GE HealthCare and NVIDIA reimagine diagnostic imaging with autonomous X-ray and ultrasound solutions
GE HealthCare (GEHC) has announced a significant collaboration with NVIDIA at GTC 2025 to develop autonomous X-ray and ultrasound solutions. The partnership aims to address healthcare challenges including staff shortages and increasing diagnostic demands, with 4.2 billion medical imaging examinations performed annually worldwide.
The collaboration leverages NVIDIA's Isaac for Healthcare platform, built on NVIDIA's computing infrastructure for physical AI, including Omniverse for robotic simulation. GE HealthCare plans to use NVIDIA's Cosmos platform for synthetic data generation and simulation to train autonomous devices before real-world deployment.
The initiative focuses on two key areas: transforming X-ray workflows by automating repetitive tasks and developing autonomous ultrasound systems to address the 90% of sonographers reporting work-related musculoskeletal disorders. This builds on their 16-year relationship and GE HealthCare's track record of 85 FDA AI-enabled device authorizations.
GE HealthCare (GEHC) ha annunciato una collaborazione significativa con NVIDIA al GTC 2025 per sviluppare soluzioni autonome per raggi e ultrasuoni. L'obiettivo della partnership è affrontare le sfide sanitarie, tra cui la carenza di personale e l'aumento della domanda di diagnosi, con 4,2 miliardi di esami di imaging medico eseguiti annualmente in tutto il mondo.
La collaborazione sfrutta la piattaforma Isaac for Healthcare di NVIDIA, costruita sull'infrastruttura di calcolo di NVIDIA per l'IA fisica, incluso Omniverse per la simulazione robotica. GE HealthCare prevede di utilizzare la piattaforma Cosmos di NVIDIA per la generazione di dati sintetici e simulazione al fine di addestrare dispositivi autonomi prima del loro impiego nel mondo reale.
L'iniziativa si concentra su due aree chiave: trasformare i flussi di lavoro dei raggi X automatizzando compiti ripetitivi e sviluppare sistemi autonomi per ultrasuoni per affrontare il 90% dei sonografi che segnalano disturbi muscoloscheletrici legati al lavoro. Questo si basa sulla loro relazione di 16 anni e sul record di GE HealthCare di 85 autorizzazioni di dispositivi abilitati all'IA dalla FDA.
GE HealthCare (GEHC) ha anunciado una colaboración significativa con NVIDIA en GTC 2025 para desarrollar soluciones autónomas de rayos X y ultrasonido. La asociación tiene como objetivo abordar los desafíos de la atención médica, incluidos la escasez de personal y el aumento de la demanda de diagnósticos, con 4.2 mil millones de exámenes de imágenes médicas realizados anualmente en todo el mundo.
La colaboración aprovecha la plataforma Isaac for Healthcare de NVIDIA, construida sobre la infraestructura de computación de NVIDIA para IA física, incluido Omniverse para simulación robótica. GE HealthCare planea utilizar la plataforma Cosmos de NVIDIA para la generación de datos sintéticos y simulación para entrenar dispositivos autónomos antes de su implementación en el mundo real.
La iniciativa se centra en dos áreas clave: transformar los flujos de trabajo de rayos X mediante la automatización de tareas repetitivas y desarrollar sistemas autónomos de ultrasonido para abordar el 90% de los ecografistas que informan trastornos musculoesqueléticos relacionados con el trabajo. Esto se basa en su relación de 16 años y en el historial de GE HealthCare de 85 autorizaciones de dispositivos habilitados para IA por la FDA.
GE 헬스케어 (GEHC)는 GTC 2025에서 NVIDIA와의 중요한 협력을 발표하여 자율 X선 및 초음파 솔루션을 개발합니다. 이 파트너십은 인력 부족 및 증가하는 진단 수요와 같은 의료 문제를 해결하는 것을 목표로 하며, 전 세계적으로 매년 42억 건의 의료 영상 검사가 수행됩니다.
이 협력은 NVIDIA의 물리적 AI를 위한 컴퓨팅 인프라를 기반으로 구축된 Isaac for Healthcare 플랫폼을 활용하며, 로봇 시뮬레이션을 위한 Omniverse도 포함됩니다. GE 헬스케어는 자율 장치를 실제 배포 전에 훈련하기 위해 NVIDIA의 Cosmos 플랫폼을 사용하여 합성 데이터 생성 및 시뮬레이션을 계획하고 있습니다.
이 이니셔티브는 두 가지 주요 영역에 초점을 맞추고 있습니다: 반복 작업을 자동화하여 X선 워크플로를 변환하고, 업무 관련 근골격계 질환을 보고하는 90%의 초음파 검사자를 해결하기 위한 자율 초음파 시스템을 개발하는 것입니다. 이는 16년 간의 관계를 기반으로 하며, GE 헬스케어의 85개 FDA AI 지원 장치 승인 이력을 바탕으로 하고 있습니다.
GE HealthCare (GEHC) a annoncé une collaboration significative avec NVIDIA lors du GTC 2025 pour développer des solutions autonomes de radiographie et d'échographie. Ce partenariat vise à relever les défis de la santé, notamment la pénurie de personnel et l'augmentation des demandes de diagnostic, avec 4,2 milliards d'examens d'imagerie médicale réalisés chaque année dans le monde.
La collaboration tire parti de la plateforme Isaac for Healthcare de NVIDIA, construite sur l'infrastructure de calcul de NVIDIA pour l'IA physique, y compris Omniverse pour la simulation robotique. GE HealthCare prévoit d'utiliser la plateforme Cosmos de NVIDIA pour la génération de données synthétiques et la simulation afin de former des dispositifs autonomes avant leur déploiement dans le monde réel.
L'initiative se concentre sur deux domaines clés : transformer les flux de travail de radiographie en automatisant les tâches répétitives et développer des systèmes autonomes d'échographie pour répondre aux 90 % des échographistes signalant des troubles musculosquelettiques liés au travail. Cela repose sur leur relation de 16 ans et le bilan de GE HealthCare de 85 autorisations de dispositifs habilités par l'IA de la FDA.
GE HealthCare (GEHC) hat eine bedeutende Zusammenarbeit mit NVIDIA auf der GTC 2025 angekündigt, um autonome Röntgen- und Ultraschalllösungen zu entwickeln. Die Partnerschaft zielt darauf ab, Herausforderungen im Gesundheitswesen anzugehen, darunter Personalmangel und steigende diagnostische Anforderungen, mit weltweit jährlich 4,2 Milliarden durchgeführten medizinischen Bildgebungsuntersuchungen.
Die Zusammenarbeit nutzt die Isaac for Healthcare-Plattform von NVIDIA, die auf der Recheninfrastruktur von NVIDIA für physische KI basiert, einschließlich Omniverse für robotische Simulationen. GE HealthCare plant, die Cosmos-Plattform von NVIDIA zur Generierung synthetischer Daten und Simulation zu verwenden, um autonome Geräte vor der Bereitstellung in der realen Welt auszubilden.
Die Initiative konzentriert sich auf zwei Schlüsselbereiche: die Transformation von Röntgenarbeitsabläufen durch Automatisierung repetitiver Aufgaben und die Entwicklung autonomer Ultraschallsysteme, um die 90 % der Sonografen zu unterstützen, die über arbeitsbedingte Muskel-Skelett-Erkrankungen berichten. Dies baut auf ihrer 16-jährigen Beziehung und der Erfolgsbilanz von GE HealthCare mit 85 von der FDA genehmigten KI-unterstützten Geräten auf.
- Leading position in AI healthcare with 85 FDA AI-enabled device authorizations
- Strategic partnership with NVIDIA to develop autonomous imaging solutions
- Addresses significant market opportunity with 4.2 billion annual medical imaging examinations
- Technology could reduce healthcare staff shortages and improve efficiency
- Builds on existing successful 16-year relationship with NVIDIA
- Implementation timeline and costs not specified
- Regulatory approval process could delay market entry
- Success of autonomous systems not yet proven in clinical settings
Insights
GE HealthCare's collaboration with NVIDIA represents a strategic pivot toward autonomous imaging solutions that addresses critical healthcare workforce challenges. With 4.2 billion imaging exams performed annually and 81% of U.S. health systems reporting radiologist shortages, this partnership targets a significant market pain point.
The partnership leverages GE's dominant position in medical imaging AI—having secured 85 FDA authorizations over three years—combined with NVIDIA's computational infrastructure. By focusing initially on X-ray and ultrasound, the two most widely used imaging modalities, GE is targeting high-volume clinical workflows where autonomy could deliver maximum operational impact.
The technical approach is sophisticated, utilizing NVIDIA's Isaac platform for robotics, Omniverse for simulation, and Cosmos for synthetic data generation—enabling virtual testing before physical deployment. This could significantly accelerate development cycles while ensuring safety parameters are met.
For GE HealthCare, this collaboration strengthens their competitive positioning against rivals like Siemens Healthineers and Philips, who are making similar AI investments. The focus on autonomous solutions represents a potential shift from traditional equipment sales toward more software-centric offerings, which could improve margin profiles if successfully commercialized.
While the announcement lacks specifics on timelines and commercialization strategy, the initiative directly addresses documented clinical workflow inefficiencies that cost healthcare systems billions annually.
The GE HealthCare-NVIDIA collaboration targets the most pressing operational challenges facing diagnostic imaging departments today. Autonomous capabilities in X-ray could revolutionize workflow efficiency by eliminating repetitive technologist tasks, potentially addressing the double-digit staffing shortages mentioned in the announcement.
For ultrasound, the clinical impact could be even more significant. With 90% of sonographers reporting work-related musculoskeletal disorders from repetitive scanning motions, autonomous scanning capabilities could substantially reduce occupational injuries while standardizing image acquisition—potentially improving diagnostic consistency.
The technology approach is particularly promising. By utilizing synthetic data generation and virtual training environments, GE can develop systems capable of adapting to diverse clinical scenarios before deployment. Their previous work with the SonoSAMTrack foundation model, which achieved over 90% similarity scores in segmentation accuracy, demonstrates their capability in developing clinically-relevant AI applications.
From a clinical implementation perspective, autonomous systems could free technologists to focus on complex cases and direct patient interaction—addressing both the quantitative staffing shortage and qualitative aspects of care delivery. For radiology departments struggling with volume management, these tools could serve as force multipliers for existing staff.
The progression from assistive AI to autonomous operations represents a significant leap forward in how imaging departments might function in the next decade, potentially improving access to diagnostic services in underserved areas.
- Building on its 125-year legacy of medical imaging innovation and a 16-year relationship with NVIDIA, the two companies team up to advance AI-driven autonomous solutions designed to ease the growing burden on healthcare professionals.
GE HealthCare has been at the forefront of medical technology innovation with a series of “firsts” that date 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.”
Transforming 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
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
“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.”
Forward-Looking Statements
This release contains forward-looking statements. These forward-looking statements might be identified by words, and variations of words, such as “will,” “expect,” “may,” “would,” “could,” “plan,” “believe,” “anticipate,” “intend,” “aim,” “estimate,” “potential,” “position,” and similar expressions. These forward-looking statements may include, but are not limited to, statements about the collaboration, the anticipated outcomes of the collaboration, and any new products or solutions resulting from the collaboration or otherwise. These forward-looking statements involve risks and uncertainties, many of which are beyond the control of the Company. Factors that could cause the Company’s actual results to differ materially from those described in its forward-looking statements include, but are not limited to, the Company’s inability to achieve the anticipated benefits of the collaboration, business or commercial disruptions, and unexpected risks and liabilities impacting the Company. Other factors that may cause such a difference also include those discussed in the "Risk Factors" section of the Company’s Annual Report on Form 10-K filed with the
About GE HealthCare Technologies Inc.
GE HealthCare is a trusted partner and leading global healthcare solutions provider, innovating medical technology, pharmaceutical diagnostics, and integrated, cloud-first AI-enabled solutions, services and data analytics. We aim to make hospitals and health systems more efficient, clinicians more effective, therapies more precise, and patients healthier and happier. Serving patients and providers for more than 125 years, GE HealthCare is advancing personalized, connected and compassionate care, while simplifying the patient’s journey across care pathways. Together, our Imaging, Advanced Visualization Solutions, Patient Care Solutions and Pharmaceutical Diagnostics businesses help improve patient care from screening and diagnosis to therapy and monitoring. We are a
GE HealthCare is proud to be among 2025 Fortune World’s Most Admired Companies™.
Follow us on LinkedIn, X, Facebook, Instagram, and Insights for the latest news, or visit our website https://www.gehealthcare.com for more information.
i Mahesh, Mahadevappa, Ansari, Armin J., and Fred A. Mettler, Jr. “Patient Exposure from Radiologic and Nuclear Medicine Procedures in
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
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
ix Any reported results are preliminary and subject to change.
View source version on businesswire.com: https://www.businesswire.com/news/home/20250318436532/en/
GE HealthCare Media Contact:
Karin Dalsin
Global Communications Director
M +1 612-219-2855
karin.dalsin@gehealthcare.com
Source: GE HealthCare Technologies Inc.