Home NVIDIA and GE Healthcare Partner to Advance Autonomous Diagnostic Imaging with Physics AI

NVIDIA and GE Healthcare Partner to Advance Autonomous Diagnostic Imaging with Physics AI

Mar 20, 2025 19:27 CST Updated 19:27
NVIDIA

Artificial Intelligence Computing Service Provider

GE Healthcare

Digital Solution Provider

图片1.png


San Jose, California, USA — GTC — March 18, 2025, Pacific Time — NVIDIA today announced a collaboration with GE Healthcare to advance autonomous imaging technology innovation, with a focus on developing autonomous X-ray technology and ultrasound applications.

 

To achieve autonomy in systems such as X-ray and ultrasound, medical imaging systems need to understand the physical world and operate autonomously, thereby automating complex workflows such as patient positioning, scanning, and quality inspection.

 

To achieve this goal, leading partner GE Healthcare is adopting the new NVIDIA Isaac™ for HealthCare medical device simulation platform. The platform includes pre-trained models and physics-based sensor, anatomy, and environmental simulations, which can accelerate the R&D process, allowing GE Healthcare to train, test, and validate the capabilities of autonomous imaging systems in a virtual environment before deployment.

 

"Healthcare is one of the most important application areas for AI, with demand for medical services far outstripping supply," said Kimberly Powell, Vice President of Healthcare at NVIDIA. "We are collaborating with industry leader GE Healthcare to empower life-saving medical devices with autonomous capabilities through three computers from Isaac for Healthcare, helping to expand access to healthcare services worldwide."

 

Expanding Access to Imaging Technology Through Physical AI


Ultrasound and X-ray are the most common and widely used diagnostic imaging systems, yet nearly two-thirds of the global population lacks access to such examination services. By adding robotic capabilities to imaging systems, it will help expand the reach of medical services.

 

NVIDIA and GE Healthcare have been collaborating for nearly two decades, jointly developing innovative imaging reconstruction technologies in areas such as CT, MRI, image-guided therapy, and breast imaging.

 

"GE Healthcare is committed to redefining patient care and enhancing the care experience through innovative technologies," said Roland Rott, President and CEO of GE Healthcare's Imaging business. "We look forward to developing autonomous imaging systems powered by NVIDIA's physics-based AI to improve the patient experience and address the growing workload and staffing shortages in the healthcare industry."

 

Isaac for Healthcare: Bridging the Gap Between Simulation and Reality


NVIDIA will also support other customers in building simulation environment use cases through Isaac for Healthcare. The simulation environment allows robotic systems to safely learn skills in a physically accurate virtual setting to address real-world scenarios such as surgery, which are often difficult to replicate.

 

Isaac for Healthcare is a physical AI platform built on NVIDIA's three major robotic computing platforms (NVIDIA DGX™, NVIDIA Omniverse™, and NVIDIA Holoscan). It includes AI models optimized for medical robots, enabling understanding, action, and observation functions through enhanced vision and language processing capabilities. The platform also provides a simulation framework for developers to accurately simulate medical environments and enables real-time robotic decision-making via the edge AI computing platform, NVIDIA Holoscan.

 

Simulation options for medical sensors are often limited. With Isaac for Healthcare, developers can now access physics-based digital twins of medical environments, import custom sensors, instruments, and even anatomical structures to train robots for diverse scenarios. Such virtual environments help bridge the gap between simulation and reality, supporting rapid digital prototyping.

 

Isaac for Healthcare supports multi-scale simulation from microstructures, operating rooms to complete hospital facilities. Through simulation strategy training, robotic systems can learn how to respond in various medical scenarios within the operating room and how to optimally assist doctors in decision-making and providing care services to patients.

 

The Ecosystem of Medical Robots is Expanding Rapidly


Isaac for Healthcare accelerates the development of medical robot solutions by simulating complex medical scenarios, training AI models, and optimizing robotic applications in surgeries, endoscopy, and cardiovascular interventions. Institutions including Moon Surgical, Neptune Medical, and Xcath have already started using this platform ahead of schedule.

 

The platform supports ecological partners in seamlessly integrating their simulation tools, sensors, robotic systems, and medical probes into a dedicated simulation environment. Ecological partners, including Ansys, Franka, ImFusion, Kinova, and Kuka, have already started deploying this functionality in advance.

 

Isaac for Healthcare is now available for early access.

 

>>>>

About NVIDIA


NVIDIA (NASDAQ: NVDA) is a global leader in the field of accelerated computing.