Cutting-edge research is utilizing artificial intelligence (AI) to provide insights into the flow of fluids in the brain

 

A groundbreaking technique powered by artificial intelligence (AI) has emerged for measuring fluid flow surrounding the blood vessels in the brain, holding significant implications for the development of treatments targeting diseases like Alzheimer's.

The perivascular spaces encompassing cerebral blood vessels play a crucial role in transporting fluid-like substances throughout the brain and aiding in waste clearance. Disruptions in fluid flow have been associated with neurological conditions such as Alzheimer's, small vessel disease, strokes, and traumatic brain injuries, but measuring these alterations in real-time poses challenges.

Led by Associate Professor Douglas Kelley from the University of Rochester, a multidisciplinary team of mechanical engineers, neuroscientists, and computer scientists devised a novel AI-based velocimetry method to precisely calculate brain fluid flow. The findings are detailed in a study published in the Proceedings of the National Academy of Sciences.

Kelley, a faculty member in Rochester's Department of Mechanical Engineering, explains, "In this study, we combined some measurements from inside the animal models with a novel AI technique that allowed us to effectively measure things that nobody's ever been able to measure before."

This research builds upon years of experiments led by Maiken Nedergaard, the codirector of Rochester's Center for Translational Neuromedicine and a coauthor of the study. Previous investigations conducted by the group involved two-dimensional studies of fluid flow in perivascular spaces by injecting minuscule particles into the fluid and tracking their position and velocity over time. However, a more intricate understanding of the system necessitated more complex measurements, which posed a challenge when exploring this vital fluid system.

To tackle this challenge, the team collaborated with George Karniadakis from Brown University and leveraged artificial intelligence. By integrating the existing two-dimensional data with physics-informed neural networks, they achieved unprecedented high-resolution insights into the system.

Kelley remarks, "This is a way to reveal pressures, forces, and the three-dimensional flow rate with much more accuracy than we can otherwise do. The pressure is important because nobody knows for sure quite what pumping mechanism drives all these flows around the brain yet. This is a new field."

The research received support from the Collaborative Research in Computational Neuroscience program, the National Institutes of Health Brain Initiative, and the Army Research Office's Multidisciplinary University Research Initiatives program.