Particle-guided image registration

Abstract

We present a novel image registration method based on B-spline free-form deformation that simultaneously optimizes particle correspondence and image similarity metrics. Different from previous B-spline based registration methods optimized w.r.t. the control points, the deformation in our method is estimated from a set of dense unstructured pair of points, which we refer as corresponding particles. As intensity values are matched on the corresponding location, the registration performance is iteratively improved. Moreover, the use of corresponding particles naturally extends our method to a group-wise registration by computing a mean of particles. Motivated by a surface-based group-wise particle correspondence method, we developed a novel system that takes such particles to the image domain, while keeping the spirit of the method similar. The core algorithm both minimizes an entropy based group-wise correspondence metric as well as maximizes the space sampling of the particles. We demonstrate the results of our method in an application of rodent brain structure segmentation and show that our method provides better accuracy in two structures compared to other registration methods.

Fig. 1

Schematic diagram of (a) overlapping particles and local intensity similarity in correspondence across subjects. Colored in blue, green, and red, each particle has correspondence across subjects and attracts together minimizing H_P . At the same time, the entropy of local intensities sampled in colored squares is also minimized so that the particles stay at a locally similar position. (b) a repulsion force uniformly distributes in-subject particles to fill a given region.

Fig. 2

Overall algorithm flow. The registration process is finished when the system stabilizes, and images are registered with the estimated T_j.

Fig. 3

Visual comparison of segmentation results. From left to right, the moving, fixed, result of proposed method, B-spline, and ANTS respectively in the first three rows. The bottom row shows sagittal slices of the fixed image, the result of the proposed image, and the moving image. The intensity scale was inverted during the acquisition but corrected in the experiments.