Using GAN for learning joint task/response distribution in fMRI

Lee, JY; Loktyushin, A; Stelzer, J; Lohmann, G

Local TagsRelease HistoryDetailsSummary

Using GAN for learning joint task/response distribution in fMRI

Lee, J., Loktyushin, A., Stelzer, J., & Lohmann, G. (submitted). Using GAN for learning joint task/response distribution in fMRI.

Item is Released

show all hide all

Basic

show hide

Item Permalink: https://hdl.handle.net/21.11116/0000-0007-80BE-2 Version Permalink: https://hdl.handle.net/21.11116/0000-0007-80C2-C

Genre: Meeting Abstract

Files

show Files

Locators

show

hide

Locator:
https://openreview.net/pdf?id=rylMuVFoFN (Any fulltext) Open Access status unknown

Description:
-

OA-Status:

Creators

show

hide

Creators:
Lee, JY^{1, 2}, Author
Loktyushin, A^{1, 2}, Author
Stelzer, J^{1, 2}, Author
Lohmann, G^{1, 2}, Author

Affiliations:
1Department High-Field Magnetic Resonance, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497796
2Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497794

Content

show

hide

Free keywords: -

Abstract: This is a proof-of-principle study on using generative adversarial network (GAN) to synthesize functional Magnetic Resonance Imaging (fMRI) data. We trained GAN to model the joint distribution of motor task functional magnetic resonance imaging (fMRI) data and the corresponding task labels. Synthesized images by the trained GAN successfully replicated the task relevant fMRI signal in the motor cortex. This result shows a potential for using GAN to augment fMRI data.

Details

show

hide

Language(s):

Dates: Submitted: 2019-05

Publication Status: Submitted

Pages: -

Publishing info: -

Table of Contents: -

Rev. Type: -

Identifiers: -

Degree: -

Event

show

hide

Title: Medical Imaging with Deep Learning (MIDL 2019)

Place of Event: London, UK

Start-/End Date: 2019-07-08 - 2019-07-10

Legal Case

show

Project information

show

Source 1

show

hide

Title: Medical Imaging with Deep Learning (MIDL 2019)

Source Genre: Proceedings

Creator(s):

Affiliations:

Publ. Info: -

Pages: - Volume / Issue: - Sequence Number: - Start / End Page: - Identifier: -