GE HealthCare and Nvidia partner on AI-driven autonomous imaging

USA – GE HealthCare is deepening its collaboration with Nvidia to develop AI-driven autonomous X-ray and ultrasound technologies.

The partnership, announced at GTC 2025 in San Jose, California, aims to tackle the growing shortage of radiology staff as healthcare systems struggle to meet increasing patient demand.

GE HealthCare will utilize Nvidia’s Isaac for Healthcare platform, which integrates AI, robotics, and digital simulation to create smarter imaging solutions.

This technology will allow GE HealthCare to train and test autonomous medical imaging systems in a virtual environment before deploying them in real-world settings.

The process involves using Nvidia’s Cosmos platform for synthetic data generation and physics-based sensor simulation, helping refine AI models for more accurate and efficient imaging.

“GE HealthCare has a deep history of firsts in medical imaging, and we continue to build upon our legacy of innovation as a healthcare solutions provider,” said Roland Rott, president and CEO of Imaging at GE HealthCare.

“We are excited about our expanded relationship with Nvidia and the potential of autonomous X-ray and ultrasound.

“We are focused on unlocking smarter, more automated solutions that enhance efficiency, standardize imaging, and help ease the burden of increased volumes and double-digit staff shortages on healthcare professionals.”

The partnership’s initial focus is developing an autonomous X-ray system using Nvidia’s Isaac for Healthcare and Jetson platforms.

AI models will be trained to automate routine tasks performed by radiology technologists, allowing medical teams to concentrate on direct patient care and complex cases.

There is also potential for machine-to-patient interactions, where AI systems guide patients through their scans autonomously.

For ultrasound imaging, the goal is to ease the physical strain on sonographers and improve workflow efficiency.

AI-driven automation could assist in capturing high-quality images, reducing repetitive movements that often lead to work-related injuries in medical professionals.

Advances in image understanding and robotic navigation could enable AI to take on a larger share of daily ultrasound procedures.

GE HealthCare and Nvidia have already collaborated on AI-powered imaging solutions in the past.

One notable innovation is SonoSAMTrack, a foundation model trained on around 200,000 image-mask pairs, which enhances medical image analysis and segmentation.

“Artificial intelligence and physical AI offer an incredible opportunity to expand global access to GE HealthCare’s advanced imaging systems,” said Kimberly Powell, VP of healthcare at Nvidia.

“Working together to train and test autonomous solutions, we will accelerate the future of medical imaging capabilities, starting with the two most widely used modalities: X-ray and ultrasound.”