Information Technology Reference
In-Depth Information
Chapter 6
Graph Image Language Techniques
Supporting Advanced Classification and
Cognitive Interpretation of CT Coronary
Vessel Visualizations
Mirosław Trzupek
AGH University of Science and Technology
Faculty of Electrical Engineering, Automatics, Computer Science and Electronics
Department of Automatics
al. A. Mickiewicza 30
30-059 Krakow
Abstract.
The aim of this chapter is to present a graph image language techniques
to the development of a syntactic semantic description of spatial visualizations of
coronary artery system. The proposed linguistic description makes it possible to
intelligently model the examined structure and then to advanced classification and
cognitive interpretation of coronary arteries (automatically find the locations of
significant stenoses and identify their morphometric diagnostic parameters). This
description will be correctly formalised using ETPL(k) (Embedding Transforma-
tion-preserved Production-ordered k-Left nodes unambiguous) graph grammars,
supporting the search for stenoses in the lumen of arteries forming parts of the
coronary vascularisation. ETPL(k) grammars generate IE graphs (indexed edge-
unambiguous) which can unambiguously represent 3D structures of heart muscle
vascularisation visualised in images acquired during diagnostic examinations with
the use of spiral computed tomography.
1 Introduction
Coronary Heart Disease (CHD) is the leading cause of death in the industrialized
world. Early diagnosis and risk assessment are widely accepted strategies to com-
bat CHD [25]. Recent years have seen a rapid development of stereovision as well
as algorithms for the 3D visualisation and reconstruction of 3D objects, which has
become noticeable in modern medical diagnostics as well [5][7][17]. It has be-
come possible not just to reliably map the structures of a given organ in 3D, but
also to accurately observe its morphology. Such modern visualisation techniques
are now used in practically all types of image diagnostics as well as in many other
medical problems. Below, the author discusses the results of his research on the
Search WWH ::
Custom Search