Analyst memo
AI Advances in Ultrasound Imaging
NVIDIA and Siemens Healthineers collaborate to develop NV-Raw2Insights-US, a model that enhances ultrasound imaging by learning from raw sound signals, driving advancements in AI-native diagnostic tools.
Published Apr 28, 2026, 4:09 AMUpdated Apr 28, 2026, 4:09 AM
What happened
NVIDIA and Siemens Healthineers introduced NV-Raw2Insights-US, an AI model that processes raw ultrasound signals to create personalized imaging by estimating the speed of sound through the body.
Why it matters
This technological advancement could redefine ultrasound imaging by offering clearer images through personalized sound-speed mapping, potentially improving diagnostic accuracy.
Who is affected
Clinicians and patients stand to benefit from improved imaging accuracy, while medical device manufacturers may consider integrating AI models like NV-Raw2Insights-US into their systems.
Risks / uncertainty
The technology is investigational and not yet cleared for sale in the U.S., and its future availability remains uncertain.