New AI technique could revolutionize Alzheimer’s treatment

Researchers from the University of Rochester, led by Associate Professor Douglas Kelley, have developed a groundbreaking technique that utilizes artificial intelligence (AI) to measure fluid flow around the blood vessels of the brain. This innovative method has the potential to revolutionize the development of treatments for diseases like Alzheimer’s.

The perivascular spaces surrounding cerebral blood vessels play a crucial role in transporting fluid-like substances throughout the brain and facilitating the removal of waste products. Disruptions in fluid flow have been associated with various neurological conditions, including Alzheimer’s, small vessel disease, strokes, and traumatic brain injuries. However, accurately measuring these alterations in vivo has been challenging.

To address this issue, a multidisciplinary team of mechanical engineers, neuroscientists, and computer scientists collaborated to develop AI velocimetry measurements that provide precise calculations of brain fluid flow. The study, published in the Proceedings of the National Academy of Sciences, outlines the team’s findings.

Associate Professor Douglas Kelley 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.” Kelley, who is affiliated with the Department of Mechanical Engineering at the University of Rochester, highlights the significance of their research.

A video shows a perivascular space (area within white lines) into which the researchers injected tiny particles. The particles (shown as moving dots) are trailed by lines which indicate their direction. Having measured the position and velocity of the particles over time, the team then integrated this 2D video with physics-informed neural networks to create an unprecedented high-resolution, 3D look at the brain’s fluid flow system. Credit: Douglas Kelley

The research builds upon extensive experiments conducted by Maiken Nedergaard, co-author of the study and codirector of Rochester’s Center for Translational Neuromedicine. In previous studies, the team successfully conducted two-dimensional investigations of fluid flow in perivascular spaces by injecting minuscule particles into the fluid and tracking their position and velocity over time. However, gaining a comprehensive understanding of the intricate system required more sophisticated measurements, which posed a significant challenge given the vital and dynamic nature of the fluid system.

To overcome this challenge, the researchers collaborated with George Karniadakis from Brown University and harnessed the power of artificial intelligence. By combining the existing two-dimensional data with physics-informed neural networks, they were able to achieve unprecedented levels of resolution in their observations of the system.

Douglas Kelley explains, “This approach enables us to accurately determine pressures, forces, and three-dimensional flow rates, surpassing the capabilities of conventional methods. The measurement of pressure is particularly important, as the exact pumping mechanism that drives these flows around the brain remains unknown. This research opens up a new frontier in this field.”

The integration of artificial intelligence with the team’s experimental data allowed for a more comprehensive understanding of fluid dynamics within the perivascular spaces. This breakthrough technique provides valuable insights into the forces and flow rates involved, shedding light on the complex mechanisms governing fluid circulation in the brain.

Source: University of Rochester

Leave a Comment