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.