The radiologist’s new task is spotting fake scans
the radiologist’s new task is spotting fake scans: fda cleared 92 ai medical devices in q1 alone, three-quarters of them for radiology, while a study in radiology found clinicians caught only 41 percent of deepfake x-rays. the same models that read images can now forge them.
the screening problem just moved one layer down.
Context
RSNA reported on Mar 24, 2026 that neither radiologists nor multimodal LLMs can easily tell AI-generated X-rays from real ones. The study, in Radiology, involved 17 practicing radiologists from six countries; the abstract says only 41 percent spontaneously identified AI-generated images before being told the dataset contained synthetic ones.
Axis Intelligence's dashboard (Sep 2, 2026), a third-party tracker rather than the FDA, lists 92 AI device authorizations in the first quarter of 2026.
The 41 percent figure and the deepfake X-ray finding match the Radiology study. The 92 devices in Q1 comes from a third-party tracker, and the three-quarters-for-radiology share was not confirmed in the excerpt read. The FDA's own list of AI-enabled devices is the primary source to check.
Related work
- RSNA: Deepfake X-rays fool radiologists and AI ↗Mar 24, 2026.
- Radiology: The rise of deepfake medical imaging ↗Mar 24, 2026.
- FDA: List of AI-enabled medical devices ↗Primary list.
Watch next
- Count Q1 2026 authorizations from the FDA's own list.
Sources
- RSNA press release, Mar 24, 2026rsna.org
- Radiology studypubs.rsna.org
- Axis Intelligence, FDA AI device statisticsaxis-intelligence.com
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 2 October 2026 at 03:34 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →