Recent advances in portable ultrasound technologies have demonstrated the potential for hands-free data acquisition. There are technical barriers, however, as these probes require wire connections, can lose sight of moving targets, and cause data interpretation problems.
A new study by a team of engineers at the University of California San Diego has reported a fully integrated autonomous portable ultrasound system-on-patch (USoP). It is the first fully integrated portable ultrasonic system for deep-tissue monitoring, even on the go.
Muyang Lin, a Ph.D. candidate in the Department of Nanoengineering at UC San Diego and the study’s first author, said: “This project offers a complete solution for portable ultrasound technology: not only the portable sensor but also the control electronics are made in portable form factors. We have created a wearable device that can wirelessly detect vital signs in deep tissue.”
USoP builds on the lab’s previous soft ultrasonic sensor design work. While previous soft ultrasonic sensors require connecting cables for data and power transfer, user mobility is limited.
This technique uses an ultrasonic transducer array to communicate with a small, flexible control circuit to collect and transmit data wirelessly. The data is interpreted using machine learning, which also tracks moving subjects.
According to the lab’s findings, the ultrasound system-on-patch enables continuous tracking of physiological signals from tissues up to 164 mm, continuously measuring central blood pressure, heart rate, cardiac output and other physiological signals for up to twelve hours.
“This technology has great potential to save and improve lives,” Lin said. “The sensor can evaluate cardiovascular function in motion. Abnormal blood pressure values and cardiac output, whether at rest or during exercise, are hallmarks of heart failure. For healthy populations, our device can measure cardiovascular responses to exercise in real time, providing insight into each person’s actual exercise intensity, which can lead to personalized training plans.”
Ziyang Zhang, a master’s student in the Department of Computer Science and Engineering at UC San Diego and co-first author, said: “In the end, we made the generalization of the machine learning model work by applying an advanced fitting algorithm. This algorithm can automatically minimize the differences in domain distribution between different subjects, which means that the machine intelligence can be transferred from subject to subject. With minimal retraining, we can train the algorithm on one subject and apply it to many other new subjects.”
- Lin, M., Zhang, Z., Gao, X., et al. A fully integrated portable ultrasound system to monitor deep tissues in moving subjects. Nat Biotechnology (2023). DOI: 10.1038/s41587-023-01800-0