Key Points
- Researchers developed a machine learning algorithm that is optimizing focused ultrasound–mediated blood-brain barrier opening procedures.
- Results from this preclinical study should lead to more effective drug delivery and disease detection in humans.
Focused ultrasound, when combined with the intravenous injections of microbubbles, safely and transiently opens the blood-brain barrier (BBB). Opening the BBB can enhance the delivery of a variety of therapeutic agents to the brain and also promote the release of disease-associated molecules for use in liquid biopsy assays.
In a recently published study, Costas Arvanitis, PhD, associate professor of mechanical engineering and biomedical engineering, and his team of researchers at the Georgia Institute of Technology developed a machine learning–assisted, closed-loop ultrasound system that continuously listens to acoustic signals generated by microbubbles.
The team’s data-driven approach enabled the identification of safer, more effective ultrasound exposure settings while also improving the consistency and reliability of BBB opening.
Using more than 54,000 acoustic datasets collected during experiments, the researchers trained the machine learning model to enable the focused ultrasound system to detect subtle acoustic patterns that may precede harmful microbubble behavior.
The Georgia Tech team and their collaborators from the University of Maryland and Johns Hopkins University showed that the method translated effectively from mice to rats, marking an important step toward clinical translation. Because the system is flexible and data-driven, it could eventually be incorporated into existing focused ultrasound platforms and tailored to individual patients.
“This approach represents a promising shift in how we perform BBB opening with focused ultrasound and microbubbles, from fixed or reactive protocols to adaptive, data-driven sonication strategies,” said Dr. Arvanitis. “By leveraging machine learning, we can better anticipate microbubble behavior and optimize the treatment in real time to achieve safer and more effective BBB opening. This has the potential to improve the delivery of next-generation therapeutics to the brain, while also enabling new focused ultrasound–based liquid biopsy approaches for diagnosis and treatment monitoring.”
In the future, clinicians may be able to confirm BBB opening treatment effects without relying on MRI. The technology could also enable shorter, more cost-effective, and more accessible outpatient treatments. The next phase of this research will focus on adapting and validating the system for use in humans.
This study was supported by the National Institutes of Health National Cancer Institute and the Focused Ultrasound Foundation.
See Advanced Science (Open Access)
See Georgia Tech’s Press Release
Related Stories
Method Established for Measuring and Predicting Blood-Brain Barrier Opening with Focused Ultrasound August 2025
Focused Ultrasound for Drug Delivery to the Brain: Ultrasound Frequency Matters January 2025