NVIDIA open-sources first GPU-accelerated medical physics simulation framework

NVIDIA today announced the open-source release of its Medical Physics Simulation framework, a GPU-accelerated tool built on NVIDIA Isaac for Healthcare. The framework helps medical robotics developers model anatomy-device interaction, generate hard-to-capture scenarios, test in silico, and train or evaluate robot policies before costly hardware testing. It uses NVIDIA CUDA and is powered by the Warp, Newton, and Cosmos simulation and generative AI technologies. The framework can run up to 8,192 parallel training environments, cutting training from over five hours to under two minutes. Early adopters include CMR Surgical, which contributed clinical data from its Versius system to the Open-H Embodiment dataset; Johnson & Johnson MedTech, which is building digital twins of its MONARCH platform; XCath using it for endovascular training; Inner Logic for synthetic data and regulatory support; and Medtronic Structural Heart for catheter navigation research. The open-source release allows developers to inspect, adapt, and build on the framework with transparency.