Elements of information theory
Elements of information theory
Selectivity Estimation Without the Attribute Value Independence Assumption
VLDB '97 Proceedings of the 23rd International Conference on Very Large Data Bases
3D Multi-Modality Medical Image Registration Using Feature Space Clustering
CVRMed '95 Proceedings of the First International Conference on Computer Vision, Virtual Reality and Robotics in Medicine
Multi-variate Mutual Information for Registration
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
Incorporating Connected Region Labelling into Automatic Image Registration Using Mutual Information
MMBIA '96 Proceedings of the 1996 Workshop on Mathematical Methods in Biomedical Image Analysis (MMBIA '96)
Improved Fast Gauss Transform and Efficient Kernel Density Estimation
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
IPMI'07 Proceedings of the 20th international conference on Information processing in medical imaging
International Journal of Computer Vision
MBIA'11 Proceedings of the First international conference on Multimodal brain image analysis
Hi-index | 0.00 |
We extend an information metric from intermodality (2-image) registration to multimodality (multiple-image) registration so that we can simultaneously register multiple images of different modalities. And we also provide the normalized version of the extensible in- formation metric, which has better performance in high noise situations. Compared to mutual information which can even become negative in the multiple image case, our metric can be easily and naturally extended to multiple images. After using a new technique to effciently compute high dimensional histograms, the extensible information metric can be effciently computed even for multiple images. To showcase the new measure, we compare the results of direct multimodality registration using high-dimensional histogramming with repeated intermodality registration. We find that registering 3 images simultaneously with the new metric is more accurate than pair-wise registration on 2D images obtained from synthetic magnetic resonance (MR) proton density (PD), MR T2 and MR T1 3D volumes from Brain Web. We perform the unbiased registration of 5 multimodality images of anatomy, CT, MR PD, T1 and T2 from Visible Human Male Data with the normalized metric and high-dimensional histogramming. Our results demonstrate the effcacy of the metrics and high-dimensional histogramming in affine, multimodality image registration.