Interpolation artefacts in mutual information-based image registration
Computer Vision and Image Understanding - Special issue on analysis of volumetric image
Multi-modal Volume Registration Using Joint Intensity Distributions
MICCAI '98 Proceedings of the First International Conference on Medical Image Computing and Computer-Assisted Intervention
3-D Deformable Registration of Medical Images Using a Statistical Atlas
MICCAI '99 Proceedings of the Second International Conference on Medical Image Computing and Computer-Assisted Intervention
Towards a Better Comprehension of Similarity Measures Used in Medical Image Registration
MICCAI '99 Proceedings of the Second International Conference on Medical Image Computing and Computer-Assisted Intervention
Efficient Semiautomatic Segmentation of 3D Objects in Medical Images
MICCAI '00 Proceedings of the Third International Conference on Medical Image Computing and Computer-Assisted Intervention
| Hi-index | 0.00 |
A new similarity measure for volume registration is proposed, which uses using the assumption that the joint distribution of a target tissue is known. This similarity measure is designed so that it can deal with the tissue slide that occurs at boundaries between the target tissue and other tissues. Pre-segmentation of the target tissue is unnecessary. We intend to apply the proposed measure to registering volumes acquired at different time-phases in dynamic CT scans of the liver using contrast materials. In order to derive the similarity measure, we first formulate the ideal case where the joint distributions of all the tissues are known, after which we derive the measure for a realistic case where only the joint distribution of the target tissue is known. We applied the proposed measure experimentally to eight dynamic CT data sets of the liver. After describing a practical method for estimating the joint distribution of the liver from real CT data, we show that the problem of tissue slide is effectively dealt with using the proposed measure.