Diffusion weighted imaging distortion correction using hybrid multimodal image registration

In this paper, we introduce a hybrid image registration approach for diffusion weighted image (DWI) distortion correction. General intensity-based multimodal registration uses mutual information (MI) as the similarity metric, which can cause matching ambiguities due to the intensity correspondence uncertainty in some anatomical regions. We propose to overcome such limitations by enhancing the registration framework with automatically detected landmarks. These landmarks are then integrated naturally into multimodal diffeomorphic demons algorithm using Gaussian radial basis functions. The proposed algorithm was tested with clinical DWI data, with results demonstrating that better distortion correction can be achieved using the hybrid algorithm as compared to using a pure intensity-based approach.