This comes as a response to the industry-wide challenges of availability, cost and dependencies associated with custom and proprietary hardware components, the company said in a press release.
Click here to follow our WhatsApp channel
The architecture is a scalable platform that supports multiple applications and provides a real-time decision-making tool to the medical fraternity, it said.
Developed from the ground up, the architecture boasts an image processing pipeline for noise reduction, edge and contrast enhancement, texture and color enhancement, and speckle correction. What sets it apart is its inclusion of AI/ML models developed for the detection, identification and classification of polyps — abnormal growths often found during colonoscopies, the company said.
Also read: HPE and NVIDIA collaborate to launch a supercomputing solution in GenAI
The collaboration leverages the NVIDIA Holoscan and NVIDIA IGX Orin platforms, which offer ultra-low latency in data transfer, superior image processing and scalability to support multiple AI-enabled applications. This helps ensure improved visualization for image processing and AI-based decision support, such as for polyp detection and classification.
“The combination of LTTS’ expertise in medical device development and NVIDIA’s full-stack edge AI computing platform delivers unprecedented value to the medical technology industry by accelerating the development of AI-enabled, software-defined medical devices,” Shanker Trivedi, senior vice president of Enterprise Business, NVIDIA.
Amit Chadha, chief executive officer (CEO) and managing director, L&T Technology Services, said: “Our collaboration with NVIDIA helps us push the boundaries of what is possible in medical imaging. The combination of the NVIDIA Holoscan software platform for the edge AI inference and the NVIDIA IGX Orin hardware platform accelerate the development of AI-powered medical imaging solutions by improving image quality and real-time clinical decision-making, making clinicians more efficient and improving patient outcomes.”