- Campbell Arnold
- Aug 5
- 3 min read
“There are few things people fear more than cancer, with the possible exception of neurodegenerative diseases.”
— Robb Wolf
Welcome to RadAccess: Impressions—your quick-read companion to the main RadAccess newsletter. Here we only deliver the essential information. For more details, you can always turn to the full RadAccess newsletter.
In this issue, we cover:
Bringing ARIA-E Detection to the Point of Care
Prospective Study Shows Synthetic STIR Saves Time and Boosts Image Quality
EMVision’s emu Clinical Trial Takes Flight
Low-field Super-Resolution Challenge Enters Validation Phase
If you want to stay up-to-date with the latest in Radiology and AI, then don't forget to subscribe!
Bringing ARIA-E Detection to the Point of Care
As amyloid-targeting Alzheimer’s therapies become more common, monitoring for side effects like ARIA-E (amyloid-related imaging abnormalities with edema) is essential. Repeated high-field MRI scans are costly and logistically challenging, especially for rural or underserved patients. At the 2025 Alzheimer’s Association International Conference, a Washington University study reported 100% sensitivity for ARIA-E detection using Hyperfine’s 64mT portable MRI in a cohort of 31 patients. While early, these results suggest portable MRI could play a key role in expanding access to ARIA-E surveillance as Alzheimer’s treatments scale up—bringing follow-up imaging to where treatments are being delivered.
Prospective Study Shows Synthetic STIR Saves Time and Boosts Image Quality
A prospective study published in European Radiology evaluated SubtleSYNTH, an AI algorithm developed by Subtle Medical (full disclosure: my employer) that generates spinal STIR images from routine T1- and T2-weighted scans. The findings were promising:
~90 seconds saved per exam by forgoing a dedicated STIR scan
Higher image quality, with significantly improved SNR and CNR
Radiologist preference for synthetic images across artifact level, sharpness, and diagnostic confidence
Equivalent diagnostic performance across 14 common spinal pathologies
The results suggest that synthetic MRI may be the next evolution in scan acceleration—boosting speed and quality without compromising accuracy.
EMVision’s emu Clinical Trial Takes Flight
EMVision announced they have begun patient recruitment at five of six clinical sites for its pivotal trial evaluating emu, a portable electromagnetic brain imaging device designed to detect hemorrhage in stroke patients. The trial, which spans major US and Australian hospitals, aims to enroll 300 participants and demonstrate >80% sensitivity and specificity. Unlike CT or MRI, emu uses low-power, non-ionizing radio waves and requires minimal infrastructure—making it well suited for emergency, pre-hospital, or resource-limited environments. If successful, it could pave the way for a new category of portable neuroimaging devices.
Low-field Super-Resolution Challenge Enters Validation Phase
The MICCAI 2025 ULF-EnC Challenge, which focuses on enhancing 64mT brain images, is entering the validation phase. This challenge provides users with a open-access 64mT T1, T2, & FLAIR dataset and paired 3T acquisitions. With registration still open, this is a rare chance to test your super-resolution algorithm on a unique dataset and contribute to the future of accessible neuroimaging. Sign up today!
Resource Highlight: Call for Open Source Low-Field Papers
This is your chance to showcase your low-field MRI work in a special NMR in Biomedicine issue dedicated to advancing open-access, low-field MRI systems! The issue is accepting submissions through March 15th, 2026.
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
Barakos, Jerome, et al. "Detection and management of amyloid-related imaging abnormalities in patients with Alzheimer’s disease treated with anti-amyloid beta therapy." The journal of prevention of Alzheimer's disease 9.2 (2022): 211-220.
Li, Jie, et al. "Diagnostic interchangeability of deep-learning based Synth-STIR images generated from T1 and T2 weighted spine images." European Radiology (2025): 1-11.
Tanenbaum, L. N., et al. "Deep learning–generated synthetic MR imaging STIR spine images are superior in image quality and diagnostically equivalent to conventional stir: a multicenter, multireader trial." American Journal of Neuroradiology 44.8 (2023): 987-993.
Key developments in pivotal trial and continuous innovation study. EMVision ASX Release.
2025 Ultra-Low-Field MRI Image Enhancement Challenge (ULF-EnC) website.
Lucas, Alfredo, et al. "Multisequence 3-T image synthesis from 64-mT low-field-strength MRI using generative adversarial networks in multiple sclerosis." Radiology 315.1 (2025): e233529.
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.
