Skip to Main content Skip to Navigation
New interface
Poster communications

RNN-LSTM neural network for predicting fMRI neurofeedback scores from EEG signals

Caroline Pinte 1 Claire Cury 1 Pierre Maurel 1 
1 EMPENN - Neuroimagerie: méthodes et applications
INSERM - Institut National de la Santé et de la Recherche Médicale, Inria Rennes – Bretagne Atlantique , IRISA-D6 - SIGNAL, IMAGE ET LANGAGE
Abstract : In the context of neurofeedback (NF), simultaneous acquisitions with electroencephalography (EEG) and functional magnetic resonance imaging (fMRI) provide more effective NF training due to their complementarity [1]. However, the use of MRI is expensive and draining for the subject. Therefore, we would like to reduce its use. Following the work of Cury et al. [2], we propose a method based on a recurrent neural network (RNN) that consists in learning a model from simultaneous EEG-fMRI acquisitions to predict NF-fMRI scores with EEG signals alone.
Document type :
Poster communications
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03798824
Contributor : Caroline Pinte Connect in order to contact the contributor
Submitted on : Wednesday, October 5, 2022 - 2:45:03 PM
Last modification on : Tuesday, October 25, 2022 - 4:16:16 PM

Identifiers

  • HAL Id : hal-03798824, version 1

Citation

Caroline Pinte, Claire Cury, Pierre Maurel. RNN-LSTM neural network for predicting fMRI neurofeedback scores from EEG signals. rtFIN 2022 - Real-Time Functional Imaging and Neurofeedback meeting, Oct 2022, New Haven, United States. ⟨hal-03798824⟩

Share

Metrics

Record views

0

Files downloads

0