A Wearable Ultrasound Device to Evaluate Human Heart Structure and Function

Engineers and doctors have developed a wearable ultrasound device that can assess both the structure and function of the human heart. The portable device, about the size of a postage stamp, can be worn for up to 24 hours and works during strenuous exercise.

Sheng Xu, a nanoengineering professor at the University of California, San Diego, who is leading the project, says the goal is to make ultrasound accessible to more people. Currently, echocardiography, an ultrasound examination of the heart, requires highly trained technicians and large equipment.

“This technology will allow anyone to use ultrasound imaging on the go,” said Xu.

Thanks to custom AI algorithms, the device can measure how much blood your heart pumps. This is important because the heart’s inability to pump enough blood is the cause of most cardiovascular disease. Also, problems with heart function often only appear when the body is in motion.

The work is published in the January 25th issue of the magazine. Nature.

Cardiac imaging is an essential clinical tool for assessing long-term heart health, detecting developing problems, and treating critically ill patients. This new wearable, non-invasive human heart monitor provides real-time, automated insight into elusive heart pumping activity, even during exercise.

Wearable cardiac monitoring system uses ultrasound to continuously capture images of the heart’s four chambers from different angles and uses custom AI technology to analyze clinically relevant subsets of images in real time To do. This project builds on the team’s previous progress in deep tissue wearable imaging technology.

Due to the increased risk of heart disease, more sophisticated and comprehensive surveillance procedures are needed. 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. ”

Sheng Xu, Professor of Nanoengineering, University of California, San Diego

By comparison, existing non-invasive methods have limited sampling capabilities and provide limited data. The wearable technology developed by Xu’s team enables safe, non-invasive, high-quality cardiac imaging, resulting in images with high spatial resolution, temporal resolution, and contrast. “It also minimizes patient discomfort and overcomes some of the limitations of his non-invasive techniques, such as CT and PET, which can expose patients to radiation,” said the University of California San Diego’s. said Hao Huang, a doctoral student at his Xu Group.

The unique design of the sensor makes it ideal for moving objects. Xiaoxiang Gao, a postdoctoral fellow in his Xu group at the University of California, San Diego, said:

Importance of cardiac imaging

Cardiovascular disease is the number one cause of death among the elderly, and is on the rise among young people due to lifestyle factors. Symptoms of heart disease are transient and unpredictable, making them difficult to detect. This is driving demand for more advanced, comprehensive, non-invasive, and cost-effective monitoring techniques, such as long-term cardiac imaging facilitated by this wearable device.

Cardiac imaging is one of the most powerful tools for screening and diagnosing heart problems before they become problems. Hongjie Hu, a postdoctoral fellow in his Xu lab at the University of California, San Diego, said: “Cardiac imaging reveals the underlying true story: whether strong but normal contractions of heart chambers lead to volume fluctuations or, as an emergency, morphological problems of the heart have developed. Regardless, real-time imaging monitoring of the heart conveys the big picture with vivid detail and visual effects.”

How it works in detail

This new system gathers information through a wearable patch as soft as human skin, designed for optimal adhesion. The patch measures 1.9 cm (L) x 2.2 cm (W) x 0.09 cm (T), the size of a postage stamp. It sends and receives ultrasound waves that are used to produce a constant stream of images of the heart’s structures in real time. This ultrasonic patch is soft and stretchy and adheres well to the skin during exercise.

The system can use ultrasound to examine the left ventricle of the heart in separate biplane views, producing more clinically useful images than before. As a use case, the team demonstrated cardiac imaging during exercise, which is not possible with the stiff and cumbersome equipment used in clinical settings.

Cardiac performance is measured by stroke volume (the amount of blood the heart pumps with each beat), ejection fraction (the percentage of blood pumped out of the heart’s left ventricle with each beat), and cardiac output (the amount of blood the heart pumps with each beat). the amount of blood pumped out each minute).

Xu’s team developed algorithms that facilitate continuous AI-powered automation.

“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. Measure.” Xu Group at UC San Diego.

“Specifically, AI components include deep learning models for image segmentation, algorithms for heart volume calculations, and data imputation algorithms,” says a master’s student at the Xu Group at the University of California, San Diego. student Ruixiang Qi said. “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 is the first to be functionalized in a wearable ultrasound device. Continuous waveforms of key cardiac indices in a variety of static and post-exercise physical states never before achieved.”

Therefore, this technology can continuously and non-invasively generate curves for these three indicators as the AI ​​component processes a continuous stream of images to generate numbers and curves.

To create the platform, the team faced several technical challenges that required careful decision making. To fabricate the wearable device itself, the researchers used a piezoelectric 1-3 composite bonded with an Ag-epoxy backing as the material for the transducer of the ultrasound imager, reducing the risk and improving the performance of previous methods. Improved efficiency. When choosing the transmit configuration of the transducer array, the wide-beam compound transmission gave excellent results. They also chose from his nine popular models for machine learning-based image segmentation and landed on his FCN-32, which achieved the highest possible accuracy.

In the current iteration, the patch is connected to your computer via a cable and can automatically download data while the patch is still on. The team developed a wireless circuit for the patch.

next step

Xu plans to commercialize the technology through Softsonics, a UC San Diego spinoff he co-founded with engineer Shu Xiang. He also encourages others in his scientific community to follow his lead and work on this area of ​​research that needs further investigation.

To follow up on these results, Xu immediately recommends the following four steps.

• B-mode imaging enabling more diagnostic capabilities, including various organs
• Designing a Soft Imager to Allow Researchers to Fabricate Large Transducer Probes Covering Multiple Locations Simultaneously
• Miniaturization of the back-end system that drives the soft imager
• We are working towards a general machine learning model that fits more subjects