On sequential Monte Carlo sampling methods for Bayesian filtering
Statistics and Computing
Real-Time Registration of 3D Cerebral Vessels to X-ray Angiograms
MICCAI '98 Proceedings of the First International Conference on Medical Image Computing and Computer-Assisted Intervention
The Correlation Ratio as a New Similarity Measure for Multimodal Image Registration
MICCAI '98 Proceedings of the First 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
Alignment by maximization of mutual information
ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
Iterative x-ray/ct registration using accelerated volume rendering
Iterative x-ray/ct registration using accelerated volume rendering
A tutorial on particle filters for online nonlinear/non-GaussianBayesian tracking
IEEE Transactions on Signal Processing
Accurate and precise 2D-3D registration based on X-ray intensity
Computer Vision and Image Understanding
An adaptive Monte Carlo approach to phase-based multimodal image registration
IEEE Transactions on Information Technology in Biomedicine
New CTA protocol and 2d-3d registration method for liver catheterization
MICCAI'06 Proceedings of the 9th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part I
Stochastic 3d motion compensation of coronary arteries from monoplane angiograms
MICCAI'12 Proceedings of the 15th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part I
Hi-index | 0.00 |
Digital subtraction angiography (DSA) reconstructions and 3D Magnetic Resonance Angiography (MRA) are the modalities of choice for diagnosis of vascular diseases. However, when it comes to treatment through an endovascular intervention, only two dimensional lower resolution information such as angiograms or fluoroscopic images are usually available. Overlaying the pre-operative information from high resoluion acquisition onto the images acquired during intervention greatly helps physician in performing the operation. We propose to register pre-operative DSA or MRS with intra-operative images to bring the two data sets into a single coordinate frame. The method uses the vascular structure, which is present and visible from most of DSA, MRA and x-ray angiogram and fluoroscopic images, to determine the registration parameters. A robust multiple hypothesis framework is built to minimize a fitness measure between the 3D volume and the 2D projection. The measure is based on the distance map computed from the vascular segmentation. Particle Filters are used to resample the hypothesis, and direct them toward the feature space’s zones of maximum likelihood. Promising experimental results demonstrate the potentials of the method.