Intrapatient, B-spline transformation, mutual information, rigidity penalty
CT and MR images in the pelvic region.
Acquired on a 3T Philips Ingenia.
Acquired on Brilliance Big Bore.
MR and CT scans were acquired for 27 male patient for radiotherapy purposes. Non-rigid registration was used to align and resample the MR and CT volumes to train a deep learning model for synthetic CT generation. MR was the fixed image and CT the moving image.
For parameter files see the Elastix Model Zoo repository on GitHub.
Elastix version: 4.9
Command line call:
elastix -p par0059_rigid.txt -p par0059_bspline.txt –f MR_image.nii.gz -m CT_image.nii.gz -out output_dir -fMask MR_body_mask.nii.gz
Florkow et al. (2019), Deep learning-based MR-to-CT synthesis: the influence of varying gradient echo-based MR images as input channels, under submission
© 2020 Viktor van der Valk