Researchers at the University of Rochester, Brown University, and the University of Copenhagen have developed a physics-informed neural network approach to measure cerebrospinal fluid flow velocities in the brain’s glymphatic system — something standard MRI cannot directly capture due to the flows being too slow. By training neural networks on MRI-derived dye-spreading videos, the team inferred both fluid velocity and tissue permeability without invasive methods. The results revealed a two-speed regime: fast flow of a few microns per second along open regions near the brain’s surface, and a roughly 50× slower trickle through deep brain tissue. The longer-term goal is to extend the technique to human subjects, where it could potentially screen for glymphatic circulation deficits associated with Alzheimer’s disease or assess disruptions following concussion.
To read more about this research, click here.