Scale-Space and Edge Detection Using Anisotropic Diffusion
IEEE Transactions on Pattern Analysis and Machine Intelligence
An augmented Fast Marching Method for computing skeletons and centerlines
VISSYM '02 Proceedings of the symposium on Data Visualisation 2002
Muliscale Vessel Enhancement Filtering
MICCAI '98 Proceedings of the First International Conference on Medical Image Computing and Computer-Assisted Intervention
Fully Automatic 3D/2D Subtracted Angiography Registration
MICCAI '99 Proceedings of the Second International Conference on Medical Image Computing and Computer-Assisted Intervention
MICCAI '99 Proceedings of the Second International Conference on Medical Image Computing and Computer-Assisted Intervention
Artificial Intelligence: A Modern Approach
Artificial Intelligence: A Modern Approach
Alignment by maximization of mutual information
ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
A Multilevel Banded Graph Cuts Method for Fast Image Segmentation
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
Skeleton Pruning by Contour Partitioning with Discrete Curve Evolution
IEEE Transactions on Pattern Analysis and Machine Intelligence
ISBI'10 Proceedings of the 2010 IEEE international conference on Biomedical imaging: from nano to Macro
MIAR'10 Proceedings of the 5th international conference on Medical imaging and augmented reality
Hi-index | 0.00 |
Minimally invasive abdominal aortic aneurysm stenting can be greatly facilitated by overlaying the pre-operative 3-D model of the abdominal aorta onto the intra-operative 2-D X-ray images. Accurate 2-D/3-D registration in 3-D space makes the 2-D/3-D overlay robust to the change of C-Arm angulations. Typically at least two X-ray images showing the abdominal aorta with contrast medium from different angles are needed for an accurate registration in 3-D space. In this paper, a novel 2-D/3-D registration technique is proposed for using only one image with contrast medium in the abdominal aorta and one native image showing the spine to achieve accurate registration of the abdominal aorta in 3-D. The proposed method utilizes the two X-ray images in an integrated but differentiated way in order to best utilize the complementary information provided by the two types of images. A hierarchical registration scheme is deployed by a sensible partition of the registration parameter space based on the image acquisition protocol. The proposed method was validated using both synthetic and clinical datasets, and achieved significantly improved accuracy and robustness compared to the conventional methods.