Graph Cuts-Based Registration Revisited: A Novel Approach for Lung Image Registration Using Supervoxels and Image-Guided Filtering

This work revisits the concept of graph cuts as an efficient optimization technique in image registration. Previously, due to the computational burden involved, the use of graph cuts in this context has been mainly limited to 2D applications. Here we show how combining graph cuts with supervoxels, resulting in a sparse, yet meaningful graph-based image representation, can overcome previous limitations. Additionally, we show that a relaxed graph representation of the image allows for 'sliding' motion modeling and provides anatomically plausible estimation of the deformations. This is achieved by using image-guided filtering of the estimated sparse deformation field. We evaluate our method on a publicly available CT lung data set and show that our new approach compares very favourably with state-of-the-art in continuous and discrete image registration.

[1]  Daniel Rueckert,et al.  Nonrigid registration using free-form deformations: application to breast MR images , 1999, IEEE Transactions on Medical Imaging.

[2]  Vladimir Kolmogorov,et al.  An experimental comparison of min-cut/max- flow algorithms for energy minimization in vision , 2001, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  S. Vaughndill.  TUMOR AND NORMAL TISSUE MOTION IN THE THORAX DURING RESPIRATION: ANALYSIS OF VOLUMETRIC AND POSITIONAL VARIATIONS USING 4D CT , 2007 .

[4]  Heinz Handels,et al.  Estimating Large Lung Motion in COPD Patients by Symmetric Regularised Correspondence Fields , 2015, MICCAI.

[5]  R. Castillo,et al.  A framework for evaluation of deformable image registration spatial accuracy using large landmark point sets , 2009, Physics in medicine and biology.

[6]  Nassir Navab,et al.  Dense image registration through MRFs and efficient linear programming , 2008, Medical Image Anal..

[7]  Ben Glocker,et al.  Deformable medical image registration: setting the state of the art with discrete methods. , 2011, Annual review of biomedical engineering.

[8]  Michael Brady,et al.  Deformable image registration by combining uncertainty estimates from supervoxel belief propagation , 2016, Medical Image Anal..

[9]  Pedro F. Felzenszwalb,et al.  Efficient belief propagation for early vision , 2004, CVPR 2004.

[10]  Albert C. S. Chung,et al.  Non-rigid image registration of brain magnetic resonance images using graph-cuts , 2011, Pattern Recognit..

[11]  Albert C. S. Chung,et al.  Non-rigid image registration by using graph-cuts with mutual information , 2010, 2010 IEEE International Conference on Image Processing.

[12]  Gareth Funka-Lea,et al.  Graph Cuts and Efficient N-D Image Segmentation , 2006, International Journal of Computer Vision.

[13]  François-Xavier Vialard,et al.  Piecewise-diffeomorphic image registration: Application to the motion estimation between 3D CT lung images with sliding conditions , 2013, Medical Image Anal..

[14]  Sven Kabus,et al.  Estimation of Organ Motion from 4D CT for 4D Radiation Therapy Planning of Lung Cancer , 2004, MICCAI.

[15]  Thomas Guerrero,et al.  Ventilation from four-dimensional computed tomography: density versus Jacobian methods , 2010, Physics in medicine and biology.

[16]  Albert C. S. Chung,et al.  Non-rigid Image Registration Using Graph-cuts , 2007, MICCAI.

[17]  Albert C. S. Chung,et al.  Learning-based non-rigid image registration using prior joint intensity distributions with graph-cuts , 2011, 2011 18th IEEE International Conference on Image Processing.

[18]  Laurent Risser,et al.  An implicit sliding-motion preserving regularisation via bilateral filtering for deformable image registration , 2014, Medical Image Anal..

[19]  Farida Cheriet,et al.  Landmark-Based Non-rigid Registration Via Graph Cuts , 2007, ICIAR.

[20]  Michael Brady,et al.  MIND: Modality independent neighbourhood descriptor for multi-modal deformable registration , 2012, Medical Image Anal..

[21]  Tom Vercauteren,et al.  Diffeomorphic demons: Efficient non-parametric image registration , 2009, NeuroImage.

[22]  Jian Sun,et al.  Guided Image Filtering , 2010, ECCV.

[23]  Weiguo Lu,et al.  A simple fixed-point approach to invert a deformation field. , 2007, Medical physics.

[24]  Olga Veksler,et al.  Graph Cuts in Vision and Graphics: Theories and Applications , 2006, Handbook of Mathematical Models in Computer Vision.

[25]  Olga Veksler,et al.  Fast Approximate Energy Minimization via Graph Cuts , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[26]  Michael Brady,et al.  MRF-Based Deformable Registration and Ventilation Estimation of Lung CT , 2013, IEEE Transactions on Medical Imaging.

[27]  Habib Y. Baluwala,et al.  Toward physiologically motivated registration of diagnostic CT and PET/CT of lung volumes. , 2013, Medical physics.

[28]  Jan Rühaak,et al.  Highly accurate fast lung CT registration , 2013, Medical Imaging.

[29]  Pascal Fua,et al.  SLIC Superpixels Compared to State-of-the-Art Superpixel Methods , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[30]  Mattias P. Heinrich,et al.  Liver Motion Estimation via Locally Adaptive Over-Segmentation Regularization , 2015, MICCAI.

[31]  Patrick Clarysse,et al.  Automated segmentation of a motion mask to preserve sliding motion in deformable registration of thoracic CT. , 2012, Medical physics.

[32]  Brian B. Avants,et al.  Evaluation of Registration Methods on Thoracic CT: The EMPIRE10 Challenge , 2011, IEEE Transactions on Medical Imaging.

[33]  Brian B. Avants,et al.  Symmetric diffeomorphic image registration with cross-correlation: Evaluating automated labeling of elderly and neurodegenerative brain , 2008, Medical Image Anal..

[34]  Heinz Handels,et al.  Estimation of slipping organ motion by registration with direction-dependent regularization , 2012, Medical Image Anal..

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

[36]  Roberto Manduchi,et al.  Bilateral filtering for gray and color images , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).