NVIDIA and Siemens Healthineers have developed a new AI model called NV-Raw2Insights-US that processes raw ultrasound data directly, rather than relying on traditional image reconstruction methods. This approach allows the AI to learn from the nuances of sound wave interactions within each patient, enabling it to generate personalized sound speed maps for adaptive image focusing in real-time. The system utilizes NVIDIA's Holoscan platform and Blackwell-class GPUs for accelerated inference, demonstrating a shift towards end-to-end AI in ultrasound imaging. AI
Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →
IMPACT Enables more personalized and accurate ultrasound imaging by adapting to individual patient physics in real-time.
RANK_REASON This is a research-oriented release of a new AI model for a specific medical imaging application, not a general-purpose model or a product launch for broad consumer/enterprise use.