A physics-informed AI framework can reconstruct three-dimensional fluid velocity maps across the entire living brain using standard MRI data, according to an animal study published May 27 in Science Advances.
The results could offer a new understanding of the glymphatic system's role in neurological disease, said corresponding author Douglas Kelley, PhD, of the University of Rochester in New York, in a statement released by the journal.
"You can put a microscope on a small patch of the brain and watch what's happening there with a lot of detail, and we've worked with that type of data in the past, but it's only a tiny view of the overall process," he said.
"[But] if you want to image whole brains, an MRI [exam] is a great approach because it gives you a three-dimensional view."
During sleep, waterlike fluid circulates around the brain, clearing metabolic waste that is linked to diseases such as Alzheimer's in a process known as the glymphatic system, Kelley and colleagues explained. Yet exactly how this system works, especially how quickly the fluid circulates, is unclear.
MRI is a useful tool for imaging the brain, but it has limitations for this indication, namely that it doesn't capture fluid flow velocity for flows this slow, Kelley noted. He and his team used physics-based AI to determine fluid flow velocities from MRI data. The algorithm incorporated videos of dye spreading across brain tissue over time, which allowed the team to deduce how fast the fluid flows and how permeable the brain tissue is.
The method the investigators developed, called Magnetic Resonance Artificial Intelligence Velocimetry (MR-AIV), was applied to dynamic contrast-enhanced MRI (DCE-MRI) scans from five mice following injection of the tracer gadobutrol into the cisterna magna. The algorithm tracked brain-wide velocity, pressure, and tissue permeability fields from tracer concentration data alone -- without requiring direct velocity measurements, which have historically been impossible to obtain noninvasively across the whole brain, according to the authors.
The study results indicated two main ways that the glymphatic system washes away particles in the brain such as the amyloid beta proteins linked to Alzheimer's disease -- with one of these ways much faster than the other, Kelley and colleagues noted. The fast flow of the glymphatic system's fluid moves at about 3 µm/s around the brain's open regions such as the surface between the skull and the brain, while the slower flow of the fluid trickles through the brain's deep tissue (i.e., the hippocampus, caudate, and thalamus) at a rate about 50 times slower (0.1 µm/s).
A 3D visualization shows the flow speed of fluid across the brain.University of Rochester/Kelley et al.
Because DCE-MRI is already used clinically in humans, the authors argue the framework could eventually be translated to patient populations.
"We hope to someday be able to see whether an Alzheimer's patient has poor circulation in their brain or even screen for poor circulation earlier in life to try to stave off Alzheimer's," Kelley said in the journal statement. "Or we could check when somebody has been concussed to see whether the fluid circulation in their brain is disrupted. This study gets us a step closer."
The MR-AIV codebase and dataset have been made publicly available on Zenodo.
