March 18, 2025 — GE HealthCare recently announced a collaboration with NVIDIA expanding the existing relationship between the two companies to focus on innovation in autonomous imaging, beginning with autonomous X-ray technologies and autonomous applications within ultrasound.
GE HealthCare has been at the forefront of medical technology innovation with a series of “firsts” dating back more than a century, starting with the invention of its X-ray tube, followed by several others including the first handheld ultrasound, first 3D obstetric ultrasound, and on-device AI algorithms for pneumothorax triage. X-ray and ultrasound continue to be the most widely used diagnostic imaging systems with 4.2 billion medical imaging examinations performed annually at a global scale.i However, rising demand, driven by an aging population, has led to significant radiology staff shortages, challenging healthcare systems, increasing the burden on healthcare providers, and delaying critical diagnoses.ii
Autonomous X-ray and ultrasound are promising new areas of development, using AI-enabled software to capture and analyze medical images, which could minimize the burden on technicians and radiologists. With NVIDIA as a world leader in accelerated computing and AI and GE HealthCare’s position as a leading global healthcare solutions provider — topping the FDA list of AI-enabled device authorizations for three years in a row with 85 authorizationsiii — this collaboration plan has the potential to help solve some of healthcare’s biggest challenges.
GE HealthCare aims to develop AI-enabled X-ray and ultrasound systems by leveraging the new NVIDIA Isaac for Healthcare platform, built on NVIDIA’s three computers utilized to build physical AI, including NVIDIA Omniverse for robotic simulation workflows. Using the NVIDIA Cosmos platform for synthetic data generation, physics-based sensor simulation, imitation, and reinforcement learning, GE HealthCare plans to train, test, and tune autonomous ultrasound and X-ray devices in a virtual environment before deployment in the physical world.
“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, Imaging at GE HealthCare. “We are excited about our expanded relationship with NVIDIA and the potential of autonomous X-ray and ultrasound as 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.”
X-ray Workflow, Efficiency and Access
NVIDIA and GE HealthCare will initially focus on autonomous development within X-ray systems, specifically the potential utilization of the NVIDIA Isaac for Healthcare and Jetson platforms. GE HealthCare plans to explore Isaac for Healthcare platform and synthetic data generation to simulate various scenarios. This will help to automate repetitive tasks performed by a technologist in the patient exam room. The goal is to enable care teams to focus more of their time on direct patient care and complex cases. The companies will also explore the development of machine-to-patient interactions to autonomously lead the patient through the scan journey.
Advancing Ultrasound Solutions
As ultrasound grows in popularity and complexity, sonographers and radiology technologists face high patient volumes, long hours, and mental and physical stress. Approximately 90% of sonographers report work-related musculoskeletal disorders,iv and among U.S. health systems, 81% report radiology technologist shortages.v
To help address these challenges, GE HealthCare and NVIDIA plan to explore the development of autonomous ultrasound systems to reduce the burden on sonographers and radiologists. For sonographers, autonomous ultrasound systems could streamline workflow and reduce demanding physical strain resulting from repetitive motions. In addition, AI has the potential to take on more of the daily workload though advancements in image understandingvi and robotic navigation.vii
This work will build on a long-standing relationship between the two companies, spanning various areas of GE HealthCare’s business. As an example of previous synergies, GE HealthCare used NVIDIA technology for the development of GE HealthCare’s pioneering research foundation model SonoSAMTrackviii. SonoSAMTrack is a healthcare-specific research foundation model that GE HealthCare trained on approximately 200,000 image-mask pairs, which delineate diverse sets of regions of interest including organs and lesions, and exhibited an average similarity score of over 90%, indicating a high degree of segmentation accuracyix.
“Artificial intelligence and physical AI offer an incredible opportunity to expand global access to GE HealthCare’s advanced imaging systems,” said Kimberly Powell, vice president 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.”
Please go to https://www.gehealthcare.com for more information.
References
i Mahesh, Mahadevappa, Ansari, Armin J., and Fred A. Mettler, Jr. “Patient Exposure from Radiologic and Nuclear Medicine Procedures in the United States and Worldwide: 2009–2018.” Radiology v. 307, no. 1 (2022). Accessed March 5, 2025. https://doi.org/10.1148/radiol.221263
ii The American Society of Radiologic Technologists in 2022 and 2023 estimate that radiographer and sonographer vacancy rates in 2023 almost tripled from the rates in 2021, with 2023 vacancy rates reported at 18.1% for radiography and 16.7% for sonography. Source: American Society of Radiologic Technologists. Radiation Therapy Staffing and Workplace Survey 2022. Accessed March 5, 2025. https://www.asrt.org/docs/default-source/research/staffing-surveys/radiation-therapy-staffing-and-workplace-survey-2022.pdf; American Society of Radiologic Technologists. Radiologic Sciences Workplace and Staffing Survey 2023. Accessed March 5, 2025. https://www.asrt.org/docs/default-source/research/staffing-surveys/radiologic-sciences-workplace-and-staffing-survey-2023.pdf
iii “Artificial Intelligence and Machine Learning (AI/ML)-Enabled Medical Devices,” December 20, 2024, https://www.fda.gov/medical-devices/software-medical-device-samd/artificial-intelligence-and-machine-learning-aiml-enabled-medical-devices
iv Work Related Musculoskeletal Disorders In Sonography, Society Of Diagnostic Medical Sonography, Susan Murphey, https://journals.sagepub.com/doi/full/10.1177/8756479317726767
v “Radiology Staffing Shortages Nation Wide?”, AHEC online, Sept 27, 2021.
vi "Image-based Navigation in Real-World Environments via Multiple Mid-Level Representations." SpringerLink, 2023. Accessed March 5, 2025. https://link.springer.com/article/10.1007/s10514-023-10147-z
vii Marasigan, John Albert L., and Yung-Hao Wong. "Adaptive Robotics: Integrating Robotic Simulation, AI, Image Analysis, and Cloud-Based Digital Twin Simulation for Dynamic Task Completion." Lecture Notes in Computer Science, 2024. Accessed March 5, 2025. https://link.springer.com/chapter/10.1007/978-3-031-60615-1_17
viii This work is in concept phase and may never become a product. Not for sale. Not cleared or approved by the U.S. FDA or any other global regulator for commercial availability.
ix Any reported results are preliminary and subject to change.
July 19, 2024 
