I will be taking a brief hiatus for the next three months. I’m going to be using this time to step back, reflect, and rework the format of the show to bring you even more valuable insights and engaging conversations. I’m looking forward to returning in the fall with fresh episodes, new guests, and even deeper dives into the challenges and opportunities shaping mission-driven machine learning-powered companies.

In the meantime, I'm thrilled to share another way you can continue to learn and engage with the world of AI through Pixel Scientia Labs. While the podcast is on pause, I invite you to explore our Webinar Initiative at pixelscientia.com/webinars.

Links:

• Webinars from Pixel Scientia

What role can artificial intelligence play in detecting breast cancer earlier, when it's most treatable? In this episode of Impact AI, we hear from Nico Karssemeijer, Chief Science Officer of ScreenPoint Medical, about how his team is using AI to transform breast cancer screening. Drawing on more than four decades of experience in medical imaging, Nico shares how ScreenPoint’s AI tools assist radiologists by analyzing mammograms, highlighting suspicious areas, and even learning from years of patient data. The conversation explores what it takes to build trustworthy medical AI, overcome challenges with data diversity and device bias, and the importance of clinical validation. To find out how AI is being integrated into real-world healthcare to improve outcomes (and what goes into building a successful AI-powered medical company), tune in today!

Key Points:

• What led Nico to turn decades of research into a breast imaging AI startup.
• How ScreenPoint uses AI to support radiologists in early detection.
• Challenges of working with diverse data from different imaging devices.
• The importance of training models with clean, representative data.
• Strategies for reducing bias across vendors and populations.
• How independent, real-world validation drives trust and clinical adoption.
• Finding a balance between model accuracy and explainability.
• Why domain expertise is crucial for building a successful AI-powered startup.
• Driving adoption in medical AI through clinical partnerships and rigorous trials.

Quotes:

“It’s amazing how much more information you can get out of the mammograms [using AI]. That surprises me all the time.” — Nico Karssemeijer

“You can't just say, ‘This mammogram is abnormal,’ because then [the radiologists] are puzzled. – The algorithm is getting so good that it identifies areas the radiologists would probably not see by themselves. – You have to – mark the area in the exam where a lesion is found.” — Nico Karssemeijer

“It's incredibly important to have enough domain expertise when you start a company, because it's easy to fail because you don't understand well enough what the customer wants [or] where the field is going.” — Nico Karssemeijer

Links:

Nico Karssemeijer

ScreenPoint Medical

Nico Karssemeijer on LinkedIn

Nico Karssemeijer on Google Scholar

Resources for Computer Vision Teams:

LinkedIn – Connect with Heather.

Computer Vision Insights Newsletter – A biweekly newsletter to help bring the latest machine learning and computer vision research to applications in people and planetary health.

Computer Vision Strategy Session – Not sure how to advance your computer vision project? Get unstuck with a clear set of next steps. Schedule a 1 hour strategy session now to advance your project.

How can we harness medical imaging and artificial intelligence to shift healthcare from reactive to predictive? In this episode, I sit down with Ángel Alberich-Bayarri to discuss how artificial intelligence is revolutionizing radiology and precision medicine. Ángel is the CEO of Quibim, a company recognized globally for its AI-powered tools that turn radiological scans into predictive biomarkers, enabling more precise diagnoses and personalized treatments.

In our conversation, we hear how his early work in radiology and engineering led to the founding of Quibim and how the company’s AI-based technology transforms medical images into predictive biomarkers. We unpack the challenges of data heterogeneity, how Quibim tackles image harmonization using self-supervised learning, and why accounting for regulations is critical when building healthcare AI products. Ángel also shares his perspective on the value of model explainability, the concept of digital twins, and the future of preventative imaging. Join us to discover how AI is disrupting clinical decision-making and preventive healthcare with Ángel Alberich-Bayarri.

Key Points:

• Hear about Ángel’s background and how his career led to founding Quibim.
• Find out how Quibim turns radiology images into predictive clinical insights.
• Different use cases of Quibim’s technology and why biopsy data is important.
• He explains why Quibim avoids relying solely on radiologist annotations.
• Challenges of using medical imaging: data fragmentation and scanner variability.
• Explore Quibim’s self-supervised image learning harmonization techniques.
• How Quibim increases the explainability of the model while maintaining accuracy.
• Why understanding clinical workflows and radiologist adoption behavior is critical.
• Uncover how regulations influence the development of Quibim’s technology.
• Ángel’s advice for entrepreneurs and leaders of AI-powered startups.
• Quibim’s plans for predictive modeling, digital twins, and AI for preventative medicine.

Quotes:

“We would like AI to be able to mine all this hidden information we have right now in the images. Our vision is long-term, being able to understand what is happening until this point within the human body.” — Ángel Alberich-Bayarri

“What [Quibim is] investing in is the next frontier that not only detects and diagnoses disease, but also predicts or prognoses what is going to happen.” — Ángel Alberich-Bayarri

“Human behavior has a lot of nuances that need to be appreciated when AI is adopted.” — Ángel Alberich-Bayarri

“The bolder the claims you make, it’s the higher level of evidence you need to achieve.” — Ángel Alberich-Bayarri

“Taking care of health before we have symptoms, it’s just going to be a growing business, and therefore, a lot of AI tools will be needed to understand our inner us.” — Ángel Alberich-Bayarri

Links:

Ángel Alberich-Bayarri on LinkedIn

Ángel Alberich-Bayarri on X

Quibim

Resources for Computer Vision Teams:

LinkedIn – Connect with Heather.

Computer Vision Insights Newsletter – A biweekly newsletter to help bring the latest machine learning and computer vision research to applications in people and planetary health.

Computer Vision Strategy Session – Not sure how to advance your computer vision project? Get unstuck with a clear set of next steps. Schedule a 1 hour strategy session now to advance your project.

Drug development is notoriously time-consuming and expensive, but what if we could simulate clinical trials before they even begin? Orr Inbar, Co-Founder and CEO of QuantHealth, joins me to explore how his team is doing just that. By simulating trials with AI-native models, QuantHealth helps pharmaceutical companies make better decisions about how to design trials and test drugs.

Orr shares how QuantHealth uses real-world patient data and detailed drug biology to build deep-learning models capable of forecasting patient responses to new therapies. He breaks down their biggest challenges, like the complexities of messy healthcare data, hidden biases, and the importance of domain knowledge when building AI tools for regulated environments. He also shares a key lesson for any AI startup: focus on solving real problems, not just building clever models. Tune in for a fascinating look at how AI is reshaping drug development and what the future of clinical trials could look like!

Key Points:

• Some background on Orr, his parents, and how he founded QuantHealth.
• Key problems QuantHealth is solving as a clinical trial simulation company.
• A breakdown of the biggest challenges facing clinical trials.
• Why we need to improve data-driven trials of drugs.
• How QuantHealth builds their foundation models for trial simulations.
• Examples of the type of predictions their models make in clinical contexts.
• How they use patient and drug data to make predictions and build “digital drugs”.
• Key challenges of working with these different types of data.
• Methods for combating bias, including the use of exogenous data. 
• How they incorporate the medical context in model development.
• QuantHealth’s validation process: how they meet rigorous industry standards.
• Orr’s advice to other AI startups on creating value, not just smart models.
• Where you can expect to see QuantHeath in the next three to five years.

Quotes:

“There is a constant desire in drug development and pharmaceutical research to get your hands on more data. This makes sense since it's a very data-driven industry. But at the same time, there was a mismatch there, because there's actually quite a lot of data already out there.” — Orr Inbar

“How do we bridge the gap between the data that we already have and the insights that we need to generate to answer those questions?” — Orr Inbar

“If you take a step back and look at how drugs are being developed today and with an emphasis on clinical trials, we're essentially doing the same things that we were doing 50 years ago.” — Orr Inbar

“Even in a world of GenAI, you can't just snap your fingers and get the solution. It requires a lot of work to structure and harmonize the data.” — Orr Inbar

“Every trial that we simulate, we first go through a data enrichment process where we look for the latest information in terms of research publications, recently completed trials that are relevant to our drug of interest, and incorporate that data into our data sets.” — Orr Inbar

Links:

Orr Inbar on LinkedIn
QuantHealth

Resources for Computer Vision Teams:

LinkedIn – Connect with Heather.

Computer Vision Insights Newsletter – A biweekly newsletter to help bring the latest machine learning and computer vision research to applications in people and planetary health.

Computer Vision Strategy Session – Not sure how to advance your computer vision project? Get unstuck with a clear set of next steps. Schedule a 1 hour strategy session now to advance your project.

The recent destruction of the Pacific Palisades in Los Angeles was a brutal reminder of why we need robust early wildfire detection systems. Joining me today is Shahab Bahrami, the co-founder and CTO at SenseNet – a company that provides advanced AI-powered cameras and sensors to protect communities and valuable assets against wildfires.

Shahab is passionate about using interdisciplinary research to bridge the gap between machine learning and optimization, and he begins today’s conversation by detailing his professional background and how it led him to co-found SenseNet. Then, we unpack SenseNet and how its technology works, how it gathers data for its AI models, the challenges of relying on images and other sensor data to train machine learning models, and how SenseNet uses multiple sources to detect or define any one problem. To end, we learn why and how SenseNet uses various AI models in a single sensor, how it measures the overall impact of its tech, where the company plans to be in the next five years, and Shahab’s valuable advice for other leaders of AI-powered startups.     

Key Points:

• Shahab Bahrami walks us through his professional background and how it led to SenseNet. 
• The ins and outs of SenseNet and how its technology works. 
• How machine learning fits into SenseNet’s offerings, and how it gathers the necessary data. 
• The challenges of working with images and other sensor data to train models.  
• How SenseNet integrates information from different sources to zero in on a single anomaly. 
• Understanding how it uses multiple AI models to adapt to variations post-installation. 
• How the system chooses which AI model to apply and when. 
• Shahab describes how his company measures the overall impact of its technology. 
• His advice to other leaders of AI-powered startups, and his five-year vision for SenseNet. 

Quotes:

“We have one of the most comprehensive wildfire detection solutions in the world, and it is proven by multiple, real-world projects.” — Shahab Bahrami

“Having separate AI models is the solution that we are now implementing.” — Shahab Bahrami

“For the sensor’s AI – because it is a semi-supervised AI, it automatically adapts itself to local conditions. It learns gradually what is normal and what is abnormal, and it is a continuous learning. It won’t stop.” — Shahab Bahrami

“AI changes fast. Every day we have a new AI engine, we have a new model, and leaders, I believe, need to stay updated and make sure their teams have the support and also the resources to keep innovating.” — Shahab Bahrami

Links:

Shahab Bahrami 

Shahab Bahrami on LinkedIn

SenseNet

Resources for Computer Vision Teams:

LinkedIn – Connect with Heather.

Computer Vision Insights Newsletter – A biweekly newsletter to help bring the latest machine learning and computer vision research to applications in people and planetary health.

Computer Vision Strategy Session – Not sure how to advance your computer vision project? Get unstuck with a clear set of next steps. Schedule a 1 hour strategy session now to advance your project.

AI is transforming drug discovery by making biological data more accessible and actionable, bridging the gap between complex sequencing data and real-world therapeutic breakthroughs. As Rick Schneider puts it, it's all about leveraging powerful models to “build use cases that matter and bring value.”

In this episode of Impact AI, we hear from the CEO and Co-founder of Helical to find out how bio-foundation models are transforming pharmaceutical research. Rick shares how Helical’s AI platform enables drug discovery by leveraging biological sequencing data without requiring companies to build their own models from scratch. He also reveals the challenges of working with high-dimensional biological data, the power of model specialization for specific therapeutic areas, and the growing role of open-source AI in healthcare innovation.

Whether you're in biotech, AI, or simply curious about the future of medicine, this episode offers invaluable insights into how AI is shaping the next generation of drug discovery. Tune in today!

Key Points:

• Introducing Rick, his engineering background, and Helical’s mission.
• The challenges of leveraging biological foundation models for drug discovery.
• Understanding biological sequencing data and its complexities.
• Key technical challenges: messy datasets, long-range dependencies, and model architecture.
• How Helix, Helical’s mRNA foundation model, competes with industry leaders.
• Three key factors in building biological foundation models: data, compute, and talent
• The shift from narrow AI to general-purpose AI in pharma.
• Benchmarking and evaluating foundation models for different use cases.
• Commercializing Helical’s platform through partnerships with pharma companies.
• Insight into the role of open-source AI in advancing biological research.
• The future of biological foundation models: scaling up for greater impact.
• Rick’s vision for Helical as the backbone of in silico pharma labs.

Quotes:

“The question is, how do I leverage [powerful biological foundation models] and – build use cases that matter and bring value? Helical is building a therapeutic area, an agnostic AI platform that is empowering single-cell RNA and DNA bio foundation models for drug discovery.” — Rick Schneider

“In bio, you can still innovate on the architecture side and not simply [with] the scale of the models. It's not simply by throwing more compute at the models that you get to the very best outcomes.” — Rick Schneider

“Be okay with being different in your approach and accept [that you will] be contrarian to certain things.” — Rick Schneider

Links:

Rick Schneider on LinkedIn

Helical

Helical on GitHub

Helical on Hugging Face

Introducing Helix-mRNA-v0

Helix-mRNA

Helix-mRNA: A Hybrid Foundation Model For Full Sequence mRNA Therapeutics

Resources for Computer Vision Teams:

LinkedIn – Connect with Heather.

Computer Vision Insights Newsletter – A biweekly newsletter to help bring the latest machine learning and computer vision research to applications in people and planetary health.

Computer Vision Strategy Session – Not sure how to advance your computer vision project? Get unstuck with a clear set of next steps. Schedule a 1 hour strategy session now to advance your project.

AI tools for healthcare are becoming more prevalent than ever before, and today, we explore how this could help usher in a future of democratized healthcare for all. I am joined by the neurocritical stroke and epilepsy specialist Junaid Kalia, MD, founder of NeuroCareAI – an innovative enterprise utilizing artificial intelligence solutions to enhance health outcomes and efficiency.

Junaid begins with his professional background and what led him to found NeuroCareAI before explaining what his company does and the products and services it offers. Then, we unpack the primary data sets that inform NeuroCareAI’s work, how to overcome the challenges of combining varied data types, the ethical responsibilities of AI, and how to ensure generalizability is upheld over long periods. To end, we learn why it’s essential to distinguish explainability from reason, how to mitigate the effects of bias on radiology data, how the regulatory process stunts the development of machine learning solutions, and Junaid’s vision of the future of NeuroCareAI. 

Key Points:

• Junaid Kalia walks us through his professional background and why he formed NeuroCareAI.
• The ins and outs of NeuroCareAI and how it incorporates AI into its products and services. 
• Understanding the two main forms of data that govern the company’s work. 
• The challenges of combining different data types and how to overcome them.  
• Unpacking the ethical responsibilities of AI. 
• Generalizability over time: How Junaid and his team ensure their models continue to perform.
• Model accuracy versus explainability, and distinguishing explainability from reason. 
• How bias affects models trained on radiology data and how to mitigate this. 
• The way the regulatory process affects the development of machine learning solutions.
• Junaid Kalia’s advice for other leaders of AI-powered startups. 
• His view on the future of NeuroCareAI. 

Quotes:

“Coming from a very low resource country like Pakistan, I wanted to start a project in which AI can help democratize in countries with low resource settings.” — Junaid Kalia

“Our mission is if you save a life, it is as if you save the life of all mankind.” — Junaid Kalia

“When you are deploying artificial intelligence, you need to make sure that it's deployed ethically. [For] some of these things, we do expect our partner sites – [to] have a real quality assurance system in place before they can deploy my artificial intelligence, because I just want to be ethical.” — Junaid Kalia

“We need to differentiate [and] distinguish between reasoning and explainability. In the vision world, I believe that explainability is nice to have. In the large language models space, reasoning, in my opinion, is a must-have.” — Junaid Kalia

Links:

Junaid Kalia on LinkedIn

Junaid Kalia on X
NeuroCareAI

Resources for Computer Vision Teams:

LinkedIn – Connect with Heather.

Computer Vision Insights Newsletter – A biweekly newsletter to help bring the latest machine learning and computer vision research to applications in people and planetary health.

Computer Vision Strategy Session – Not sure how to advance your computer vision project? Get unstuck with a clear set of next steps. Schedule a 1 hour strategy session now to advance your project.

Radiologists face a growing demand for imaging analysis, yet existing AI tools remain fragmented, each solving only a small part of the workflow. Today, we continue our series on domain-specific foundation models with Paul Hérent, Co-Founder and CEO of Raidium. He joins us to discuss how foundation models could revolutionize radiology by providing a single AI-powered solution for multiple imaging modalities.

Paul shares his journey from radiologist to AI entrepreneur, explaining how his background in cognitive science and medical imaging led him to co-found Raidium. He breaks down the challenges of building a foundation model for radiology, from handling massive datasets to addressing bias and regulatory hurdles, and their approach at Raidium. We also explore Raidium’s vision for the future: its plans to refine multimodal AI, expand its applications beyond radiology, and commercialize its technology to improve patient care worldwide. Tune in to learn how foundation models could shape the future of radiology, enhance patient care, and expand global access to medical imaging!

Key Points:

• Paul Hérent’s background in radiology, cognitive science, and founding Raidium.
• Why existing AI tools in radiology are fragmented and have limited adoption.
• How Raidium’s foundation model unifies multiple radiology tasks.
• Raidium’s multimodal AI: handling diverse imaging types in one system.
• Outlining the vast, diverse data used to train Raidium’s model, including radiology reports.
• The teams, compute power, and infrastructure behind Raidium’s AI development.
• Challenges in data curation, regulatory hurdles, and proving clinical value.
• What makes a good foundation model and the role of self-supervised learning (SSL).
• Insights into how Raidium benchmarks its model using rigorous medical imaging tests.
• The role of diverse data, human oversight, and continuous learning in reducing bias.
• Their current R&D phase and plans for commercialization.
• Key lessons Paul learned about AI startups, from data needs to product-market fit.
• The future of foundation models in radiology and beyond.
• Paul’s advice to AI founders: Build a team with both AI and domain expertise.
• Raidium’s vision: Improving the lives of patients and global healthcare access.

Quotes:

“In practice, there is still little AI adoption because every solution solves only a tiny part of what radiologist do. [For radiologists] it's a wider job. We want, as a radiologist, to have one tool to rule all modalities.” — Paul Hérent

“Data is key. If you have good data, not only to build a data set, but proprietary data, challenging data, rare data in a specific domain. It's very valuable because the architecture is not particularly innovative.” — Paul Hérent

“Build a team with people you trust. Entrepreneurship is not trivial. Be complementary.” — Paul Hérent

“The dream of Raidium is to build something that has a huge impact on a patient's life.” — Paul Hérent

“If we go beyond the rich countries, many, many people have no access to radiology. Two-thirds of countries don’t have access to radiologists. It's a big need. If we can contribute with our approach to more accessible health, we will be very happy.” — Paul Hérent

Links:

Paul Hérent on LinkedIn

Paul Hérent on Google Scholar

Raidium

Resources for Computer Vision Teams:

LinkedIn – Connect with Heather.

Computer Vision Insights Newsletter – A biweekly newsletter to help bring the latest machine learning and computer vision research to applications in people and planetary health.

Computer Vision Strategy Session – Not sure how to advance your computer vision project? Get unstuck with a clear set of next steps. Schedule a 1 hour strategy session now to advance your project.

What if a routine endoscopy could do more than just detect disease by actually predicting treatment outcomes and revolutionizing precision medicine? In this episode of Impact AI, Matt Schwartz, CEO and Co-Founder of endoscopy video management and AI analysis platform Virgo, discusses how AI and machine learning are transforming endoscopy.

Tuning in, you’ll learn how Virgo’s foundation model, EndoDINO, trained on the largest endoscopic video dataset in the world, is unlocking new possibilities in gastroenterology. Matt also shares how automated video capture, AI-powered diagnostics, and predictive analytics are reshaping patient care, with a particular focus on improving treatment for inflammatory bowel disease (IBD). Join us to discover how domain-specific foundation models are redefining healthcare and what this means for the future of precision medicine!

Key Points:

• An introduction to Matt Schwartz and Virgo’s mission.
• The importance of video documentation in endoscopy and its impact on healthcare.
• Machine learning’s role in automating endoscopic video capture and clinical trial recruitment.
• Building the EndoDINO foundation model to unlock endoscopy data for precision medicine.
• Data collection: the process of gathering 130,000+ procedure videos for model training.
• Foundation model development using self-supervised learning and DINOv2.
• Model development challenges, from hyper-parameter tuning to domain-specific adjustments.
• Applying EndoDINO to predict inflammatory bowel disease (IBD) treatment responses.
• Commercializing EndoDINO through licensing to health systems and pharma companies.
• The future of foundation models in endoscopy: expanding applications beyond GI diseases.
• Advice for AI startup founders to prioritize data capture as a foundation for AI success.
• Insight into Virgo’s vision to transform IBD treatment and preventative care.

Quotes:

“There's a massive amount of endoscopic video data being generated across a wide range of endoscopic procedures, and nobody was capturing that data – [Virgo] realized early on that endoscopy data could hold the key to unlocking all sorts of opportunities in precision medicine.” — Matt Schwartz

“With the foundation model paradigm, you can compress a lot of heavy compute needs into a single model and then build different applications on top of the foundation. This is going to have a positive impact on the clinical deployment of foundation models.” — Matt Schwartz

“Our foundation model can turn something like a routine colonoscopy into a precision medicine screening tool for IBD patients.” — Matt Schwartz

“There are a lot of untapped data resources in healthcare. If a founder can build a first product that is the data capture engine, it will set them up for a ton of future success when it comes to AI development.” — Matt Schwartz

Links:

Virgo

Matt Schwartz on LinkedIn

Matt Schwartz on X

EndoML

Introducing EndoDINO: A Breakthrough in Endoscopic AI

Resources for Computer Vision Teams:

LinkedIn – Connect with Heather.

Computer Vision Insights Newsletter – A biweekly newsletter to help bring the latest machine learning and computer vision research to applications in people and planetary health.

Computer Vision Strategy Session – Not sure how to advance your computer vision project? Get unstuck with a clear set of next steps. Schedule a 1 hour strategy session now to advance your project.

Zelda Mariet, Co-Founder and Principal Research Scientist at Bioptimus, joins me to continue our series of conversations on the vast possibilities and diverse applications of foundation models. Today’s discussion focuses on how foundation models are transforming biology. Zelda shares insights into Bioptimus’ work and why it’s so critical in this field. She breaks down the three core components involved in building these models and explains what sets their histopathology model apart from the many others being published today. They also explore the methodology for properly benchmarking the quality and performance of foundation models, Bioptimus’ strategy for commercializing its technology, and much more. To learn more about Bioptimus, their plans beyond pathology, and the impact they hope to make in the next three to five years, tune in now.

Key Points:

• Who is Zelda Mariet and what led her to create Bioptimus. 
• What Bioptimus does and why it’s so important.
• Why their first model announced was for pathology.
• Zelda breaks down three core components that go into building a foundation model.
• How their histopathology foundation model is different from the number of other models published at this point.
• Their methodology behind properly benchmarking how well their foundation model performs.
• Different challenges they’ve encountered on their foundation model journey.
• How they plan to commercialize their technology at Bioptimus. 
• Thoughts on whether open source is part of their long-term strategy for the model, and why.  
• Developing a product roadmap for a foundation model.
• She shares some information regarding their next step, beyond pathology, at Bioptimus.
• The importance of understanding what kind of structure you want to capture in your data.
• Where she sees the impact of Bioptimus in the next three to five years. 

Quotes:

“Working on biological data became a little bit of a fascination of mine because I was so instinctively annoyed at how hard it was to do.” — Zelda Mariet

“Bioptimus is building foundation models for biology. Foundation models are essentially machine learning models that take an extremely long time to train [and] are trained over an incredible amount of data.” — Zelda Mariet

“There are two things that are well-known about foundation models, they’re hungry in terms of data and they’re hungry in terms of compute.” — Zelda Mariet

“On the philosophical side, science is something that progresses as a community, and as much as we have, what I would say is a frankly amazing team at Bioptimus, we don’t have a monopoly on people who understand the problems we’re trying to solve. And having our model be accessible is one way to gain access into the broader community to get insight and to help people who want to use our models, get insight into maybe where we’re not doing as well that we need to improve.” — Zelda Mariet

Links:

Zelda Mariet on LinkedIn

Zelda Mariet

Bioptimus

Resources for Computer Vision Teams:

LinkedIn – Connect with Heather.

Computer Vision Insights Newsletter – A biweekly newsletter to help bring the latest machine learning and computer vision research to applications in people and planetary health.

Computer Vision Strategy Session – Not sure how to advance your computer vision project? Get unstuck with a clear set of next steps. Schedule a 1 hour strategy session now to advance your project.