Multiresolution elastic matching
Computer Vision, Graphics, and Image Processing
Validation of Non-rigid Registration Using Finite Element Methods
IPMI '01 Proceedings of the 17th International Conference on Information Processing in Medical Imaging
Deformable templates using large deformation kinematics
IEEE Transactions on Image Processing
Scale Space'03 Proceedings of the 4th international conference on Scale space methods in computer vision
| Hi-index | 0.00 |
Non-rigid registration can automatically quantify small changes in volume of anatomical structures over time by means of segmentation propagation. Here we use a non-rigid registration algorithm based on optimising normalised mutual information to quantify small changes in brain ventricular volume in MR images of a group of five patients treated with growth hormone replacement therapy and a control group of six volunteers. The lateral ventricles are segmented from each subject image by registering the brainweb image [1] which has this structure delineated. The mean (standard deviation) volume change measurements are 1.09cc (0.73cc) for the patient group and 0.08cc (0.62cc) for the volunteer group, this difference is statistically significant at the 1% level. We validate our volume change measurements by comparing them to previously published results obtained by visual inspection of difference images, and demonstrate high rank correlation coefficient (p = 0.7, n=11).