| | |
Summary: Validation Metrics for Non-Rigid Registration of
Medical Images containing Vessel Trees
Thomas Lange1
, Hans Lamecker2
, Michael H¨unerbein1
, Sebastian Eulenstein1
,
Siegfried Beller1
, Peter M. Schlag1
1
Klinik f¨ur Chirurgie und Chirurgische Onkologie,
Charit´e - Universit¨atsmedizin Berlin, 13125 Berlin
2
Zuse-Institut Berlin, 14195 Berlin
Email: thomas.lange@charite.de
Abstract. Validation of non-rigid registration methods is still a chal-
lenging task. Different evaluation criteria were published, yet no widely
accepted gold standard exists. The aim of this paper is to provide quan-
titative evaluation metrics suited for clinical 3D images containing vessel
trees, such as liver or brain data. We present a method to identify corre-
|
