Super-resolution Reconstruction for Diffusion-weighted Images using High Order SVD

摘要

The spatial resolution of diffusion-weighted imaging (DWI) is limited because of the loss of high-frequency information such as edges during data acquisition process. In this paper, method based on the patch-based super-resolution framework is proposed for single image super-resolution reconstruction of DWI dataset and the high order SVD was introduced to achieve more accurate image reconstruction and reduce the computational complexity. Experimental results demonstrate that the proposed method outperformed currently methods in both DWI reconstruction and its further applications.