Portable ultrasound device that assesses the structure and function of the human heart

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

The goal is to make ultrasound more accessible to a wider population, said Sheng Xu, a professor of nanoengineering at the University of California, San Diego, who leads the project. Currently, echocardiograms – ultrasound examinations of the heart – require highly trained technicians and bulky equipment.

“The technology allows anyone to use ultrasound imaging on the go,” Xu said.

Using custom AI algorithms, the device is able to measure the amount of blood pumped by the heart. This is important because the heart that does not pump enough blood is the cause of most cardiovascular disease. And problems with heart function often only show up when the body is in motion.

The work is described in the January 25 issue of the journal Nature.

Cardiac imaging is an essential clinical tool for assessing long-term heart health, detecting problems as they arise, and caring for critically ill patients. This new wearable, non-invasive heart monitor for humans provides real-time, automated information about the heart’s hard-to-capture pumping activity, even when a person is exercising.

The wearable heart monitoring system uses ultrasound to continuously capture images of the four heart chambers from different angles and analyze a clinically relevant subset of the images in real time using custom artificial intelligence technology. The project builds on the team’s previous advances in wearable imaging technologies for deep tissue.

The growing risk of heart disease calls for more advanced and inclusive monitoring procedures. By providing patients and physicians with deeper detail, continuous, real-time monitoring of cardiac images is poised to fundamentally optimize and reshape the cardiac diagnostics paradigm. »

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

In 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, and high-quality cardiac imaging, resulting in images with high spatial resolution, temporal resolution, and contrast. “It also minimizes patient discomfort and overcomes some limitations of noninvasive technologies such as CT and PET scans, which could expose patients to radiation,” said Hao Huang, a doctoral student in the Xu group at UC San Diego. .

The sensor’s unique design makes it ideal for moving bodies. “The device can be strapped to the chest with minimal constraint on subjects’ movements, even providing continuous recording of cardiac activities before, during and after exercise,” said Xiaoxiang Gao, postdoctoral researcher in the Xu group of UC San Diego.

The importance of cardiac imaging

Heart disease is the leading cause of death in older people and is also becoming more common in younger people due to lifestyle factors. The signs of heart disease are transient and unpredictable, making them difficult to spot. This has increased the demand for more advanced, inclusive, non-invasive and cost-effective monitoring technologies such as long-term cardiac imaging, which this wearable device facilitates.

Cardiac imaging is one of the most powerful tools for finding and diagnosing heart problems before they become problems. “The heart goes through all kinds of different pathologies,” said Hongjie Hu, a postdoctoral researcher at UC San Diego’s Xu lab. “Cardiac imaging will reveal the true story underneath. Whether it is a strong but normal contraction of the heart chambers resulting in fluctuating volumes, or a cardiac morphological problem has occurred in an emergency, monitoring in real-time image on the heart shows the whole image with vivid detail and visual effect.”

How it works in detail

The new system collects information through a wearable patch as soft as human skin, designed for optimal adhesion. The patch measures 1.9cm (L) x 2.2cm (W) x 0.09cm (T), approximately the size of a postage stamp. It sends and receives ultrasound waves which are used to generate a constant stream of images of the structure of the heart in real time. This ultrasonic patch is soft and stretchy, and it adheres well to human skin even during exercise.

The system can examine the left ventricle of the heart in separate biplane views using ultrasound, generating more clinically useful images than previously available. As a use case, the team demonstrated imaging of the heart during exercise, which is not possible with the rigid and bulky equipment used in clinical settings.

The performance of the heart is characterized by three factors: stroke volume (the volume of blood the heart pumps with each beat), ejection fraction (the percentage of blood pumped from the left ventricle of the heart with each beat) and cardiac output (the volume of blood the heart pumps every minute).

Xu’s team developed an algorithm to facilitate continuous AI-assisted automatic processing.

“A deep learning model automatically segments the shape of the left ventricle from the continuous image recording, extracting its volume frame by frame and outputting waveforms to measure stroke volume, stroke volume, cardiac output and ejection fraction,” said Mohan Li, a master’s student in the Xu group at UC San Diego.

“Specifically, the AI ​​component involves a deep learning model for image segmentation, a heart volume calculation algorithm, and a data imputation algorithm,” said Ruixiang Qi, a master’s student in the Xu group from UC San Diego. “We are using this machine learning model to calculate cardiac volume based on the shape and segmentation area of ​​the left ventricle. The imaging segmentation deep learning model is the first to be functionalized in devices portable ultrasound It allows the device to deliver accurate and precise continuous waveforms of key cardiac clues in different physical states, including static and after exercise, which has never been achieved before.”

Thus, this technology can generate curves of these three indices in a continuous and non-invasive way, because the AI ​​component processes the continuous stream of images to generate numbers and curves.

To create the platform, the team faced technical challenges that required careful decision making. To produce the wearable device itself, the researchers used a bonded 1-3 piezoelectric composite with an Ag-epoxy backing as the material for the transducers in the ultrasound imager, reducing risk and improving efficiency over methods previous ones. When choosing the transmission configuration of the transducer array, they achieved superior results with wide-beam compound transmission. They also selected from nine popular models for machine learning-based image segmentation, landing on FCN-32, which achieved the highest accuracy possible.

In the current iteration, the patch is connected via cables to a computer, which can download data automatically while the patch is still activated. The team developed a wireless circuit for the patch, which will be covered in an upcoming post.

Next steps

Xu plans to commercialize this technology through Softsonics, a UC San Diego spin-off company he co-founded with engineer Shu Xiang. He also encourages others in his scientific community to follow his example and work on areas of this research that merit further exploration.

To act on these findings, Xu recommends four immediate next steps:

• B-mode imaging, which allows for more diagnostic capabilities involving different organs
• The flexible imager design, which allows researchers to fabricate large transducer probes that cover multiple positions simultaneously
• Miniaturization of the back-end system that powers the software imager
• Work on a general machine learning model that scales to more topics