Estimation of Large Motion in Lung CT by Integrating Regularized Keypoint Correspondences into Dense Deformable Registration.
Jan RühaakThomas PolzinStefan HeldmannIvor J. A. SimpsonHeinz HandelsJan ModersitzkiMattias P. HeinrichPublished in: CoRR (2018)
Keyphrases
- deformable registration
- accurate registration
- image registration
- brain images
- deformation field
- b spline
- prostate cancer
- similarity metric
- statistical shape model
- displacement field
- diffusion tensor
- radiation therapy
- brain tumors
- least squares
- optical flow
- point correspondences
- keypoints
- motion parameters
- feature matching
- thin plate spline
- motion estimation
- image sequences
- three dimensional
- registration accuracy
- planar scenes
- image intensity
- ct images
- camera motion
- loss function
- mutual information
- image analysis
- moving objects