The collaboration will explore agentic co-planning, patient-specific simulation, and real-time computing to personalize cancer treatment and expand access to care.
Siemens Healthineers and NVIDIA are collaborating to develop the next generation of adaptive radiotherapy, combining imaging and oncology expertise with accelerated computing and simulation to streamline clinical workflows and broaden access to cancer care.
Announced at GTC Berlin, the partnership aims to apply agentic and robotic intelligence to radiotherapy planning and delivery, giving oncologists tools to tailor treatment to individual patients in real time.
By 2050, approximately 35 million people worldwide are projected to be diagnosed with cancer each year, according to figures cited by the companies. That growing caseload is placing pressure on care teams to deliver precise, personalized treatment while contending with limited specialist capacity. The companies say greater workflow efficiency can help extend access to care without compromising the precision needed to target tumors and spare healthy tissue.
Agentic Co-Planning and Real-Time Simulation
Under the collaboration, Siemens Healthineers is working with NVIDIA to develop adaptive radiotherapy capabilities built around three pillars: agentic co-planning, patient-specific simulation, and real-time computing.
NVIDIA Nemotron open foundation models are being explored to power agentic co-planning, with the aim of helping oncologists evaluate and refine personalized treatment strategies. Those models could then be paired with NVIDIA CUDA-accelerated dose calculation for rapid patient-specific simulation and the NVIDIA Holoscan platform to connect live sensor data with AI and simulation to support adaptive treatment.
The approach is designed to let clinicians adjust treatment plans based on day-to-day changes in a patient’s anatomy, a longstanding challenge in radiation oncology.
Building on Varian’s Accela Launch
The NVIDIA collaboration extends recent work by Varian, the Siemens Healthineers cancer-care business, which recently launched its Accela adaptive radiotherapy system.
“Adaptive radiotherapy is built on a single principle: treatment should adapt to the patient, not the other way around,” says Arthur Kaindl, head of Varian, in a release. “We’ve made important advances in precision and adaptation—most recently, with the launch of the Accela system. Our collaboration with NVIDIA builds on that progress, exploring how AI and real-time computing could give clinicians greater speed and insight to make informed decisions, adapt treatment with greater confidence, and deliver personalized care to more patients.”
Kimberly Powell, vice president of healthcare at NVIDIA, framed the Siemens Healthineers work as part of a broader push to apply agentic and physical AI across medicine.
“Agentic and physical AI are opening new possibilities across medicine, from designing proteins and powering autonomous laboratories to improving personalized cancer care,” says Powell in a release. “Together with healthcare and life science leaders, we’re accelerating scientific discovery and advancing more precise, accessible care around the world.”
The Siemens Healthineers partnership was among several healthcare collaborations NVIDIA announced at GTC Berlin, which also included an open protein design model developed with the UW Medicine Institute for Protein Design and scientific agent initiatives with Automata, Benchling, Boltz, Danaher, and others.
ID 184397276 © Michaelvi | Dreamstime.com
