Open AccessNon‑local diffusion‑weighted image super‑resolution using collaborative joint information
Author(s) -
Yang Zhang,
Peiyu He,
Jiliu Zhou,
Xi Wu
Publication year - 2017
Publication title -
experimental and therapeutic medicine
Language(s) - Uncategorized
Resource type - Journals
eISSN - 1792-1015
pISSN - 1792-0981
DOI - 10.3892/etm.2017.5430
Subject(s) - diffusion mri , image resolution , weighting , computer science , partial volume , artificial intelligence , resolution (logic) , magnetic resonance imaging , computer vision , pattern recognition (psychology) , algorithm , physics , medicine , acoustics , radiology
Due to the clinical durable scanning time and other physical constraints, the spatial resolution of diffusion-weighted magnetic resonance imaging (DWI) is highly limited. Using a post-processing method to improve the resolution of DWI holds the potential to improve the investigation of smaller white-matter structures and to reduce partial volume effects. In the present study, a novel non-local mean super-resolution method was proposed to increase the spatial resolution of DWI datasets. Based on a non-local strategy, joint information from the adjacent scanning directions was taken advantage of through the implementation of a novel weighting scheme. Besides this, an efficient rotationally invariant similarity measure was introduced for further improvement of high-resolution image reconstruction and computational efficiency. Quantitative and qualitative comparisons in synthetic and real DWI datasets demonstrated that the proposed method significantly enhanced the resolution of DWI, and is thus beneficial in improving the estimation accuracy for diffusion tensor imaging as well as high-angular resolution diffusion imaging.