AI Shouldn't Replace Physicists - It Should Give Them Time Back
The article discusses the role of AI in the healthcare industry, emphasizing that AI should enhance the efficiency of physicists rather than replace them. TheraPanacea, founded by mathematician Nico Asperagus, focuses on developing AI platforms to improve efficiency and standardization in healthcare. The aim is for AI to handle routine tasks, allowing professionals more time for complex problem-solving.
This story was produced through MarketScale. See how Healthcare teams put it to work with Executive Thought Leadership.
Key takeaways
AI should be used to enhance the efficiency of physicists rather than replace them.
TheraPanacea develops AI platforms for improving efficiency and standardization in healthcare.
AI platforms aim to manage routine tasks, allowing professionals more time for complex analysis.
TheraPanacea was founded in 2017 as a spin-off from the mathematics and computer science department at Paris Leclerc University. Led by CEO and founder Nico Asperagus, a mathematician by training, the company has built an AI platform designed to address efficiency, quality, and standardization across the full radiation oncology workflow, from CT simulation and MR simulation through treatment delivery.
The company's academic origins shape how it operates. TheraPanacea collaborates with institutions including Gustav Roussy, Penn Medicine, and Cleveland Clinic, not only to source training data for its models but to ensure those models are clinically validated before reaching care teams. The organization employs a significant number of scientists and PhD researchers alongside engineers, and it participates actively in academic publishing. That dual identity, part technology company, part research institution, is central to how TheraPanacea positions itself in the market.
Complementing the clinical workflow, not replacing it
A recurring theme in conversations with the TheraPanacea team at the Vancouver event was the importance of fitting AI into existing clinical pathways rather than disrupting them. The goal, as described by company representatives, is to handle more standardized treatment types through automation so that dosimetry and physics staff can redirect their attention to complex or emergent cases. The platform covers auto-contouring and automated planning, areas where incremental time savings can compound into meaningful capacity gains across a busy department.
We don't wanna necessarily replace a traditional pathway. What we wanna do is complement the traditional pathway for those types of treatments that maybe are more standard, so that your dosimetry teams and your physics team can spend more time on those complex or emergent cases. — Steve Andersen, Chief Growth Officer, Head of US, TheraPanacea
To illustrate how far the field has already traveled, one team member pointed to the evolution of treatment planning over roughly two decades. Manual contouring once consumed enormous amounts of clinical time. The introduction of atlas-based libraries changed that baseline, and AI-driven auto-contouring and auto-planning represent the next step in that progression. The argument is that the profession has already absorbed major workflow shifts and is technically and culturally prepared to absorb another.
Validation and staff readiness as prerequisites for adoption
Clinicians at the event were candid about how AI products actually move through their institutions. Adoption is not driven by individual enthusiasm for a given tool. It depends on a structured evaluation process that includes mock testing before any live rollout. As one clinician described it, once a product passes through all of the institutional filters and testing phases, the decision to use it follows naturally.
I just trust my leadership (at Texas Oncology). They evaluate a lot of products. So once that is going through all of the filters, the testing, we do mock testing, and then they roll it out. It's good to go. — Dr. Dana Rosencranz, Chief Medical Physicist, Texas Oncology
That perspective underscores a broader truth about AI adoption in radiation oncology: the technology itself is only part of the equation. Proper education, staff training, and rigorous clinical validation are the conditions that determine whether a tool gets used at scale. For TheraPanacea, the emphasis on academic collaboration and published research is not incidental. It is the mechanism through which the company builds the evidence base that institutions require before committing to a new platform.
About the author
