Validation Metrics for Non-rigid Registration of Medical Images Containing Vessel Trees
Validation of non-rigid registration methods is still a challenging task. Different evaluation criteria were published, yet no widely accepted gold standard exists. The aim of this paper is to provide quantitative evaluation metrics suited for clinical 3D images containing vessel trees, such as liver or brain data. We present a method to identify corresponding points on different vessel trees by extracting consistent graph minors interactively. Four different metrics based on these correspondencies are proposed.
Unable to display preview. Download preview PDF.
- 2.Hellier P, Barillot C, Corouge I, et al. Retrospective evaluation of inter-subject brain registration. Proc MICCAI. 2001; p. 258–65.Google Scholar
- 3.Christensen G, Geng X, Kuhl J, et al. Introduction to the non-rigid image registration evaluation project (NIREP). Proc WBIR. 2006; p. 128–35.Google Scholar
- 6.Charnoz A, Agnus V, Malandain G, et al. Design of robust vascular tree matching: Validation on liver. Proc IPMI. 2005; p. 443–55.Google Scholar
- 8.Lange T, Eulenstein S, Hünerbein M, et al. Augmenting intraoperative 3D ultrasound with preoperative models for navigation in liver surgery. Lect Notes Comp Sci. 2004;3217:534–41.Google Scholar
- 9.Lange T, Lamecker H, Hünerbein M, et al. A new class of distance measures for registration of tubular models to image data. Proc BVM. 2007; p. 101–5.Google Scholar