MathWorks integrates MATLAB with NVIDIA Holoscan for med tech

MathWorks, the developer of mathematical computing software, announced today an integration that enables MATLAB to be utilised within the NVIDIA Holoscan platform. This innovation is set to empower medical device engineers by hastening the development and deployment of streaming data analysis and visualisation applications. These applications can now incorporate existing MATLAB algorithms and functions into GPU-accelerated NVIDIA Holoscan operators for real-time data processing and inference.

"The medical technology industry is being transformed by artificial intelligence," said David Niewolny, Director of Business Development for MedTech at NVIDIA. "By providing a seamless development experience for the growing MATLAB development community within NVIDIA's medical-grade Holoscan platform, NVIDIA and MathWorks are accelerating AI-powered innovation in med tech."

Medical device engineers face the challenge of navigating complex and ever-evolving global regulations while keeping up with rapid technological advancements using cutting-edge materials and electronics. This tension has caused many devices to approach obsolescence shortly after their market release, fuelling the rise of Software as a Medical Device (SaMD). The International Medical Device Regulators Forum defines SaMD as software used for one or more medical purposes without being part of a hardware medical device. To remain competitive post-deployment, SaMD products need the capability to integrate additional software features over time, necessitating the development of a software-defined workflow.

NVIDIA Holoscan is a sensor processing platform that streamlines the development and deployment of AI and high-performance computing applications for real-time insights. The platform supports bringing the latest AI applications into clinical settings by providing full-stack infrastructure for scalable, software-defined streaming data processing at the edge. The MATLAB integration within Holoscan will enable medical device engineers to use existing built-in matrix operations and complex toolbox functions for image and signal processing, filtering, transforms, and deep learning algorithms.

Deploying a Holoscan pipeline with MATLAB involves four steps: creating a MATLAB function, generating accelerated CUDA code using GPU Coder, creating a Holoscan operator wrapper, and rebuilding the Holoscan application with the new MATLAB operator. This sequence enables the creation of a fully functional, software-defined workflow for medical devices. Moreover, integrated verification and validation capabilities in MATLAB and Holoscan permit the developed workflows to comply with industry regulations and standards, including IEC 62304.

"Engineers can now write MATLAB functions and execute them thousands of times faster with NVIDIA Holoscan," said MathWorks Director of Product Marketing, David Rich. "Our collaborations with industry leaders like NVIDIA are set to drive medical device innovation as millions of our customers seek to design, develop, and test their products while complying with industry regulations and standards."