Abstract:
Conventional approaches to image registration are generally limited to imagewide
rigid transformations. However, the body and its internal organs are
non-rigid structures that change shape due to changes in the body's posture
during image acquisition, and due to normal, pathological and treatment-related
variations. Inter-subject matching also constitutes a non-rigid registration
problem. In this paper, we present a fully automated non-rigid image
registration method that maximizes a local voxel-based similarity metric.
Overlapping image blocks are defined on a 3D grid. The transformation vector
field representing image deformation is found by translating each block so
as to maximize the local similarity measure. The resulting sparsely sampled
vector field is median filtered and interpolated by a Gaussian function to
ensure a locally smooth transformation. A hierarchical strategy is adopted
to progressively establish local registration associated with image structures at
diminishing scale. Simulation studies were carried out to evaluate the proposed
algorithm and to determine the robustness of various voxel-based cost functions.
Mutual information, normalized mutual information, correlation ratio (CR) and
a new symmetric version of CR were evaluated and compared. A T1-weighted
magnetic resonance (MR) image was used to test intra-modality registration.
Proton density and T2-weighted MR images of the same subject were used to
evaluate inter-modality registration. The proposed algorithm was tested on the
2D MR images distorted by known deformations and 3D images simulating
inter-subject distortions. We studied the robustness of cost functions with
respect to image sampling. Results indicate that the symmetric CR gives
comparable registration to mutual information in intra- and inter-modality tasks
at full sampling and is superior to mutual information in registering sparsely
sampled images.
