Automated identification of vessel contours in coronary arteriograms by an adaptive tracking algorithm

Abstract

A tracking algorithm for identification of vessel contours in digital coronary arteriograms was developed and validated. Given an initial start-of-search point, the tracking process was fully automated by utilizing the spatial continuity of the vessel's centerline, orientation, diameter, and density. The incremental sections along a major vessel were sequentially identified, based on the assumptions of geometric similarity and continuation between adjacent incremental sections. The algorithm consisted of an extrapolation-update process which was guided by a matched filter. The filter parameters were adapted to the measured lumen width. The tracking process was robust and extremely efficient as indicated by test results on synthetic images, digital subtraction angiograms, and cineangiograms. The algorithm provided accurate measurement of lumen width and percent stenosis that was relatively invariant to the vessel's orientation, dynamic range, background variation, and degree of blurring.