3D Lung Registration using splineMIRIT and Robust Tree Registration (RTR) Dirk Loeckx, Dirk Smeets, Johannes Keustermans, Jeroen Hermans, Frederik Maes, Dirk Vandermeulen, and Paul Suetens K.U.Leuven, Faculty of Engineering, ESAT/PSI Medical Imaging Research Center, UZ Gasthuisberg, Herestraat 49 bus 7003, B-3000 Leuven, Belgium Abstract. Intra-patient registration of lung CT scans acquired at a different time points or inspiration levels is a valuable examination tool to study multiple lung images. It allows to study ventilation or other functional information of the lungs. In this paper, two 3D lung registration methods are presented. The first method, splineMIRIT, uses voxel based non rigid image registration. It is based on mutual information as similarity measure, a B-spline mesh to model the deformation and B-spline image interpolation. The second method, Robust Tree Registration (RTR), extends the first by includ- ing robust 3D registration of the vessel trees found in both images. The tree is represented by intrinsic matrices containing the geodesic or Eu- clidean distance between each pair of detected bifurcations. This repre- sentation is independent of the reference frame. Marginalization of point pair probabilities based on the intrinsic matrices provides soft assign cor- respondences between the two trees. This global correspondence model is combined with local bifurcation similarity models, based on the lo- cal gray value distribution. Finally, hard correspondences are deducted from the model. The correspondences between bifurcations are added to splineMIRIT as an additional similarity measure. The method is validated on the EMPIRE10 data set. Both algorithms perform well. Comparing splineMIRIT and RTR shows that on average the results slightly improve when the robust tree registration is added, leading to a 15 th and 13 th place, respectively, in the “Grand Challenges in Medical Image Analysis” workshop of MICCAI 2010. 1 Introduction Non rigid image registration is an important tool in medical image analysis. It allows to integrate complimentary information contained in multiple image data sets. Pulmonary image registration, in particular, can help e.g. in the follow- up of patients or to study the pulmonary ventilation. Pulmonary ventilation can be studied using several CT images in one breathing cycle (4D CT) [1]. In radiotherapy treatment, extraction of the lung deformation is important for correction of tumor motion, leading to a more accurate irradiation. In follow-up