A month after it got FDA approval, a startup’s first product was saving lives on the front lines of the battle against COVID-19.
Caption Health develops software for ultrasound systems, called Caption AI. It uses deep learning to empower medical professionals, including those without prior ultrasound experience, to perform echocardiograms quickly and accurately.
The results are images of the heart often worthy of an expert sonographer that help doctors diagnose and treat critically ill patients.
The coronavirus pandemic provided plenty of opportunities to try out the first dozen systems. Two doctors who used the new tool shared their stories on the condition they are their patients remain anonymous.
A 53-year-old diabetic woman with COVID-19 went into cardiac shock in a New York hospital. Without the images from Caption AI, it would have been difficult to clinch the diagnosis, said a doctor on the scene.
The system helped the physician identify heart problems in an 86-year-old man with the virus in the same hospital, helping doctors bring him back to health. It was another case among more than 200 in the facility that was effectively turned into a COVID-19 hospital in mid-March.
The Caption Health system made a tremendous impact for a staff spread thin, said the doctor. It would have been hard for a trained sonographer to keep up with the demand for heart exams, he added.
Heart Test Becomes Standard Procedure
Caption AI helped doctors in North Carolina determine that a 62-year-old man had COVID-19-related heart damage. Thanks, in part, to the ease of using the system, the hospital now performs echocardiograms for most patients with the virus.
At the height of the pandemic’s first wave, the hospital stationed ultrasound systems with Caption AI in COVID-19 wards. Rather than sending sonographers from unit to unit, the usual practice, staff stationed at the wards used the systems. The change reduced staff exposure to the virus and conserved precious protective gear.
Beyond the pandemic, the system will help hospitals provide urgent services while keeping a lid on rising costs, said a doctor at that hospital.
“AI-enabled machines will be the next big wave in taking care of patients wherever they are,” said Randy Martin, chief medical officer of Caption Health and emeritus professor of cardiology at Emory University.
Martin joined the startup about four years ago after meeting its founders, who shared expertise and passion for medicine and AI. Today their software “takes a user through 10 standard views of the heart, coaching them through some 90 fine movements experts make,” he said.
“We don’t intend to replace sonographers; we’re just expanding the use of portable ultrasound systems to the periphery for more early detection,” he added.
Coping with an Unexpected Demand Spike
In the early days of the pandemic, that expansion couldn’t come fast enough.
In late March, the startup exhausted supplies that included NVIDIA Quadro P3000 GPUs that ran its AI software. In the early days of the global shutdown, the startup reached out to its supply chain.
“We are experiencing overwhelming demand for our product,” the company’s CEO wrote, after placing orders for 100 GPUs with a distributor.
Caption Health has systems currently in use at 11 hospitals. It expects to deploy Caption AI at a number of additional sites in the coming weeks.
GPUs at the Heart of Automated Heart Tests
The startup currently integrates its software in a portable ultrasound from Terason. It intends to partner with more ultrasound makers in the future. And it advises partners to embed GPUs in their future ultrasound equipment.
The Quadro P3000 in Caption AI runs real-time inference tasks using deep convolutional neural networks. They provide operators guidance in positioning a probe that captures images. Then they automatically choose the highest-quality heart images and interpret them to help doctors make informed decisions.
The NVIDIA GPU also freed up four CPU cores, making space to process other tasks on the system, such as providing a smooth user experience.
The startup trained its AI models on a database of 1 million echocardiograms from clinical partners. An early study in partnership with Northwestern Medicine and the Minneapolis Heart Institute showed Caption AI helped eight registered nurses with no prior ultrasound experience capture highly accurate images on a wide variety of patients.
Inception Program Gives Startup Traction
Caption Heath, formerly called Bay Labs, was founded in 2015 in Brisbane, Calif. It received a $125,000 prize at a 2017 GTC competition for members of NVIDIA’s Inception program, which gives startups access to technology, expertise and markets.
“Being part of the Inception program has provided us with increased recognition in the field of deep learning, a platform to share our AI innovations with healthcare and deep learning communities, and phenomenal support getting NVIDIA GPUs into our supply chain so we could deliver Caption AI,” said Charles Cadieu, co-founder and president of Caption Health.
Now that its tool has been tested in a pandemic, Caption Health looks forward to opportunities to help save lives across many ailments. The company aims to ride a trend toward more portable systems that extend availability and lower costs of diagnostic imaging.
“We hope to see our technology used everywhere from big hospitals to rural villages to examine people for a wide range of medical conditions,” said Cadieu.
To learn more about Caption Health and other companies like it, watch the webinar on healthcare startups against COVID-19 Heart of the Matter: AI Helps Doctors Navigate Pandemic appeared first on The Official NVIDIA Blog.
Around the world, researchers in startups, academic institutions and online communities are developing AI models for healthcare. Getting these models from their hard drives and into clinical settings can be challenging, however.
Developers need feedback from healthcare practitioners on how their models can be optimized for the real world. So, San Francisco-based AI startup Arterys built a forum for these essential conversations between clinicians and researchers.
Called the Arterys Marketplace, and now integrated with the NVIDIA Clara Deploy SDK, the platform makes it easy for researchers to share medical imaging AI models with clinicians, who can try it on their own data.
“By integrating the NVIDIA Clara Deploy technology into our platform, anyone building an imaging AI workflow with the Clara SDK can take their pipeline online with a simple handoff to the Arterys team,” said Christian Ulstrup, product manager for Arterys Marketplace. “We’ve streamlined the process and are excited to make it easy for Clara developers to share their models.”
Researchers can submit medical imaging models in any stage of development — from AI tools for research use to apps with regulatory clearance. Once the model is posted on the public Marketplace site, anyone with an internet connection can test it by uploading a medical image through a web browser.
Models on Arterys Marketplace run on NVIDIA GPUs through Amazon Web Services for inference.
A member of both the NVIDIA Inception and AWS Activate programs, which collaborate to help startups get to market faster, Arterys was founded in 2011. The company builds clinical AI applications for medical imaging and launched the Arterys Marketplace at the RSNA 2019 medical conference.
It recently raised $28 million in funding to further develop the ecosystem of partners and clinical-grade AI solutions on its platform.
Several of the models now on the Arterys Marketplace are focused on COVID-19 screening from chest X-rays and CT images. Among them is a model jointly developed by NVIDIA’s medical imaging applied research team and clinicians and data scientists at the National Institutes of Health. Built in under three weeks using the NVIDIA Clara Train framework, the model can help researchers study the detection of COVID-19 from chest CT scans.
Building AI Pillar of the Community
While there’s been significant investment in developing AI models for healthcare in the last decade, the Arterys team found that it can still take years to get radiologists’ hands on the tools.
“There’s been a huge gap between the smart, passionate researchers building AI models for healthcare and the end users — radiologists and clinicians who can use these models in their workflow,” Ulstrup said. “We realized that no research institution, no startup was going to be able to do this alone.”
The Arterys Marketplace was created with simplicity in mind. Developers need only fill out a short form to submit an AI model for inclusion, and then can send the model to users as a URL — all for free.
For clinicians around the world, there’s no need to download and install an AI model. All that’s needed is an internet connection and a couple medical images to upload for testing with the AI models. Users can choose whether or not their imaging data is shared with the researchers.
The images are analyzed with NVIDIA GPUs in the cloud, and results are emailed to the user within minutes. A Slack channel provides a forum for clinicians to provide feedback to researchers, so they can work together to improve the AI model.
“In healthcare, it can take years to get from an idea to seeing it implemented in clinical settings. We’re reducing that to weeks, if not days,” said Ulstrup. “It’s absurdly easy compared to what the process has been in the past.”
With a focus on open innovation and rapid iteration, Ulstrup says, the Arterys Marketplace aims to bring doctors into the product development cycle, helping researchers build better AI tools. By interacting with clinicians in different geographies, developers can improve their models’ ability to generalize across different medical equipment and imaging datasets.
Over a dozen AI models are on the Arterys Marketplace so far, with more than 300 developers, researchers, and startups joining the community discussion on Slack.
“Once models are hosted on the Arterys Marketplace, developers can send them to researchers anywhere in the world, who in turn can start dragging and dropping data in and getting results,” Ulstrup said. “We’re seeing discussion threads between researchers and clinicians on every continent, sharing screenshots and feedback — and then using that feedback to make the models even better.”
Check out the research-targeted AI COVID-19 Classification Pipeline developed by NVIDIA and NIH researchers on the Arterys Marketplace. To hear more from the Arterys team, register for the Startups4COVID webinar, taking place July 28.
The post Taking AI to Market: NVIDIA and Arterys Bridge Gap Between Medical Researchers and Clinicians appeared first on The Official NVIDIA Blog.