NVIDIA today announced some major expansions to the NVIDIA Clara™ medical platform, including performance improvements, key partnerships and new capabilities designed to help the medical community better track, test and treat COVID-19.
Combining AI and accelerated computing, the platform can help medical researchers, technology solution providers and hospitals respond faster to the outbreak in new ways:
Breaking Genome Sequencing Speed Records – Free 90-day access to NVIDIA Clara Parabricks® for COVID-19 researchers. The software set a new speed record: DNA sequence analysis of the entire human genome was completed in 20 minutes.
Disease Detection AI Model – An AI model jointly developed with the National Institutes of Health goes live today. The model could help researchers study the severity of COVID-19 from chest CT scans and develop new tools to better study, assess the virus, and detect infection.
NVIDIA Clara Guardian for Smart Hospitals – NVIDIA Clara Guardian™ was released today. The product uses intelligent video analysis and automatic speech recognition technology, enabling a new generation of smart hospitals to monitor patients’ vital signs while avoiding human contact as much as possible.
“The COVID-19 pandemic has spurred further collaboration across the tech, research and healthcare industries to develop new computing solutions that will accelerate understanding of how, scale and severity of the disease,” said Kimberly Powell, vice president of NVIDIA’s healthcare business. There has never been a more urgent need to apply state-of-the-art AI and accelerated computing technologies to all areas of the healthcare industry, and the resulting effects will be widely felt in the post-pandemic and beyond the healthcare industry as a whole. Impact.”
Lightspeed Genome Project
Running NVIDIA Clara Parabricks ON the newly released NVIDIA A100 GPU, DNA sequencing analysis time of the entire genome was reduced to less than 20 minutes, breaking the previous record. NVIDIA also brings a GPU-accelerated RNA-sequencing solution that can output results in under 2 hours, providing researchers with important insights into disease susceptibility, disease progression, and treatment response in patients.
“Time is of the essence for our work,” said Glen Otero, vice president of scientific computing at the Translational Genomics Research Institute. Researchers at the Center for Rare Childhood Disorders are using NVIDIA Clara Parabricks helps each patient determine the most effective treatment for them and provides same-day results.”
Accelerated genomic analysis paves the way for the creation of larger, higher-quality genomic datasets. Abu Dhabi’s Department of Health recently announced a population genome project that is building a genome reference for UAE citizens using Group 42 Artemis supercomputers powered by NVIDIA DGX™ and NVIDIA Clara Parabricks, and plans to Incorporate genomic analysis into comprehensive plans for clinical care improvement.
To make it easier for users to accelerate with NVIDIA Clara Parabricks in the cloud, NVIDIA is working with the DNAnexus Enterprise Genome Cloud Platform to ensure that users are served, programs run and results returned without interruption.
New AI model helps detect COVID-19
NVIDIA is also giving researchers another tool for combating COVID-19 — a set of AI models that can help researchers detect and study infected patients from chest CT scan data.
This set of models is live in the latest version of the Clara imagery in the NGC™ Software Center.
Developed by the NVIDIA Applied Research team in collaboration with clinicians and data scientists at the National Institutes of Health (NIH), this set of models used data from regions with high rates of COVID-19 infection, including China, Italy, Japan, and the United States.
This set of AI models was built using the NVIDIA Clara application framework for medical imaging. NVIDIA Clara includes tools for domain-specific AI training and deployment, which allowed NVIDIA and the National Institutes of Health (NIH) to develop this set of models in less than three weeks.
Building robust AI models is a global priority right now, but sharing data across borders remains a formidable challenge. Currently, NVIDIA and Mass Brigham are leading a new joint COVID-19 multinational research initiative that extends the COVID-19 AI model to X-ray imaging so that it can be done without sharing any patient data and protecting patient privacy Use this set of models locally.
NVIDIA Clara Guardian Helps Frontline Hospitals
The new NVIDIA Clara Guardian application framework provides hospitals with the much-needed ecosystem of AI solutions for public safety and patient monitoring by transforming ordinary sensors into smart sensors. Its main use cases include: automated body temperature screening, protective mask detection, safe social distancing, and remote patient monitoring.
Partners in this ecosystem are using pre-trained models and transfer learning techniques to develop and deploy AI applications that combine vision, speech, and natural language processing. With the NVIDIA EGX™ edge AI platform, solution providers can securely deploy and manage large numbers of devices throughout the hospital environment.
At present, dozens of solution partners such as AnyVision, BriefCam, Care.ai, Chooch AI, Deep Vision, Diycam, IntelliSite, Malong Technology, Ouva, SafelyYou, SAFR, SmartCow, TeiaCare, Tonbo Imaging and Whiteboard Coordinator have been established globally NVIDIA Clara Guardian-based solutions are deployed in more than 50 hospitals and 10,000 patient rooms.