Diffeomorphic Diffusion Registration of Lung CT Images

Registration of the lungs in thoracic CT images is required in many elds of application in medical imaging, for example for motion estimation, analysis of pathology progression or the generation of shape atlases. In this paper, we present a robust registration approach that has been optimized for the registration of thoracic CT data. The algorithm con- sists of an initial shape-based adjustment of lung surfaces followed by an intensity-based dieomorphic image registration. The approach is evaluated based on 20 CT scans provided for the EM- PIRE10 study for pulmonary image registration. A fourth place out of 34 participants suggests a good applicability for the registration of lung CT images.

[1]  Paul J. Besl,et al.  A Method for Registration of 3-D Shapes , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Mads Nielsen,et al.  Non-rigid registration by geometry-constrained diffusion , 1999, Medical Image Anal..

[3]  Eric A. Hoffman,et al.  Automatic lung segmentation for accurate quantitation of volumetric X-ray CT images , 2001, IEEE Transactions on Medical Imaging.

[4]  Jan Modersitzki,et al.  Numerical Methods for Image Registration , 2004 .

[5]  Alain Trouvé,et al.  Computing Large Deformation Metric Mappings via Geodesic Flows of Diffeomorphisms , 2005, International Journal of Computer Vision.

[6]  Vincent Arsigny,et al.  Processing Data in Lie Groups : An Algebraic Approach. Application to Non-Linear Registration and Diffusion Tensor MRI. (Traitement de données dans les groupes de Lie : une approche algébrique. Application au recalage non-linéaire et à l'imagerie du tenseur de diffusion) , 2006 .

[7]  Nicholas Ayache,et al.  A Log-Euclidean Framework for Statistics on Diffeomorphisms , 2006, MICCAI.

[8]  J. Ehrhardt,et al.  An optical flow based method for improved reconstruction of 4D CT data sets acquired during free breathing. , 2007, Medical physics.

[9]  Nicholas Ayache,et al.  Symmetric Log-Domain Diffeomorphic Registration: A Demons-Based Approach , 2008, MICCAI.

[10]  Ernesto Zacur,et al.  Algorithms for computing the group exponential of diffeomorphisms: Performance evaluation , 2008, 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[11]  Heinz Handels,et al.  Validation and comparison of a biophysical modeling approach and non-linear registration for estimation of lung motion fields in thoracic 4D CT data , 2009, Medical Imaging.

[12]  Christine H. Lorenz,et al.  Second International Workshop on Pulmonary Image Analysis , 2009 .

[13]  B. van Ginneken,et al.  Automatic lung segmentation from thoracic computed tomography scans using a hybrid approach with error detection. , 2009, Medical physics.

[14]  J. Ehrhardt,et al.  Prediction of Respiratory Motion Using A Statistical 4 D Mean Motion Model , 2009 .

[15]  Heinz Handels,et al.  Evaluation and Comparison of Force Terms for the Estimation of Lung Motion by Non-linear Registration of 4D-CT Image Data , 2009 .

[16]  Heinz Handels,et al.  Automatic Landmark Detection and Non-linear Landmark-and Surface-based Registration of Lung CT Images , 2010 .

[17]  K. Murphy,et al.  Evaluation of Methods for Pulmonary Image Registration : The EMPIRE 10 Study , 2010 .