Landmark Constrained Non-parametric Image Registration with Isotropic Tolerances

Papenberg, Nils; Olesch, Janine; Lange, Thomas; Schlag, P.M.; Fischer, Bernd

doi:10.1007/978-3-540-93860-6_25

Cited by 11 publications

(6 citation statements)

References 12 publications

(14 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Generally, the integration of keypoint information into intensity-based image registration can be accomplished in numerous ways, see e.g. [62], [63]. In all these approaches, keypoint matches serve as additional constraints to the sought deformation, either requiring an exact correspondence [62] or allowing for user-defined tolerances [63].…”

Section: Dense Intensity-driven Registration Modelmentioning

confidence: 99%

“…[62], [63]. In all these approaches, keypoint matches serve as additional constraints to the sought deformation, either requiring an exact correspondence [62] or allowing for user-defined tolerances [63]. The primary use case of these approaches consists in integrating user input, for which an error estimate is available, into the registration process.…”

Section: Dense Intensity-driven Registration Modelmentioning

confidence: 99%

See 1 more Smart Citation

Estimation of Large Motion in Lung CT by Integrating Regularized Keypoint Correspondences into Dense Deformable Registration

Rühaak

Polzin

Heldmann

et al. 2017

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

We 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.

show abstract

Section: Dense Intensity-driven Registration Modelmentioning

confidence: 99%

Section: Dense Intensity-driven Registration Modelmentioning

confidence: 99%

Estimation of Large Motion in Lung CT by Integrating Regularized Keypoint Correspondences into Dense Deformable Registration

Rühaak

Polzin

Heldmann

et al. 2017

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

show abstract

“…Landmarks. Though the use of landmarks has been proven to improve image registration results [6,7], the issue remains that they must be provided with high accuracy for each image and often need to be set manually. We additionally face the problem that we choose to not imply any parametrical representation of our transformation ϕ, which means that we only know the values of our transformation at the grid point positions.…”

Section: Extensions For Frame Interpolation For Facial Motionmentioning

confidence: 99%

“…We additionally face the problem that we choose to not imply any parametrical representation of our transformation ϕ, which means that we only know the values of our transformation at the grid point positions. Inspired by [7] where the authors incorporate an individual landmark inaccuracy for each landmark pair, we assume that the landmarks are located at pixel positions (grid points), which avoids the interpolation of the deformation ϕ for subpixel locations. Landmarks allow us to influence the direction of the deformation estimation process.…”

Section: Extensions For Frame Interpolation For Facial Motionmentioning

confidence: 99%

Performance of Image Registration and Its Extensions for Interpolation of Facial Motion

Graßhof

Östermann

2014

Image and Video Technology – PSIVT 2013 Workshops

View full text Add to dashboard Cite

We compare the performance of an intensity based nonparametric image registration algorithm and extensions applied to frame interpolation of mouth images. The mouth exhibits large deformations due to different shapes, additionally some facial features occlude others, e.g. the lips cover the teeth. The closures and disclosures represent a challenging problem, which cannot be solved by the traditional image registration algorithms. The tested extensions include local regularizer weight adaptation, incorporation of landmarks, self-occlusion handling and penalization of folds, which have all been examined with different weight parameters. Since the performance of these algorithms and extensions turns out to be superior in case of mouth closures, we provide an algorithm for the automatic selection of deformable template and static reference image for the registration procedure. Subjective tests show that the quality of results for interpolation of mouth images is enhanced by this proposal.

show abstract

“…Different hybrid methods, which combine landmarks and image features have been proposed in literature. For example in [14,16,26], the landmarks are treated as additional constraints. The methods require a perfect interpolation of the landmarks resulting in numerical problems during optimization.…”

Section: Introductionmentioning

confidence: 99%

Variational Image Registration Using Inhomogeneous Regularization

et al. 2014

View full text Add to dashboard Cite

We present a generalization of the convolutionbased variational image registration approach, in which different regularizers can be implemented by conveniently exchanging the convolution kernel, even if it is nonseparable or nonstationary. Nonseparable kernels pose a challenge because they cannot be efficiently implemented by separate 1D convolutions. We propose to use a low-rank tensor decomposition to efficiently approximate nonseparable convolution. Nonstationary kernels pose an even greater challenge because the convolution kernel depends on, and needs to be evaluated for, every point in the image. We propose to pre-compute the local kernels and efficiently store them in memory using the Tucker tensor decomposition model. In our experiments we use the nonseparable exponential kernel and a nonstationary landmark kernel. The exponential kernel replicates desirable properties of elastic image registration, while the landmark kernel incorporates local prior knowledge about corresponding points in the images. We examine the trade-off between the computational resources needed and the approximation accuracy of the tensor decomposition methods. Furthermore, we obtain very smooth displacement fields even in the presence of large landmark displacements.

show abstract

Landmark Constrained Non-parametric Image Registration with Isotropic Tolerances

Cited by 11 publications

References 12 publications

Estimation of Large Motion in Lung CT by Integrating Regularized Keypoint Correspondences into Dense Deformable Registration

Estimation of Large Motion in Lung CT by Integrating Regularized Keypoint Correspondences into Dense Deformable Registration

Performance of Image Registration and Its Extensions for Interpolation of Facial Motion

Variational Image Registration Using Inhomogeneous Regularization

Contact Info

Product

Resources

About