Feedback Graph Attention Convolutional Network for MR Images Enhancement by Exploring Self-Similarity FeaturesDownload PDF

Published: 31 Mar 2021, Last Modified: 16 May 2023MIDL 2021Readers: Everyone
Keywords: Magnetic resonance imaging, image enhancement, self-similarity, graph similarity branch, feedback mechanism.
TL;DR: To learn self-similarity priors of MRI, we designed a specialized Graph-based structure to merge high-similarity information of sub-regions by updating larger weights to the more important and similar nodes or features in a graph attention fashion
Abstract: Artifacts, blur, and noise are the common distortions degrading MRI images during the acquisition process, and deep neural networks have been demonstrated to help in improving image quality. To well exploit global structural information and self-similarity details, we propose a novel MR image enhancement network, named Feedback Graph Attention Convolutional Network (FB-GACN). As a key innovation, we consider the global structure of an image by building a graph network from image sub-regions that we consider to be node features, linking them non-locally according to their similarity. The proposed model consists of three main parts: 1) The parallel graph similarity branch and content branch, where the graph similarity branch aims at exploiting the similarity and symmetry across different image sub-regions in low-resolution feature space and provides additional priors for the content branch to enhance texture details. 2) A feedback mechanism with a recurrent structure to refine low-level representations with high-level information and generate powerful high-level texture details by handling the feedback connections. 3) A reconstruction to remove the artifacts and recover super-resolution images by using the estimated sub-region self-similarity priors obtained from the graph similarity branch. We evaluate our method on two image enhancement tasks: i) cross-protocol super resolution of diffusion MRI; ii) artifact removal of FLAIR MR images. Experimental results demonstrate that the proposed algorithm outperforms the state-of-the-art methods.
Registration: I acknowledge that publication of this at MIDL and in the proceedings requires at least one of the authors to register and present the work during the conference.
Authorship: I confirm that I am the author of this work and that it has not been submitted to another publication before.
Paper Type: methodological development
Primary Subject Area: Image Acquisition and Reconstruction
Secondary Subject Area: Image Synthesis
Source Latex: zip
10 Replies