Title :
Automatic artery skeleton extraction
Author :
Haris, K. ; Efstratiadis, S.N. ; Maglaveras, N. ; Gourassas, J. ; Pappas, C. ; Louridas, G.
Author_Institution :
Fac. of Med., Aristotelian Univ. of Thessaloniki, Greece
fDate :
30 Oct-2 Nov 1997
Abstract :
A new approach to the problem of extracting the skeletons of arteries in angiograms is proposed. The peaks, ridges and saddles of the digitized angiogram are considered as candidate artery skeleton points and are determined by analyzing the first and second order partial derivatives of the angiogram. Next, the binary image of candidate skeleton points is constructed and thinned. The large number of short linear branches, due to noise and irrelevant anatomical structures, are eliminated through connected component labeling of skeleton curves and pruning. Experimental results on digitized angiograms are presented
Keywords :
blood vessels; diagnostic radiography; feature extraction; medical image processing; automatic artery skeleton extraction; candidate artery skeleton points; connected component labeling; digitized angiogram; irrelevant anatomical structures; medical diagnostic imaging; peaks; pruning; ridges; saddles; short linear branches; skeleton curves; Arteries; Biomedical imaging; Biomedical informatics; Cardiology; Filters; Hospitals; Labeling; Medical diagnostic imaging; Skeleton; Surface topography;
Conference_Titel :
Engineering in Medicine and Biology Society, 1997. Proceedings of the 19th Annual International Conference of the IEEE
Conference_Location :
Chicago, IL
Print_ISBN :
0-7803-4262-3
DOI :
10.1109/IEMBS.1997.757792