Multiple view geometry in computer vision
Multiple view geometry in computer vision
The Geometry of Multiple Images: The Laws That Govern The Formation of Images of A Scene and Some of Their Applications
Muliscale Vessel Enhancement Filtering
MICCAI '98 Proceedings of the First International Conference on Medical Image Computing and Computer-Assisted Intervention
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
Vessel enhancement in 2D angiographic images
FIMH'07 Proceedings of the 4th international conference on Functional imaging and modeling of the heart
| Hi-index | 0.00 |
We describe a technique for 4D-reconstruction of coronary arteries from a sequence of monoplane X-ray angiograms. An initial 3D model of coronary centerlines is reconstructed from two appropriate views. A 3D-2D registration framework is formulated in which the model deforms in space to best fit the given angiograms. The 3D motion model is hierarchical and includes rigid, affine and B-spline transformations. The registration is guided by a sum of energy terms which measures the goodness of the 3D-2D mapping and constrains the deformation of the model. The method is tested on three sequences of patient data, each containing 248 frames. The registration time for one frame varies between one and four minutes.