Spot on. When I can't interpret a study due to artifact, I say that in my report.

Let's say there's a CTA chest that is limited because the patient breathed while the scan was being acquired, I need to let the ordering clinician know that the study is not diagnostic, and recommend an alternative.

If AI eliminates the artifact by filling in expected but not actually acquired data, I am screwed and the patient is screwed.

As one of the people that look at the images, this is the best comment in the thread.

Lots of AI nonsense permeating radiology right now, which seems to be fairly effective click bait and an easy way to generate hype and headlines.

As a practicing radiologist, I think this is great. We can have AI enabled MRI scanners hallucinating images, read by AI interpreting systems hallucinating reports!

And then we have systems hallucinating patients, data, and entire medical publications! The future is here.