Matching CT and ultrasound data of the liver by landmark constrained image registration

Olesch, Janine; Papenberg, Nils; Lange, Thomas; Conrad, Matthias; Fischer, Bernd

doi:10.1117/12.812218

Cited by 7 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast to [7] we do not summarize the differences of the landmarks, but handle each of them separately. As a consequence, we are able to guarantee an individual error for each pair of landmarks.…”

Section: Methodsmentioning

confidence: 99%

“…That means, the objective function as well as the constraints are discretized first to achieve a finite optimization problem. In particular, the constraints are approximated by means of linear interpolation as described in [7].…”

Section: Methodsmentioning

confidence: 99%

“…Secondly the penalty approach suffers from parameter tuning. Another approach is described in [7]. Here, a constrained optimization problem is invoked, which ensures small landmark errors without parameter tuning, but again only the global error is restricted.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Landmark Constrained Non-parametric Image Registration with Isotropic Tolerances

et al. 2009

Self Cite

View full text Add to dashboard Cite

Abstract. The incorporation of additional user knowledge into a nonrigid registration process is a promising topic in modern registration schemes. The combination of intensity based registration and some interactively chosen landmark pairs is a major approach in this direction. There exist different possibilities to incorporate landmark pairs into a variational non-parametric registration framework. As the interactive localization of point landmarks is always prone to errors, a demand for precise landmark matching is bound to fail. Here, the treatment of the distances of corresponding landmarks as penalties within a constrained optimization problem offers the possibility to control the quality of the matching of each landmark pair individually. More precisely, we introduce inequality constraints, which allow for a sphere-like tolerance around each landmark. We illustrate the performance of this new approach for artificial 2D images as well as for the challenging registration of preoperative CT data to intra-operative 3D ultrasound data of the liver.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%