Brain graph super-resolution using adversarial graph neural network with application to functional brain connectivity.

Journal: Medical image analysis
Published Date: Apr 21, 2021

Abstract

Brain image analysis has advanced substantially in recent years with the proliferation of neuroimaging datasets acquired at different resolutions. While research on brain image super-resolution has undergone a rapid development in the recent years, brain graph super-resolution is still poorly investigated because of the complex nature of non-Euclidean graph data. In this paper, we propose the first-ever deep graph super-resolution (GSR) framework that attempts to automatically generate high-resolution (HR) brain graphs with N nodes (i.e., anatomical regions of interest (ROIs)) from low-resolution (LR) graphs with N nodes where N

Authors

  • Megi Isallari
    BASIRA lab, Faculty of Computer and Informatics Engineering, Istanbul Technical University, Istanbul, Turkey. Electronic address: http://basira-lab.com/.
  • Islem Rekik
    Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, USA.

Keywords

External Resources

Popular Topics
Recent Journals