Institute Homepage
Institute Homepage DE Sign In

Back

Miscellaneous 2019

Using GAN for learning joint task/response distribution in fMRI

{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.}

Author(s): Lee, JY and Loktyushin, A and Stelzer, J and Lohmann, G
Book Title: Medical Imaging with Deep Learning (MIDL 2019)
Year: 2019
Bibtex Type: Miscellaneous (misc)
Electronic Archiving: grant_archive

BibTex 

@misc{item_3267284,
  title = {{Using GAN for learning joint task/response distribution in fMRI}},
  booktitle = {{Medical Imaging with Deep Learning (MIDL 2019)}},
  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.}},
  year = {2019},
  slug = {item_3267284},
  author = {Lee, JY and Loktyushin, A and Stelzer, J and Lohmann, G}
}