Free-Form Registration Involving Disappearing Structures: Application to Brachytherapy MRI
Registration of two images is difficult if large deformations are induced due to the absence of a structure in one image. We propose a penalty term that minimizes the volume of the missing structure in one image during free-form registration. The registration optimum found is based on image similarity, provided that the missing volume is minimal. We demonstrate our method on cervical MR images for brachytherapy. The intrapatient registration problem involves one image in which a therapy applicator is present and one in which it is not. Experiments show improvement of registration when including the penalty term. The improvements of surface distance and overlap of the bladder and rectum (which are close to the applicator volume) provide proof of principle of our method.
Keywordsregistration regularization missing correspondence surface mesh
Unable to display preview. Download preview PDF.
- 7.Miga, M.I., Roberts, D.W., Kennedy, F.E., Platenik, L.A., Hartov, A., Lunn, K.E., Paulsen, K.D.: Modeling of retraction and resection for intraoperative updating of images. Neurosurgery 49(1), 75–84 (2001)Google Scholar
- 8.Vigneron, L.M., Noels, L., Warfield, S.K., Verly, J.G., Robe, P.A.: Serial FEM/XFEM-Based Update of Preoperative Brain Images Using Intraoperative MRI. Int. J. Biomed. Imaging 2012, 872783 (2012)Google Scholar
- 10.Commandeur, F., Velut, J., Acosta, O.: A VTK algorithm for the computation of the Hausdorff distance. Midas Journal (September 2011)Google Scholar