Have any of the methods made radiologists more efficient? If you were to imagine a system that made a radiologist 10x more efficient what would it look like?
Yes, massive increases in efficiency. A radiologist can read anywhere from 50-100 images per day (depending on modality CXR/MR/CT/etc). Voice dictation is ubiquitous and residents are trained from the beginning on how to navigate the templating software.
There are three areas that take a lot of time that radiologist would like to see automated:
Those are the hot three topics for machine learning. Personally, I think that a normal vs. non-normal classifier for CXRs would be more interesting because you could have a completely generated note for normal reads, and radiologists could just quickly look at the image without writing/dictating anything. Of note, hospitals and radiology departments typically lose money on X-ray reads because the reimbursement is $7-$20 (compared to $100+ for MR/CT). So if you could halve the read time, they might become profitable again.
Edit: In terms of 10x, what you'd want is a system that would automatically make the reads (i.e. radiologist report), and a very efficient way for radiologist to verify what is written. It's hard to make a pathologic read, but since roughly 50% of reads are normal, you could start with normal reports.
Before even going to AI/ML type of things, our startup (www.radfox.fi) is doing "simple" fixes to current workflows, first making sure radiology referrals are at the same time informative and decisive (=quality and accuracy of the referral)
And then bringing checklist driven analysis for radiologist.
