DELTACAST video solutions adds NVIDIA Jetson platform and Clara Holoscan SDK support for AI medical devices
DELTACAST with NVIDIA Jetson™ edge AI platform and Clara™ Holoscan SDK integration gives medical device developers access to DELTACAST’s full range of video IO for real-time, low-latency, 4K/8K video capture and AI-powered graphic overlay capabilities.
DELTACAST today announces support for the NVIDIA Jetson™ and Clara™ Holoscan platforms as of the DELTACAST VideoMaster SDK 6.20 release. DELTACAST is an NVIDIA partner for real-time video capture, transport and processing. For more than 30 years, DELTACAST has been delivering video solutions for developers at major broadcast, ProAV, medical and industrial device manufacturers.
“With the development of AI for surgical video applications, providing medical device OEMs with robust, ultra-low latency, 4K or 8K augmented reality graphics capabilities is today a key requirement,” explains Gerald Olivier, Head of Product Marketing at DELTACAST.
New advances in AI computation make it possible for medical devices to automatically detect, measure, predict, simulate, map, and guide clinical care teams. NVIDIA Clara Holoscan is an AI computing platform for medical devices. It combines hardware systems for low-latency sensor and network connectivity, optimized libraries for data processing and AI, and core microservices to run streaming, imaging and other applications, from embedded to edge to cloud.
The new integration provides software driver support for DELTACAST I/O cards to be inserted into the PCI Express slots in the Clara Holoscan developer kits. To ensure low latency and high throughput, it provides a direct path for data exchange between the GPU and DELTACAST I/O card using remote direct memory access (RDMA).
In addition, DELTACAST adds a unique passive 12G-SDI bypass relay to ensure continuous video flow from the camera to the operating room monitors in case of medical device power outage. “AI-powered applications in operating rooms must adhere to very strict safety regulations — for example, surgical video must remain available to the surgeon even if the video processor loses power,” says Yaniv Lazimy, Technical Product Manager for Medical Devices at NVIDIA. “DELTACAST’s passive bypass option makes this possible, going above and beyond existing features and greatly reducing the need for a separate feed to a redundant backup monitor — all of which offers a great improvement for AI-powered surgical video solutions.”
Medtech companies around the world are adopting NVIDIA Clara Holoscan for AI solutions in medical imaging, surgery and electron microscopy. Clara Holoscan accelerates the development of these new medical instruments by providing a universal platform that can deliver high-bandwidth signal processing and accelerated computing for reconstruction, AI processing and advanced 3D visualization.
NVIDIA Jetson is the leading AI-at-the-edge computing platform with over one million developers. With pre-trained AI models, developer SDKs and support for cloud-native technologies across the full Jetson lineup, manufacturers of intelligent machines and AI developers can build and deploy high-quality, software-defined features on embedded and edge devices targeting robotics, healthcare, industrial applications, and more.
DELTACAST is proud to work with NVIDIA to create technology that, ultimately, will save lives and improve patient outcomes.
Medical devices manufacturers interested to benefit from DELTACAST video I/O can contact the company at firstname.lastname@example.org .