Loading...
Loading...

Go to the content (press return)

Brain MRI super-resolution using generative adversarial networks

Author
Sánchez, I.; Vilaplana, V.
Type of activity
Presentation of work at congresses
Name of edition
First International conference on Medical Imaging with Deep Learning
Date of publication
2018
Presentation's date
2018-07-05
Book of congress proceedings
International conference on Medical Imaging with Deep Learning: Amsterdam, 4 - 6th July 2018
First page
1
Last page
8
Repository
http://hdl.handle.net/2117/126234 Open in new window
https://openreview.net/group?id=MIDL.amsterdam/2018/Conference#oral-papers Open in new window
URL
https://midl.amsterdam/scientific-program/ Open in new window
Abstract
In this work we propose an adversarial learning approach to generate high resolution MRI scans from low resolution images. The architecture, based on the SRGAN model, adopts 3D convolutions to exploit volumetric information. For the discriminator, the adversarial loss uses least squares in order to stabilize the training. For the generator, the loss function is a combination of a least squares adversarial loss and a content term based on mean square error and image gradients in order to improve ...
Citation
Sánchez, I., Vilaplana, V. Brain MRI super-resolution using generative adversarial networks. A: International conference on Medical Imaging with Deep Learning. "International conference on Medical Imaging with Deep Learning: Amsterdam, 4 - 6th July 2018". 2018, p. 1-8.
Group of research
GPI - Image and Video Processing Group
IDEAI-UPC - Intelligent Data Science and Artificial Intelligence Research Center

Participants

Attachments