Dutch medical technology firm Philips has entered a collaboration with NVIDIA to advance magnetic resonance (MR) imaging using artificial intelligence (AI).
The partnership aims to leverage AI to improve scan times, workflow efficiency, and image quality, enabling healthcare providers to deliver faster and more accurate diagnoses.
Under the collaboration, Philips and NVIDIA will develop a foundational model for MR imaging, utilising NVIDIA’s advanced AI computing platform.
The foundational model will be built on a large deep-learning neural network and will be trained on extensive datasets.
It will be designed to significantly enhance MR image quality, accelerate scan times, and improve diagnostic workflow and accuracy across various clinical applications.
Philips MRI business leader Ioannis Panagiotelis said: “Our AI-powered MRI solutions are already enabling healthcare providers to deliver better care to more people.
“By partnering with NVIDIA to build an MR Foundational Model, we’re pioneering a new frontier for medical imaging, one that has the potential to transform the role of MR in the diagnosis and treatment of a wide range of diseases.
“The benefits for patients and healthcare providers could be enormous.”
Key features of the foundational model include zero-click planning of scans across different anatomies, which promises to speed up workflows and increase throughput.
Interactive image enhancement capabilities, such as denoising, super-resolution, and sharpening, will enable more precise diagnoses.
Radiologists will benefit from the ability to preview images and adjust quality and speed parameters before scans, streamlining the diagnostic process.
The collaboration will also focus on seamless integration into existing MR workflows.
Using NVIDIA’s VISTA-3D, Philips plans to build an interactive foundation model for 3D medical imaging, and MAISI, a 3D model that generates high-quality synthetic images.
The advanced technologies aim to create a domain-specific solution customised to the unique challenges of MR imaging.
Last year, Philips introduced its next-generation AI cardiovascular ultrasound platform to speed up cardiac ultrasound analysis and reduce the burden on echocardiography labs.
The new AI applications are trained on anonymous patient data sets from real-life clinical environments and were approved by the US Food and Drug Administration (FDA).
