UZ sensor for analyzing the work of the heart in motion

2023: Product Announcement

In late January 2023, UC San Diego unveiled a wearable ultrasound device that analyzes how the heart works in motion.

The wearable heart monitoring system uses ultrasound to continuously capture images of four heart cameras from different angles and analyzes the clinically relevant portion of the images in real time using specially designed AI technology. The project draws on previous advances by a team at the University of California in wearable deep tissue imaging technologies. The ultrasound sensor, developed by a team of scientists, provides safe, non-invasive and high-quality cardiac imaging, resulting in images with high spatial resolution, temporal resolution and contrast.

The system collects information through a wearable patch as soft as human skin designed for optimal fit. A patch measuring 1.9 cm (D) x 2.2 cm (W) x 0.09 cm (T), about the size of a postage stamp. It sends and receives ultrasonic waves, which are used to create a constant stream of real-time images of the heart's structure. This ultrasonic patch is soft and stretchable, sticking well to human skin even during physical exertion.

UZ sensor for analyzing the work of the heart in motion

The system can examine the left ventricle of the heart in separate two-plane projections using ultrasound, producing more clinically useful images than those available until January 2023. As a practical example, the team of scientists demonstrated imaging of the heart during exercise, which is not possible with rigid and bulky equipment used in clinical settings. The technology can generate curves of these three cardiac measures continuously and non-invasively, as the AI component processes a continuous stream of images to generate numbers and curves.

To manufacture the device, the researchers used a piezoelectric composite 1-3 coupled to an Ag-epoxy base as a material for transducers in an ultrasonic imager. This allowed to reduce risk and increase efficiency compared to previous methods. When choosing the transmission configuration of the sensor array, the researchers achieved excellent results through broad-beam composite transmission. They also selected one of nine popular models for machine learning-based image segmentation, settling on the FCN-32 that provided the highest possible accuracy.

As of January 31, 2023, the patch connects through cables to a computer that can automatically download data until the patch is removed. The team developed a wireless circuit for the patch, which will be discussed in March 2023. The developers plan to commercialize the technology through Softsonics, a company based at the University of California, San Diego.^[1]

Notes