Meeting Banner
Abstract #3938

Predicting Blood-oxygenation-level Dependent Signal from Local Field Potentials Using Recurrent Neural Networks

Xiaodi Zhang1, Wen-Ju Pan1, and Shella Dawn Keilholz1
1Biomedical Engineering, Emory University/Georgia Institute of Technology, Atlanta, GA, United States

We implemented a stacked long short-term memory neural network to predict the blood-oxygenation-level dependent signal from the band-limited power of local field potentials in a variety of frequencies. The model was trained with simultaneously acquired resting state fMRI and LFP data from rats under Isoflurane anesthesia. The results show that the model prediction has a higher Pearson correlation with the ground truth of BOLD signal than the LFP band-limited power in any frequency bands.

This abstract and the presentation materials are available to 2020 meeting attendees and eLibrary customers only; a login is required.

Join Here