This shows clear ignorance of what radiologists do, it's like a fish telling someone how to improve land transportation.

For some reason CS people fixate on radiology for automation just because it is imaging, but there's a lot of context behind it. There's a reason a radiologist/pathologist is called a doctor's doctor, and no one in the field is worried about automation.

For perspective: Training to be a radiologist is 5+1 years, your family doc trains for 3.

> For some reason CS people fixate on radiology for automation just because it is imaging

Precisely because it's imaging. Training data is abundant, and has the potential to be well labelled. And one of the most active field of AI research is... computer vision. So it's no wonder the low hanging fruit would be medical imaging.

> There's a reason a radiologist/pathologist is called a doctor's doctor, and no one in the field is worried about automation.

Spoken like Garry Kasparov.

> For perspective: Training to be a radiologist is 5+1 years, your family doc trains for 3.

What I love is how the immediate knee jerk reaction isn't to explain why the ML approaches won't work but to immediately retreat behind gatekeeping, in this case the tittle and number of years of schooling.

They are a specialist. A family doctor would order tests that a radiologist would read.

Replacing them with AI would seems like a straightforward process.

What behind the scenes context would make it impossible?

> What behind the scenes context would make it impossible?

The MD context. One first needs to train AI to perform the job of a general MD before you can get into stuff like radiology (that is, their real job, not what some novice CS grads, or not so novice AI experts like Hinton imagine it to be - I.e. not segmenting things into funky shapes or running some funky black box magic that spits out "tumor/not tumor" with no context whatsoever, no. Actually diagnosing real people, where a life is on the line, and if you fuck up enough times, your career).

> The MD context. One first needs to train AI to perform the job of a general MD before you can get into stuff like radiology

That's true. Waymo had to train their AI to perform the job of a firefighter for them to recognize a fire hydrant and a firetruck.

> I.e. not segmenting things into funky shapes or running some funky black box magic that spits out "tumor/not tumor" with no context whatsoever, no.

... But that's the goal right? There's a tumor right there at these coordinates or not.

No, identifying the tumor is only step 1, and is the easiest step. Most non-radiologists can identify whether a tumor is present. The harder part (and the true value of radiologist reads) is everything that comes after finding the tumor: what structures are the tumor invading? Is there spread to lymph nodes? Are there secondary findings that might affect the diagnosis or treatment?

These questions and their relevance changes for every individual case, and while each question by itself may be approachable with AI, getting a detailed and relevant report without meaningless noise from an AI ensemble is a very very hard problem.

Finally an answer that's not just throwaway accounts flagging a submission!

These are all interesting problems where I could see an AI struggling. I guess the next step, once tumor identification becomes a solved problem, will be to train the AI on treatment data and follow-up, ie, this is an example where there was spread to lymph nodes.

Interesting times ahead!

> But that's the goal right?

Part of it.

Human doctors will not only tell you if there's something funky in the image, but will also interpret it in light of a patient's medical history, symptoms, possible diagnoses, etc.

Subtle shading near some structure involved in one of two possible conditions might be very important, but an obvious cyst in an unrelated organ likely means nothing. People are weird close-up!

This is an excellent point. An AI may be able to do a diagnosis to you, but a doc could do diagnosis+post diagnosis, with the foresight of medical history. Theoretically an AI could possibly do this as well, but we're nowhere close.

"Replacing them with AI would seems like a straightforward process."

And yet....

"A machine will never beat a human at Go, the problem space is just too vast."

The years of schooling, of course!

This AMA cabal/Luddite radiologist narrative is ridiculous. Many work on ML actively, we would love to have assist technologies, radiology residents are scared shitless about AI. I would really recommend you speak with more practicing radiologists outside of academia.

Though it’s plausible that ML could eventually take on some screening or diagnostic tasks from highly trained radiologists or pathologists, there is the hurdle of accountability that will need to be tackled. As with self-driving technology, the models will have to be good enough to take on the liability risk at scale.

> the hurdle of accountability

The medical field is notorious for delivering "efforts", not results (unlike engineering). No SLA here.

It depends on the specific situation. Screening mammography for instance carries significant financial (and emotional) risk of missing a call that ends up being cancer.

Risk for the radiologist or the patient?

Patient outcome, financially for the radiologist.

Liability will be delegated away from the hospital and onto the service provider, same way they are with diagnostics on clinical lab equipment. Hospitals love to continue to get paid while shouldering less risk.

They can destroy as many textile mills as they like, but the economic incentives of technology will win the day.

Probably. But it can take a long time.