Philips-Nvidia team-up strives to create a ‘self-driving MRI’ machine
A new partnership between Philips and Nvidia aims to allow technologists and other members of the radiology team to see an MR image before acquisition even begins.
The Amsterdam-based imaging giant first announced its partnership with the AI powerhouse in May 2025. Now almost a year later, Philips is discussing what they’re working on and how it could benefit radiology providers.
Generating this AI-driven image preview before acquisition begins will hopefully help to “validate scan plans” while guiding setup decisions, the two contend. Philips and Nvidia said their work is part of a broader effort to move toward autonomous MRI—allowing for greater image consistency across different operators, sites and patient populations.
“For technologists and radiology teams, this seemingly small shift can make a real difference,” Sathish Kumar Balakrishnan, head of global research and development for MRI at Philips, said in a March 17 news article from the company. “MRI is incredibly powerful, but it can also be complex–and complexity is where variability creeps in. A predictive preview aims to reduce uncertainty at the moment it can cost the most: right before the scan begins.”
Experts said this predictive preview is generated using patient context, chosen protocol settings and the AI model’s learned understanding of anatomy. Philips emphasized that the preview “isn’t meant to replace the images the scanner actually acquires.” Rather, it serves as a planning aid to help the MRI operator validate choices, fine-tune positioning and spot issues before committing resources.
The AI tool works by combining Philips’ MR foundation model with Nvidia’s NV-Segment for automated contouring, NV-Generate for predictive previews and NV-Reason for context-aware decision support. Philips said its research is exploring a myriad ways this practice change could aid radiology teams. Benefits could include making positioning more consistent, spotting potential problems earlier, reducing rescans, and improving consistency in image quality.
Philips said it sees a near future where autonomous or “self-driving MRI” potentially becomes reality. With this redesigned care model, a patient arrives and checks in at an automated kiosk. The system retrieves relevant info from the electronic health record to prepare for the scan. And the autonomous MRI machine uses integrated sensors and AI to position the patient, select the appropriate scan and provide simple on-screen guidance.
A preview helps validate the protocol and positioning, and the scan runs with AI continuously monitoring image quality and adjusting to “preserve diagnostic clarity.” Afterward, the MRI system helps the patient exit safely and flags any quality considerations for the radiologist.
“The technology pieces are converging to make our ambition of autonomous MRI more than a slogan,” Balakrishnan added.
Read much more in the news item from Philips here.
Marty Stempniak has covered healthcare since 2012, with his byline appearing in the American Hospital Association's member magazine, Modern Healthcare and McKnight's. Prior to that, he wrote about village government and local business for his hometown newspaper in Oak Park, Illinois. He won a Peter Lisagor and Gold EXCEL awards in 2017 for his coverage of the opioid epidemic.