Piecewise-Quadrilateral Registration by Optical Flow – Applications in Contrast-Enhanced MR Imaging of the Breast

Abstract

Abstract. In this paper we propose a method for the nonrigid registration of contrast-enhanced dynamic sequences of magnetic resonance(MR) images. The algorithm has been developed with accuracy in mind, but also has a clinically viable execution time (i.e. a few minutes) as a goal. The algorithm is driven by multiresolution optical flow with the brightness consistency assumption relaxed, subject to a regularized best-fit within a family of transforms. The particular family of transforms we have employed uses a grid of control points and trilinear interpolation. We present validation results from a study simulating non-rigid deformation by a biomechanical model of the breast, with simulated uptake of a contrast agent. We further present results from applying the algorithm as part of a routine breast cancer screening protocol.

Efficient computational fluid dynamics mesh generation by image registration

“…Extending the cost function to cope with differences in intensity between the images being registered can help to overcome the fact that the SSD cost function can be sensitive to such differences. An example of the use of an earlier version of the algorithm described in the current paper for correcting image motion is given by Froh et al (2006) and Martel et al (2007).…”

Adaptive Grid Generation Based Non-rigid Image Registration using Mutual Information for Breast MRI

“…Transformation at one resolution level is used to initialize the parameters at the next finer resolution level. In the literature, resolution refines in grid density, image resolution, B-spline levels and Gaussian pyramid in [2,4,6,20,21] as non-rigid image registration is usually iterative upgrading to search for the best transform parameters. In the framework, a multi-resolution strategy, which refines in image size, grid size and image intensity levels, is introduced.…”

“…This is implemented by enforcing unity deviations of the Jacobian determinant of the deformation. In [20], a multi-resolution optical flow with brightness consistency assumption relaxed and subjected to a regularized best-fit within a family of transforms is addressed. A bio-mechanically based elastic breast registration was developed [12] to fit the real breast tissues movement by using position of skin and muscle surface as the only boundary conditions instead of regulating by a smoothness term or regularization term.…”

Computerized method for nonrigid MR-to-PET breast-image registration

“…Normalized mutual information was used as a similarity measure. The fluid flow [36] and optical flow [37] techniques have also been applied to MR-to-MR breast-image registration. All these approaches rely on well-defined relationships between voxel intensities between the images being registered and all involve optimization.…”