What is it about?
Brain activity is distributed over the three-dimensional volume and evolves over time. How can we know what part of brain is working during a particular task at a given time? This problem was previously solved using math equations. Here, we have shown that with integration of AI and computational neuroscience models, we are able to greatly enhance our ability to image human brain function.
Featured Image
Photo by Steve Johnson on Unsplash
Why is it important?
Our findings show that with pre-trained deep neural network, we can map out brain electrical activity from electrophysiological recordings over the scalp with simple operations.
Perspectives
We hope this work would help make dynamic brain mapping more available to various clinics, helping diagnosis and treatment of neurological disorders.
Dr. Bin He
Carnegie Mellon University
Read the Original
This page is a summary of: Deep neural networks constrained by neural mass models improve electrophysiological source imaging of spatiotemporal brain dynamics, Proceedings of the National Academy of Sciences, July 2022, Proceedings of the National Academy of Sciences,
DOI: 10.1073/pnas.2201128119.
You can read the full text:
Contributors
The following have contributed to this page
