Munich Startup: What does your startup do? What problem do you solve?
Kathrin Khadra, Ryver.ai: AI applications to support radiology often struggle with accuracy and robustness. In a broader context, this means that diseases in underrepresented patient groups, such as people of color or people with rare diseases, are detected less well by AI.
This is because access to test and training data is generally very difficult due to data protection and fragmented IT infrastructure. To obtain data, radiology AI providers either negotiate 12-24 month collaborations with hospitals or purchase data from brokers for up to 200 euros per image.
Ryver.ai solves this data shortage through AI-generated radiology data (e.g., X-rays, CTs, MRIs). You can think of our software like an art forger. Based on real images, it understands specific characteristics and can then generate completely new images, so-called synthetic data. The images can now be used to train radiology AI applications in clinical practice. Since the synthetic data is no longer directly attributable to real patients, it protects privacy.
Munich Startup: But that already exists, doesn’t it?
Kathrin Khadra: That’s true. Similar solutions have been used for years in developing autonomous vehicles. Much of the training data is merely simulations of traffic scenarios.
Ryver.ai uses the latest findings from generative AI research to achieve a quality level that makes synthetic data relevant for the healthcare market.
Solution for an urgent problem
Munich Startup: What’s your founding story?
Kathrin Khadra: We met a few years ago through scholarships. I know Jonas from the Manage and More scholarship at UnternehmerTUM and Simona through the Femtec scholarship.
In 2020, at the beginning of the lockdown, we founded a voucher platform together for small local shops in Munich to provide them with a revenue stream while they had to close their stores. That went really well, but we quickly realized it wasn’t a topic we wanted to work on for the next 10 years. So we handed it over to Regional Hero, who had built a very similar concept in Berlin and continue to pursue the topic.
After that, we sat down and began to think about what problem out there urgently needs a solution. We were quickly convinced that the massive data requirements for AI development combined with the high relevance of data protection represent a growing challenge. We tested several solutions for different industries, and one survived: synthetic data for radiology AI.
Munich Startup: What have been your biggest challenges so far?
Kathrin Khadra: Of course, developing the technology is very complex. Generating synthetic data at a quality level that can be used in a medical context presents many difficulties.
Introducing this technology into a very risk-averse market is at least equally difficult. We had to invest a lot of effort to gain the trust of potential customers.
Munich Startup: Where do you want to stand in one year, and where in five years?
Kathrin Khadra: By next year, we want to bring the first product for lung CTs with tumor indications to market following initial pilots. After that, we’ll continue to expand our generative models. This means adding new body parts like the head and abdomen as well as additional imaging modalities such as MRI.
In about five years, our solutions will be able to provide data for a very broad spectrum of applications in clinical AI as well as in the pharmaceutical industry.
“Driving force in the background”
Munich Startup: How have you experienced the Munich startup ecosystem so far?
Kathrin Khadra: Jonas and I have been part of the UnternehmerTUM ecosystem from hour zero. We started with the Manage and More scholarship, refined our idea in the Xplore program, and recently completed our funding round with support from Xpreneurs.
We’ve also continuously received support from the TUM Venture Labs. Antoine Leboyer, our mentor, for example, provided the crucial connection to our first investor.
The environment of fellow founders, all facing similar challenges, is incredibly valuable and helps us repeatedly when we have to make difficult decisions.
Munich Startup: Hidden champion or shooting star?
Kathrin Khadra: Above all, we want to solve a serious and major problem: safe medical AI for every patient. If that requires being a shooting star to draw attention to it, we’re happy to do so. Otherwise, we’re simply the driving force in the background.
