Laplacian pyramid-based complex neural network learning for fast MR imaging

Haoyun Liang, Yu Gong, Hoel Kervadec, Jing Yuan, Hairong Zheng, Shanshan Wang

Track: full conference paper

TL;DR: Proposed and designed a new Laplacian pyramid-based multi-scale complex neural network learning framework for fast MR imaging.

Keywords: Deep learning, complex convolution, Laplacian pyramid decomposition

Abstract: A Laplacian pyramid-based complex neural network, CLP-Net, is proposed to reconstruct high-quality magnetic resonance images from undersampled k-space data. Specifically, three major contributions have been made: 1) A new framework has been proposed to explore the encouraging multi-scale properties of Laplacian pyramid decomposition; 2) A cascaded multi-scale network architecture with complex convolutions has been designed under the proposed framework; 3) Experimental validations on an open source dataset fastMRI demonstrate the encouraging properties of the proposed method in preserving image edges and fine textures.

Paper Type: both

Presentation Upload Agreement: I agree that my presentation material (videos and slides) will be made public.