Ali Zifan and Panos Liatsis and Panagiotis Kantartzis and
Manolis Gavaises and Nicos Karcanias and Demosthenes Katritsis
Automatic 3D Reconstruction of Coronary Artery Centerlines from Monoplane Xray Angiogram Images
105 - 110
2008
2
3
International Journal of Medical and Health Sciences
https://publications.waset.org/pdf/3093
https://publications.waset.org/vol/15
World Academy of Science, Engineering and Technology
We present a new method for the fully automatic 3D
reconstruction of the coronary artery centerlines, using two Xray
angiogram projection images from a single rotating monoplane
acquisition system. During the first stage, the input images are
smoothed using curve evolution techniques. Next, a simple yet
efficient multiscale method, based on the information of the Hessian
matrix, for the enhancement of the vascular structure is introduced.
Hysteresis thresholding using different image quantiles, is used to
threshold the arteries. This stage is followed by a thinning procedure
to extract the centerlines. The resulting skeleton image is then pruned
using morphological and pattern recognition techniques to remove
nonvessel like structures. Finally, edgebased stereo correspondence
is solved using a parallel evolutionary optimization method based on
f symbiosis. The detected 2D centerlines combined with disparity
map information allow the reconstruction of the 3D vessel
centerlines. The proposed method has been evaluated on patient data
sets for evaluation purposes.
Open Science Index 15, 2008