UCSD wearable heart sensor technology. [Image courtesy of David Baillot, Jacobs School of Engineering, UC San Diego]
Engineers and physicians at the University of California, San Diego (UCSD) have developed a wearable ultrasound device to assess heart function and structure.
Roughly the size of a postage stamp, the device features a wear time of up to 24 hours and works during strenuous exercise.
Researchers aim to make ultrasound accessible to more people, according to the university. His Sheng Xu, professor of nanoengineering at UCSD, is leading the project. Details of the work to date appear in his January 25th issue of the journal. Nature.
“This technology will allow anyone to use ultrasound imaging on the go,” said Xu. Said.
Researchers say the device can measure how much blood the heart pumps, thanks to custom AI algorithms.
A wearable monitoring system uses ultrasound to continuously capture images of the heart’s four chambers from different angles. Analyze clinically relevant subsets of images in real time using custom-built AI technology.
“With the increased risk of heart disease, we need more sophisticated and comprehensive surveillance procedures,” said Xu. “By providing patients and physicians with more detailed information, continuous, real-time cardiac imaging monitoring is poised to fundamentally optimize and reshape the cardiac diagnostic paradigm.”
Student Hao Huang, Ph.D., a member of Xu’s group at UCSD, says the system minimizes patient discomfort. Huang said it also overcomes the limitations of non-invasive techniques such as his CT and PET, which can expose patients to radiation.
Learn more about UCSD devices
The design of the device allows it to be mounted on the chest with minimal restriction to the user’s movements. Collect information via wearable patches that are “soft as human skin”. This system sends and receives ultrasound waves that are used to produce a continuous stream of images of the heart’s structures in real time.
The system uses ultrasound to examine the heart’s left ventricle in two separate planes, researchers say. The team developed an algorithm that facilitates continuous AI-assisted automated processing.
“A deep learning model automatically segments the shape of the left ventricle from continuous image recordings, extracts its volume frame-by-frame, and generates waveforms to calculate stroke volume, cardiac output, and ejection fraction. We measure,” said Mohan Li. His Xu group at UCSD.
This technology can generate curves to provide accurate, continuous waveforms of key cardiac indicators in a variety of physical conditions. Its AI component processes a continuous stream of images to generate numbers and curves.
“Specifically, AI components include deep learning models for image segmentation, algorithms for heart volume calculation, and data imputation algorithms,” says Ruixiang Qi, a master’s student in UCSD’s Xu Group. said Mr. “We use this machine learning model to calculate the volume of the heart based on the shape and area of the left ventricular segmentation. The imaging segmentation deep learning model was first functionalized in a wearable ultrasound device.
The current iteration of the patch connects to your computer via a cable. The computer can then automatically download the data while the user is wearing the patch. The team also developed a radio circuit for the patch. Xu intends to commercialize the technology through his Softsonics, which he spun out of his UCSD, which he co-founded.
