Pneumonia diagnosis

Democratizing Ultrasound with Caption: How AI Can Transform Pneumonia Diagnosis

First used in the 1950s, ultrasound relies on high-frequency sound waves to provide cross-sectional images of the body. Over the past 60+ years, ultrasound has become an essential technology for rapid diagnosis, particularly because it is cheaper and more accurate than many other imaging methods.

After selling artificial intelligence (AI)-based image recognition startup IQ Engines to Yahoo in 2013, Kilian Koepsell and Charles Cadieu decided to apply the same technology to other areas where it might have a positive impact. They concluded that the right use case was to tackle a bottleneck in medical imaging and ultrasound in particular: the need for highly skilled professionals.

To solve this problem, Koepsell and Cadieu co-founded Legend Health around the principle, it is necessary to apply technology to “imitate the expertise of highly qualified medical experts and put this capacity in the hands of every care provider”.

The Bill & Melinda Gates Foundation spotted the work Caption was doing to develop AI ultrasound software — known as Caption AI — for the heart. This led the foundation to award Caption a $4.95 million grant in November to develop similar AI technology for lung ultrasounds to improve the rapid and accurate diagnosis of pneumonia, one a leading killer of young children and a huge health threat in the developing world.

Spotlight on Captioning AI

Caption AI guides any healthcare professional in performing and then interpreting a cardiac ultrasound. Unlike other AI technologies that simply support image evaluation and interpretation for diagnostic purposes, Caption noticed that the challenge is actually having the training to produce a good quality image. in the first place.

Caption AI guides both the user to produce the image, as well as image evaluation to support diagnosis, explains Koepsell, who is Caption’s CTO.

The AI ​​software was developed for the heart because doctors identified it as the most difficult organ to image medically. Additionally, heart disease is widespread and is one of the leading causes of death worldwide.

Koepsell explains: “The more we looked, the more we learned that – specifically for the heart – it is very difficult to have good eyesight. It takes a lot of training to understand what’s going on and how to adjust the probe.

To guide the medical professional, Caption “recreated the entire user interface,” according to Koepsell. He explains, “Rather than just showing a gray 2D ultrasound cone that then needs to be interpreted, we have on-screen instructions.”

The AI ​​software gives feedback and advice on which direction to move the probe for best impact. Koepsell adds, “Caption AI really walks you through until they have the image they’re looking for. It automatically saves the image and then guides them to the next image. »

In July 2020, Caption AI became the first AI cardiac ultrasound software to be approved by the United States Food and drug administration (FDA). The approved software was then integrated into a marketable device developed by a partner. According to Koepsell, the software and device are already available in 20 hospitals across the United States.

Democratizing access to lung ultrasounds

Although preventable and treatable, pneumonia remains the leading cause of death in children under five worldwide. The lung disease tragically killed 1.3 million children in 2011 and was responsible for 18% of child deaths worldwide, according to the Gates Foundation.

In addition to its work rolling out vaccination programs in developing countries to protect children from pneumonia, the Gates Foundation is also focused on improving access to other diagnostic and treatment tools.

As part of this, the global health charity looked at what Caption was doing to democratize cardiac ultrasound and how this could be extended to the lungs. “The Gates Foundation focuses on areas where $1 can have the greatest impact,” says Koepsell. He adds that one of the biggest challenges in addressing global health challenges is detection and therefore ultrasound has a huge role to play here.

Similar to the cardiac ultrasound market, the bottleneck in the lung ultrasound field is a lack of trained users with the correct level of clinical skills and technological expertise. There is therefore an urgent need for solutions like Caption to democratize access to high quality medical images.

Associate Professor of Emergency Medicine at Yale University and Chief of Emergency Ultrasound Dr. Chris Moore wrote in a Release“Extending this AI to lung ultrasound and putting it in the hands of clinicians could have profound implications for the diagnosis and treatment of pneumonia, one of the leading causes of death among our youngest citizens around the world, as well than for Covid-19 and other lung conditions.”

The need for high quality and accessible ultrasound has only become more evident in the Covid-19 pandemic. Even though Caption and the Gates Foundation began discussing this project before Covid-19, Koepsell notes that there has been an increased use of bedside ultrasound due to Covid-19 and that a real bottleneck of bottleneck in the pandemic has been the lack of staff. Therefore, the pandemic has highlighted the importance of democratized lung ultrasound.

The $4.95 million grant from Caption’s Gates Foundation lasts two years, and Koepsell hopes the ultrasound software will be ready for deployment during that time. However, the next bottleneck to the widespread use of Caption’s software is the cost of the ultrasound devices themselves.

That element is beyond Caption’s purview, but Koepsell notes that the company is working with hardware developers and he’s optimistic that sufficiently inexpensive devices will become available within the next few years.

Related companies