Joint Segmentation and Nonlinear Registration Using Fast Fourier Transform and Total Variation

Image segmentation and registration play active roles in machine vision and medical image analysis of historical data. We explore the joint problem of segmenting and registering a template (current) image given a reference (past) image. We formulate the joint problem as a minimization of a functional that integrates two well-studied approaches in segmentation and registration: geodesic active contours and nonlinear elastic registration. The template image is modeled as a hyperelastic material (St. Venant-Kirchhoff model) which undergoes deformations under applied forces. To segment the deforming template, a two-phase level set-based energy is introduced together with a weighted total variation term that depends on gradient features of the deforming template. This particular choice allows for fast solution using the dual formulation of the total variation. This allows the segmenting front to accurately track spontaneous changes in the shape of objects embedded in the template image as it deforms. To solve the underlying registration problem, we use gradient descent and adopt an implicit-explicit method and use the fast Fourier transform.

[1]  Eldad Haber,et al.  Intensity Gradient Based Registration and Fusion of Multi-modal Images , 2006, MICCAI.

[2]  Tony F. Chan,et al.  Structure-Texture Image Decomposition—Modeling, Algorithms, and Parameter Selection , 2006, International Journal of Computer Vision.

[3]  Steven J. Ruuth,et al.  Implicit-explicit methods for time-dependent partial differential equations , 1995 .

[4]  Guy Marchal,et al.  Automated multi-moda lity image registration based on information theory , 1995 .

[5]  Xavier Bresson,et al.  Fast Global Minimization of the Active Contour/Snake Model , 2007, Journal of Mathematical Imaging and Vision.

[6]  Dianne P. O'Leary,et al.  Deblurring Images: Matrices, Spectra and Filtering , 2006, J. Electronic Imaging.

[7]  Max A. Viergever,et al.  Image registration by maximization of combined mutual information and gradient information , 2000, IEEE Transactions on Medical Imaging.

[8]  Paul A. Viola,et al.  Alignment by Maximization of Mutual Information , 1997, International Journal of Computer Vision.

[9]  A. Raoult.  Non-polyconvexity of the stored energy function of a Saint Venant-Kirchhoff material , 1986 .

[10]  A. Yezzi,et al.  A variational framework for joint segmentation and registration , 2001, Proceedings IEEE Workshop on Mathematical Methods in Biomedical Image Analysis (MMBIA 2001).

[11]  Gene H. Golub,et al.  A Nonlinear Primal-Dual Method for Total Variation-Based Image Restoration , 1999, SIAM J. Sci. Comput..

[12]  Solene Ozere,et al.  Joint Segmentation/Registration Model by Shape Alignment via Weighted Total Variation Minimization and Nonlinear Elasticity , 2015, SIAM J. Imaging Sci..

[13]  Tony F. Chan,et al.  Active contours without edges , 2001, IEEE Trans. Image Process..

[14]  M. Nikolova.  An Algorithm for Total Variation Minimization and Applications , 2004 .

[15]  Luminita A. Vese,et al.  A combined segmentation and registration framework with a nonlinear elasticity smoother , 2009, Comput. Vis. Image Underst..