Graph Image Language Techniques Supporting Advanced Classification and Cognitive Interpretation of CT Coronary Vessel Visualizations - Computational Intelligence Paradigms in Advanced Pattern Classification - page 98

for determining mutually corresponding elements for every subsequent animation
frame based on the geometric relations in 3D space.
5.3 Graph-Based Linguistic Formalisms in Spatial Modelling of
Coronary Vessels
As the structure of coronary vessels is characterized by three basic types of artery
distribution on the heart surface, the proposed methods should include three basic
cases: balanced artery distribution, right artery dominant and left artery dominant.
For the purposes of this article, in further considerations we will focus on the bal-
anced distribution of coronary arteries which is the most frequent type seen by di-
agnosticians (60-70% of all cases) [2]. To help represent the examined structure of
coronary vascularisation with a graph, it is necessary to define primary compo-
nents of the analyzed image and their spatial relations, which will serve to extract
and suitably represent the morphological characteristics significant for understand-
ing the pathology shown in the image. It is therefore necessary to identify individ-
ual coronary arteries and their mutual spatial relations. To ease this process, the
projection selected for analyzing was skeletonised. This made it possible to obtain
Fig. 6 Coronary vascularisation projection and its skeleton produced using the Pavlidis
skeletonising algorithm