us4us Collaborates with NVIDIA on Real-Time AI for Ultrasound Technology

NVIDIA annual AI technology conference GTC kicks off today, which means we can finally share some exciting news with you: we are currently collaborating with NVIDIA on integrating the NVIDIA Clara AGX developer kit with our us4R-lite™ ultrasound research platform!

From inception, us4R-lite™ has been designed to acquire raw channel data that are then processed on GPUs to enable real-time acquisition and visualization. Raw channel data is a rich source of information that can greatly extend medical diagnostic capabilities traditionally provided by conventional scanners. With great amounts of data come great challenges for processing. And so, we are now integrating our platform with the powerful NVIDIA Clara AGX, an embedded AI computer and software developer framework built for real-time AI and advanced signal processing on high-throughput streaming data.

us4us has long been a member of NVIDIA Inception, an acceleration platform for AI, data science and HPC startups, which provides go-to-market support, expertise and technology. Access to NVIDIA Clara AGX is an additional benefit for members of NVIDIA Inception.

NVIDIA Clara AGX is a groundbreaking tool aimed at a wide range of medical devices, and we are particularly interested in how it can be used in the field of ultrasound. Real-time AI is a hot topic in modern ultrasound imaging and has many promising medical applications, so integrating this technology into our system will be of great use to the ultrasound research and development community. Below, you can get a first look at the results of our preliminary research on applying Deep Convolutional Neural Networks for despeckling and image enhancement on RF data.

Comparison of standard B-mode image and its CNN despeckled version on a tissue-mimicking phantom.

This year, GTC is fully online and free to attend. Register here and make sure you check out Tuesday’s session:

  • Healthcare Keynote | Tuesday, 4/13 at 8am PST | NVIDIA VP of Healthcare, Kimberly Powell, will deliver a special address on the latest advances in AI and announce the us4us and NVIDIA partnership!

Below, you’ll find a small selection of other sessions that you might find interesting. In addition to those, you can join a Medical Imaging focused Dinner with Strangers, a MONAI bootcamp, a Clara Train 4.0 workshop, and other special events.

  • Changing Healthcare Practice, 1 Million Slides at a Time | Razik Yousfi, VP of Engineering,
  • Deploying Robust Medical Imaging AI Applications: Federated Learning and Other Approaches | Daniel Rubin, Professor, Stanford University
  • Deep Learning Using Chest X-rays to Predict Longevity and Cancer Risk | Michael Lu,Director of AI, Cardiovascular Imaging Research Center Massachusetts General Hospital and Harvard Medical School
  • Ensemble Learning Models Provide Expert-Level Prenatal Detection of Complex Heart Birth Defects | Rima Arnaout, Assistant Professor University of California, San Francisco
  • NLP to Extract Data from Cancer Pathology Reports with Human-Level Accuracy | Chris Bouton, CEO and Mike Hugo, CTO, Vyasa Analytics
  • Virtual Surgical Assistants: Inception, Education, and Deployment | Bogdan Mitrea, Staff Software Engineer, Activ Surgical
  • Hospitals of the Future: What Does it Mean to Make a Hospital Smart? | Andrew Gostine, CEO, Artisight and Robin Braun, AE – Alliances, Dell Technologies
◂   BACK


Do you have a problem with our product?
We can help you!