Deformable registration of high-resolution and cine MR tongue images.

Abstract

This work investigates a novel 3D multimodal deformable registration method to align high-resolution magnetic resonance imaging (MRI) with cine MRI of the tongue for better visual and motion analysis. Both modalities have different strengths to characterize and analyze the tongue structure or motion. Visual and motion analysis of combined anatomical and temporal information can synergistically improve the utility of each modality. An automated multimodal registration method is presented utilizing structural information computed from the 3D Harris operator to encode spatial and geometric cues into the computation of mutual information. The robustness and accuracy of the proposed method have been demonstrated using experiments on clinical datasets and yielded better performance compared to the conventional method and an average error comparable to the inter-observer variability.