Impressions | 18th Edition

Campbell Arnold
Jul 8
4 min read

“Sustainable use of MRI in remote communities will only be possible if the MRIs can be easily built and maintained autonomously in the community.”

— Sarty et al., Frontiers in Neuroimaging 2025

Welcome to RadAccess: Impressions—your quick-read companion to the main RadAccess newsletter. Like a radiology report's impressions section, we only deliver the essential information to respect your time. For more details, you can always turn to the full RadAccess newsletter.

In this issue, we cover:

MRI at the Edge: From Remote Canada to Rural Ethiopia
A Little Dose Goes a Long Way: 1% Dose Improves PET Synthesis
The Future of MRI Is Sealed: Siemens Launches Helium-Efficient MRI System
Signs of Life in the Radiology AI Market

If you want to stay up-to-date with the latest in Radiology and AI, then don't forget to subscribe!

Subscribe Here

MRI at the Edge: From Remote Canada to Rural Ethiopia

A new Frontiers in Neuroimaging special issue explores how autonomous low-field MRI could overcome cost, power, and staffing barriers to global imaging access.

Key highlights:

🇨🇦 Community-built MRI: Students in northern Canada built a working low-field MRI using aircraft maintenance skills.
🧠 First post-contrast brain tumor scan on a Hyperfine 64mT system proves feasibility of enhanced imaging at the point of care.
🤖 Native noise AI denoising boosts SNR up to 32% with minimal training data.
📊 AI harmonization tools like SynthSR reduce measurement gaps between 64mT and 3T MRI.
🌍 MRI in rural Ethiopia found strong community support when paired with education and engagement.

Bottom line: Bringing MRI to the 5 billion people without access will require innovation at every level—these early studies show it’s possible.

A Little Dose Goes a Long Way

Reducing radiation exposure in PET imaging is a long-standing research goal, with the holy grail being full MRI-to-PET synthesis. A recent study evaluated whether advanced diffusion models could synthesize full-dose PET scans from MRI alone—and how much they would benefit from 1% of standard dose PET data.

Study outline:

The team trained two score-based diffusion models and a transformer-UNet on paired MRI and PET scans from 52 epilepsy patients.
They tested performance using MRI-only inputs and MRI + 1% ultra-low-dose PET.
Evaluations focused on quantitative measures of asymmetry and consistency.

Key findings:

Diffusion models outperformed the Transformer-UNet for MRI-only synthesis, but showed notable inconsistencies between slices.
Adding just 1% of PET signal dramatically improved image consistency and accuracy across all models—effectively eliminating performance differences between models.

Bottom line: This study shows that even 1% of PET signal can go a long way—perhaps the answer isn't always a newer model, but rather better data.

The Future of MRI Is Sealed

Siemens new 1.5T Magnetom Flow.Ace just earned FDA clearance with a sealed design that uses only 0.7L of helium—99% less than conventional scanners. The lighter weight system can also cuts energy use by up to 30% and eliminates the need for a quench pipe, easing installation. Major OEMs have made helium efficient systems a clear priority, with Philips BlueSeal being the first FDA-cleared “helium-free” 1.5T MRI and GE continuing development of their Freelium product line. These sealed-magnet systems mark a major step toward sustainable, low-maintenance, and more accessible MRI.

Bottom line: The age of helium-efficient MRI is here—and it could make high-field imaging easier to deploy around the world.

Signs of Life in the Radiology AI Market?

After a slowdown in health tech funding across 2023 and 2024, signs are emerging that investor confidence is returning to radiology AI in 2025. Recent funding rounds and acquisitions point to renewed momentum in the sector:

Hoppr raised $31.5M Series A to scale AI infrastructure for imaging workflows.
Rad AI extended its Series C to $68M, backed by 4 major US health systems.
ThinkSono secured $6M to expand its AI-guided ultrasound and pursue FDA clearance.
Samsung reportedly plans a $100M investment in Exo, a point-of-care ultrasound company.
Function Health acquired Ezra; Gleamer acquired Pixyl and Caerus Medical earlier this year.

Bottom line: Radiology AI is heating up again—with fresh capital, major acquisitions, and new strategic bets signaling a pivotal year ahead.

Resource Highlight: The Imaging Wire

For this week's resource highlight, I’m recommending you subscribe to The Imaging Wire. It’s one of my favorite ways to stay updated on industry trends. This publication posts twice a week, offering an in-depth exploration of a single topic while also providing a brief overview of other notable developments.

Feedback

We’re eager to hear your thoughts as we continue to refine and improve RadAccess. Is there an article you expected to see but didn’t? Have suggestions for making the newsletter even better? Let us know! Reach out via email, LinkedIn, or X—we’d love to hear from you.

References

Disclaimer: There are no paid sponsors of this content. The opinions expressed are solely those of the newsletter authors, and do not necessarily reflect those of referenced works or companies.