A FULLY AUTOMATED IDENTIFICATION OF CORONARY BORDERS FROM THE TREE STRUCTURE OF CORONARY ANGIOGRAMS

The accurate assessment of variations in coronary arterial dimensions plays an important role in the evaluation of ischemic heart disease an d the effectiveness of treatment: Although there exist a variety of ed ge detection algorithms in the literature, most of them are human inte ractive and may provide a poor estimate on coronary lesion. In this pa per, we present a new method for automatic identification of arterial borders. The proposed algorithm makes use of mathematical morphology t o segment blood vessels which follow a tree structure, based on a prio ri knowledge of coronary anatomy. Finally, an adaptive tracking strate gy is applied to automatically identify 2-D arterial borders along bot h sides of the vessels. This is accomplished by using an edge detectio n model at a branching point, matched filters, and the tree structure of the coronary artery. Experimental results show that our approach no t only is insensitive to the intensity variations of background and no ise, but also can extract the boundary of the coronary artery accurate ly.