Summary: A multidisciplinary neuroengineering study has broken a major imaging barrier by mapping the exact flow velocity of the brain’s waste-clearing infrastructure. The research utilizes physics-informed artificial intelligence to decode magnetic resonance imaging (MRI) data, revealing the hidden mechanics of the glymphatic system, the fluid network that washes away metabolic wastes like the amyloid-beta proteins linked to Alzheimer’s disease.
The AI models uncovered a dual-speed drainage blueprint, demonstrating that protective fluid moves 50 times faster across the brain’s outer surfaces than it does when trickling through deep brain tissue.
Key Facts
- The Glymphatic Baseline: First described in 2012 by pioneering neuroscientist Maiken Nedergaard, the glymphatic system acts as the brain’s internal plumbing network. When a subject enters deep sleep, a waterlike fluid circulates around the central nervous system to wash away metabolic debris associated with neurodegenerative diseases.
- The MRI Velocity Limitation: Evaluating this internal fluid circulation within a living brain has historically been nearly impossible. Standard microscopes offer high-detail views of only a microscopic patch of tissue, while traditional 3D MRIs lack the sensory capacity to track fluid flow velocity for movements this slow.
- Physics-Informed Neural Networks: To bridge this technological gap, mechanical engineers and computational scientists developed custom physics-informed AI tools. By training neural networks on MRI videos of dye tracking across brain tissue over time, the AI successfully deduced precise fluid flow velocities and mapped tissue permeability.
- The Dual-Velocity Blueprint: The AI revealed that the glymphatic system clears out toxic amyloid-beta particles using two distinct speeds. The “fast track” moves fluid at a few microns per second across open cortical regions, such as the surface between the skull and the brain. Conversely, the “slow track” trickles through deep brain tissue at a rate roughly 50 times slower.
- The Diagnostic Roadmap: While current baseline measurements have been successfully established in animal models, researchers are optimizing the AI software for human clinical settings. The goal is to compare fluid dynamics across young, old, healthy, and diseased brains.
- Intercepting Traumas and Dementia: Senior author Professor Douglas Kelley notes that mastering this fluid mapping brings science closer to screening for poor brain circulation early in life to stave off Alzheimer’s disease. Additionally, the technology could be deployed immediately following a concussion to check if a patient’s internal fluid circulation has been dangerously disrupted.
Source: University of Rochester
When a person goes into deep sleep, waterlike fluid circulates around the brain, washing away metabolic waste that is linked to diseases such as Alzheimerโs.
This process, known as the glymphatic system, was first described in 2012 byย Maiken Nedergaardโa pioneering neuroscientist and co-director of theย University of Rochesterย Center for Translational Neuromedicine.
But questions remain about the systemโs mechanicsโnotably, how quickly the fluid circulates around the brain. Studying the circulation within a living brain is difficult to do without causing irreparable harm to a subject.
โYou can put a microscope on a small patch of the brain and watch whatโs happening there with a lot of detail, and weโve worked with that type of data in the past, but itโs only a tiny view of the overall process,โ says Professorย Douglas Kelleyย from URochesterโsย Department of Mechanical Engineering.
โIf you want to image whole brains, an MRI is a great approach because it gives you a three-dimensional view. But an MRI has serious limitations too, the biggest of which is that it does not capture the fluid flow velocity, at least not for flows this slow.โ
Kelley and his colleagues from URochester, Brown University, and the University of Copenhagen turned to artificial intelligence for help.
In a newย studyย published inย Science Advances, they outline how they used physics-informed artificial intelligence to determine fluid flow velocities from magnetic resonance imaging (MRI) data. Using videos of dye spreading across brain tissue over time, the neural networks the researchers built were able to deduce how fast the fluid flows and how permeable the brain tissue is.
The results showed that there are two main ways that the glymphatic system washes away particles in the brain such as the amyloid beta proteins linked to Alzheimerโs diseaseโand one of these ways is much faster than the other. The fast flow of the glymphatic systemโs waterlike fluid moves at a few microns per second around the brainโs open regions such as the surface between the skull and the brain, while the slower flow of the waterlike fluid trickles through the brainโs deep tissue at a rate about 50 times slower.
So far, the researchers have been working to get baseline measurements of fluid flow in the brains of animals such as mice to inform the AI tools. In the future, they hope to be able to compare the fluid flow in healthy and sick brains as well as young and old brains, with aspirations to eventually study circulation in humans.
โWeโre working hard toward being able to measure the flow of waterlike fluids in and around human brains because then the clinical applications get a lot more important and exciting,โ says Kelley. โWe hope to someday be able to see whether an Alzheimerโs patient has poor circulation in their brain or even screen for poor circulation earlier in life to try to stave off Alzheimerโs. 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.โ
Funding: The research is supported by the NIH National Center for Complementary and Integrative Health and the NIH BRAIN Initiative.
Kelleyโs collaborators on the study include Brown University PhD student Juan Diego Toscano, URochester computational scientist Yisen Guo, Brown University PhD student Zhibo Wang, URochester PhD student Mohammad Vaezi, University of Copenhagen Associate Professor Yuki Mori, Brown University Professor George Karniadakis, and URochester Assistant Professorย Kimberly Boster.
Key Questions Answered:
A: It is the brain’s unique way of taking out the biological trash. Just like any other active organ, the brain generates metabolic waste as it operates throughout the day. During deep sleep, the glymphatic system opens up, allowing a waterlike fluid to circulate through your neural architecture and flush away toxic materials like amyloid-beta proteins, which are directly linked to the development of Alzheimer’s disease.
A: Because standard MRIs are essentially blind to fluid movements that are this incredibly slow. While a traditional MRI can give a flawless 3D image of the brain’s shape, it lacks the technical capacity to calculate the velocity of the glymphatic trickle. By building a custom physics-informed AI, researchers could analyze videos of dye spreading through tissue and mathematically deduce exactly how fast the fluid is flowing and how permeable the brain structure is.
A: It provides an immediate, non-invasive look at internal structural trauma. When a person suffers a severe concussion, the physical impact can disrupt the delicate pathways of the glymphatic system, halting the brain’s ability to clean itself. By using this AI-driven fluid tracking technology, clinicians could eventually screen a concussed patient to see if their fluid circulation is damaged, allowing for much smarter, individualized recovery protocols.
Editorial Notes:
- This article was edited by a Neuroscience News editor.
- Journal paper reviewed in full.
- Additional context added by our staff.
About this neuroscience and AI research news
Author:ย Luke Auburn
Source:ย University of Rochester
Contact:ย Luke Auburn โ University of Rochester
Image:ย The image is credited to Neuroscience News
Original Research:ย Open access.
โMR-AIV reveals in vivo brain-wide fluid flow with physics-informed AIโ byJuan Diego Toscano, Yisen Guo, Zhibo Wang, Mohammad Vaezi, Yuki Mori, George Em Karniadakis, Kimberly A. S. Boster, and Douglas H. Kelley.ย Science Advances
DOI:10.1126/sciadv.aeb0404
Abstract
MR-AIV reveals in vivo brain-wide fluid flow with physics-informed AI
The circulation of cerebrospinal and interstitial fluid plays a vital role in clearing metabolic waste from the brain, and its disruption has been linked to neurological disorders. However, directly measuring brain-wide fluid transport, especially in the deep brain, has remained elusive.
Here, we introduce magnetic resonance artificial intelligence velocimetry (MR-AIV), a framework featuring a specialized physics-informed architecture and optimization method that reconstructs three-dimensional fluid velocity fields from dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). MR-AIV unveils brain-wide velocity maps while providing estimates of tissue permeability and pressure fields, quantities inaccessible to other methods.
Applied to the brain, MR-AIV reveals a functional landscape of interstitial and perivascular flow, quantitatively distinguishing slow diffusion-driven transport [โผ0.1 micrometers per second (ฮผm/s)] from rapid advective flow (โผ3 ฮผm/s).
This approach enables new investigations into brain clearance mechanisms and fluid dynamics in health and disease, with broad potential applications to other porous medium systems, from geophysics to tissue mechanics.
