2 Principles of syntax analysers operation.- 3.2 Characteristic features and advantages of structural approaches to medical image semantic analysis.- 4. Examples of Structural Pattern Analysis and Medical Image Understanding Application to Medical Diagnosis.- 4.1. Introduction.- 4.2. Pre-processing Methods Designed to Process Selected Medical Images.- 4.2.1. A Need to Apply Medical Data Pre-processing.- 4.2.2. Recommended Stages of Medical Data Pre-processing.- 4.2.3. Segmentation and Filtering of Images.- 4.2.4. Skeletonisation of the Analysed Anatomical Structures.- 4.2.5. Analysis of Skeleton Ramifications.- 4.2.6. Smoothing skeletons of the analysed anatomical structures.- 4.2.7. Transformation Straightening the External Contours of Analysed Objects.- 4.2.8. Straightening Transformation Algorithm.- 4.2.9. Basic Advantages of the Proposed Pre-processing Method.- 4.3. Making Lexical Elements for the Syntactic Descriptions of Examined structures.- 4.4. Structural Analysis of Coronary Vessels.- 4.4.1 Syntactic Analysis and Diagnosing Coronary Artery Stenoses.- 4.4.2 Recognition Results Obtained with the Use of Context-free Grammar.- 4.4.3 Conclusion.- 4.5. Structural Analysis and Understanding of Lesions in Urinary Tract.- 4.5.1 Diagnosing Stenosis of the Ureter Lumen.- 4.5.2 Application of Graph Grammar in the Analysis of Renal Pelvis Shape.- 4.6. Syntactic Methods Supporting the Diagnosis of Pancreatitis and Pancreas Neoplasm.- 4.6.1 Context-free Grammar in the Analysis of Shapes of Pancreatic Ducts.- 4.6.2 Languages of Shape Feature Description in the Analysis of Pancreatic Duct Morphology.- 4.6.3 Results of Syntactic Method Analysis of Pancreatic Ducts.- 4.9. Conclusions.- 5. The application of the Image Understanding Technology to Semantic Organisation and Content-Based Searching in Multimedia Medical Data Bases.- 6. Strengths and Weaknesses of the Image Understanding Technology Compared to Previously Known Approaches.- References.