2009-BVM-Ruppertshofen
Image Registration using Tensor Grids for Lung Ventilation Studies
H. Ruppertshofen and S. Kabus and B. Fischer
    117 -- 121  (2009)

In non-parametric image registration it is often not possible to work with the original resolution of the images due to high processing times and lack of memory. However for some medical applications like lung ventilation the information contained in the original resolution is crucial in certain regions of the image while it might be negligible in others. In this work we present an approach using tensor grids to adapt to this problem. Tensor grids reduce the data size by providing a sparser image representation and thereby allow the use of the highest image resolution locally.