© Reuters.
SAN JOSE, Calif. – GE HealthCare (NASDAQ:) has tapped into NVIDIA (NASDAQ:)’s artificial intelligence technology to create SonoSAMTrack, a research model designed to enhance ultrasound image segmentation. This collaboration aims to improve the efficiency and accuracy of medical imaging, which is a critical component of patient care.
SonoSAMTrack, an AI model developed by GE HealthCare, utilizes NVIDIA’s accelerated computing and AI technology stack to segment anatomies, lesions, and other essential areas within ultrasound images.
The model is part of a broader effort by GE HealthCare to integrate foundational AI technologies into medical imaging, aiming to speed up AI application development and ultimately benefit clinicians and patients.
This new model has demonstrated its effectiveness across seven different ultrasound datasets, showcasing its versatility in handling various anatomies and pathologies, including adult hearts, fetal heads, breast lesions, and musculoskeletal issues.
It has been noted for its high performance, outperforming other methods by a significant margin. Moreover, SonoSAMTrack has proven to be both fast and efficient, requiring as few as 2-6 clicks for precise segmentation, which reduces the need for extensive user input.
The traditional approach to incorporating AI into healthcare has often involved retraining models to meet the specific needs of different patient groups and hospital settings, a process that can be costly and complex. However, foundation models like SonoSAMTrack offer a new way forward with the potential for swift adaptation to a variety of medical conditions without extensive training requirements.
David Niewolny, Director of Business Development for Healthcare and Medical at NVIDIA, emphasized the impact of this collaboration on patient care. By combining NVIDIA’s technology with GE HealthCare’s expertise in medical imaging, the partnership is poised to set new standards in healthcare.
It is important to note that the technologies involved in SonoSAMTrack are still under development and are not currently available for sale. They have not been cleared or approved by the U.S. FDA or any other global regulator for commercial availability. The information presented is based on a press release statement and represents ongoing research and development efforts within GE HealthCare.
This article was generated with the support of AI and reviewed by an editor. For more information see our T&C.
Read the full article here
