Computer graphics (2nd ed.): C version
Computer graphics (2nd ed.): C version
3D+t Modeling of Coronary Artery Tree from Standard Non Simultaneous Angiograms
MICCAI '01 Proceedings of the 4th International Conference on Medical Image Computing and Computer-Assisted Intervention
A hierarchical approach to color image segmentation using homogeneity
IEEE Transactions on Image Processing
| Hi-index | 0.00 |
In this paper, a model-based trackingalgorithm is implemented to track the motion ofcoronary arteries. This idea was first introduced byKong et al. [10] in 1971 to assess the heart contractionusing for this purpose the coronary bifurcationsas natural landmarks on the epicardial surface.The method implemented here assumes that a coronarybifurcation can be represented by a simple Ygeometric structure. A Fuzzy C-Means algorithmis first used to segment the coronary bifurcations.Then the segmented bifurcation is skeletonized toproduce the expected Y shape. To define the Yshape geometrically, its center and the branch anglesare computed. The tracking process can nowtake place by simply looking for a similar Y shapein the next frame and so on. Using actual cineangiograms,it is demonstrated that tracking the movementof coronaries with this geometrical approach ismore accurate and robust then using a standard correlationwindow methodology.