Coronary artery skeleton detection based on topographic features
Haris, K.; Efstratiadis, S.N.; Maglaveras, N.; Gourassas, J.; Pappas, C.; Louridas, G.
Studies in Health Technology and Informatics 43 Pt B: 512-516
1997
ISSN/ISBN: 0926-9630 PMID: 10179718 Document Number: 483858
A new approach to the problem of detecting the skeletons of coronary arteries in coronary angiograms is proposed. The digitized grayscale coronary angiograms are regarded as noisy sampling of the underlying continuous surface. After the application of Gaussian filtering to reduce noise, the topographic features of the smoothed image are detected based on first and second order image derivatives. Then, the candidate arteries skeleton points are detected based on the observation that arteries are smooth elongated objects having approximately a Gaussian smoothed semi-elliptical profile. Experimental results on real digitized coronary angiograms are presented.