Share Email Print
cover

Proceedings Paper • new

Adversarial training and dilated convolutions for compressed sensing MRI
Author(s): Chao Xu; Jinxu Tao; Zhongfu Ye; Jinzhang Xu; Wajiha Kainat
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Compressed Sensing Magnetic Resonance Imaging (CS-MRI) provides the possibility to accelerate the acquisition with only a small amount of k-space data. Conventional CS-MRI methods are often time-consuming due to the numerous iterative steps. Recently, deep learning has been introduced to solve CS-MRI problem. In this paper, we propose a Residual Dilated model based on Generative Adversarial Networks, titled RDGAN, for fast and accurate reconstruction. We design a modified U-Net architecture which contains dilated convolutions to aggregate multi-scale information in the MRI. Also, inspired by residual learning, we adopt a short residual connection (SRC) and a long residual connection (LRC) strategies to help features flow into deeper layers directly and stabilise the adversarial training process. The experimental results demonstrate that the proposed RDGAN model achieves the state-of-the-art performance in CS-MRI on MICCAI 2013 grand challenge dataset.

Paper Details

Date Published: 14 August 2019
PDF: 8 pages
Proc. SPIE 11179, Eleventh International Conference on Digital Image Processing (ICDIP 2019), 111793T (14 August 2019); doi: 10.1117/12.2539623
Show Author Affiliations
Chao Xu, Univ. of Science and Technology of China (China)
Jinxu Tao, Univ. of Science and Technology of China (China)
Zhongfu Ye, Univ. of Science and Technology of China (China)
Jinzhang Xu, Hefei Univ. of Technology (China)
Wajiha Kainat, Univ. of Science and Technology of China (China)


Published in SPIE Proceedings Vol. 11179:
Eleventh International Conference on Digital Image Processing (ICDIP 2019)
Jenq-Neng Hwang; Xudong Jiang, Editor(s)

© SPIE. Terms of Use
Back to Top