MRI, electroencephalography (EEG), and magnetoencephalography (MEG) have been the most widely used techniques to study brain activity for many years. A new study introduces a novel, AI-based dynamic brain imaging technology that can map rapidly changing electrical activity in the brain at high speed, high resolution, and low cost. The breakthrough follows more than 30 years of research into improving non-invasive dynamic brain imaging technology.
Electrical activity in the brain is distributed in three dimensions and changes rapidly over time. Many attempts have been made to image brain function and dysfunction, and each method has advantages and disadvantages. MRI, for example, is commonly used to study brain activity but is too slow to capture brain dynamics. EEG is a viable alternative to MRI technology; however, its suboptimal spatial resolution impedes its widespread application in imaging.
Electrophysiological source imaging has also been used to translate scalp EEG recordings back to the brain using signal processing and machine learning to reconstruct dynamic pictures of brain activity over time. While EEG source imaging is generally less expensive and faster, users require specific training and expertise to select and tune parameters for each recording. The team introduces a first-of-its-kind AI-based dynamic brain imaging methodology in the new study, which has the potential to image neural circuit dynamics with precision and speed.