Brain MRI super-resolution using deep 3D convolutional networks

Example-based single image super-resolution (SR) has recently shown outcomes with high reconstruction performance. Several methods based on neural networks have successfully introduced techniques into SR problem. In this paper, we propose a three-dimensional (3D) convolutional neural network to gene...

Full description

Saved in:
Bibliographic Details
Published in2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017) pp. 197 - 200
Main Authors Chi-Hieu Pham, Ducournau, Aurelien, Fablet, Ronan, Rousseau, Francois
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.04.2017
Subjects
3D convolutional neural network
Biological neural networks
brain MRI
Image resolution
Image restoration
Magnetic resonance imaging
Super-resolution
Three-dimensional displays
Training
Two dimensional displays
Online AccessGet full text

Cover

More Information
Summary:Example-based single image super-resolution (SR) has recently shown outcomes with high reconstruction performance. Several methods based on neural networks have successfully introduced techniques into SR problem. In this paper, we propose a three-dimensional (3D) convolutional neural network to generate high-resolution (HR) brain image from its input low-resolution (LR) with the help of patches of other HR brain images. Our work demonstrates the need of fitting data and network parameters for 3D brain MRI.
ISSN:1945-8452
DOI:10.1109/ISBI.2017.7950500