File(s) under permanent embargo
Estimation of large motion in lung CT by integrating regularized keypoint correspondences into dense deformable registration
journal contribution
posted on 2023-06-09, 20:23 authored by Jan Rühaak, Thomas Polzin, Stefan Heldmann, Ivor SimpsonIvor Simpson, Heinz Handels, Jan Modersitzki, Mattias P HeinrichWe present a novel algorithm for the registration of pulmonary CT scans. Our method is designed for large respiratory motion by integrating sparse keypoint correspondences into a dense continuous optimization framework. The detection of keypoint correspondences enables robustness against large deformations by jointly optimizing over a large number of potential discrete displacements, whereas the dense continuous registration achieves subvoxel alignment with smooth transformations. Both steps are driven by the same normalized gradient fields data term. We employ curvature regularization and a volume change control mechanism to prevent foldings of the deformation grid and restrict the determinant of the Jacobian to physiologically meaningful values. Keypoint correspondences are integrated into the dense registration by a quadratic penalty with adaptively determined weight. Using a parallel matrix-free derivative calculation scheme, a runtime of about 5 min was realized on a standard PC. The proposed algorithm ranks first in the EMPIRE10 challenge on pulmonary image registration. Moreover, it achieves an average landmark distance of 0.82 mm on the DIR-Lab COPD database, thereby improving upon the state of the art in accuracy by 15. Our algorithm is the first to reach the inter-observer variability in landmark annotation on this dataset.
History
Publication status
- Published
File Version
- Published version
Journal
IEEE Transactions on Medical ImagingISSN
0278-0062Publisher
Institute of Electrical and Electronics EngineersExternal DOI
Issue
8Volume
36Page range
1746-1757Department affiliated with
- Informatics Publications
Research groups affiliated with
- Data Science Research Group Publications
Full text available
- No
Peer reviewed?
- Yes
Legacy Posted Date
2020-01-24First Compliant Deposit (FCD) Date
2021-01-28Usage metrics
Categories
No categories selectedKeywords
computerised tomography;image registration;lung;medical image processing;motion compensation;optimisation;pneumodynamics;dense deformable registration;pulmonary CT scan registration;large respiratory motion estimation;sparse keypoint correspondence integration;dense continuous optimization framework;curvature regularization mechanism;volume change control mechanism;parallel matrix-free derivative calculation scheme;time 5 min;distance 0.82 mm;Lungs;Optimization;Computed tomography;Robustness;Jacobian matrices;Image edge detection;Radio frequency;Computed tomography;COPD;image registration;Jacobian determinant;keypoints;lung;Markov random fields;Algorithms;Humans;Lung;Motion;TomographyX-Ray Computed