Multimodal Non-Rigid Registration Methods Based on Demons Models and Local Uncertainty Quantification Used in 3D Brain Images (original) (raw)

Non-rigid registration (NRR) of multimodal images is a common task in diagnostic and therapeutic procedures based on medical imaging, which at the same time imposes remarkable technical challenges. This work presents a novel non-rigid multimodal registration method that relies on three basic steps: first, an initial approximation of the deformation field is obtained by a parametric registration technique based on particle filtering; second, an intensity mapping based on local variability measures (LVM) is applied over the two images in order to overcome the multimodal restriction between them; and third, an optical flow method is used in an iterative way to find the remaining displacements of the deformation field. Hence the new methodology offers a solution for multimodal NRR by a quadratic optimization over a convex surface, which allows independent motion of each pixel, in contrast to methods that parameterize the deformation space. To evaluate the proposed method, a set of MR/CT clinical studies (pre-and post-radiotherapy treatment) of three patients with cerebral tumor deformations of the brain structures was employed. The resulting registration was evaluated both qualitatively and quantitatively by standard indices of correspondence over anatomical structures of interest in radiotherapy (brain, tumor and cerebral ventricles). These results showed that one of the proposed LVM (entropy) offers a superior performance in estimating the non-rigid deformation field.