Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

FastMRI leverages adversarial training to remove image artifacts

ai.facebook.com

Post reply on HN
Print view View original

11–20 of 53 posts

Re: FastMRI leverages adversarial training to remove image artifacts

#11

Post by est31 »

yboris wrote: post #9
est31 wrote: post #8

I'm no fan of this. What if it treats a tumor as an artifact? This reminds me of the xerox scandal about broken OCR that erroneously deduplicated parts of images that had different contents. This module might work well, but the modules by cheap competitors might have such behaviour, and it's extremely hard to test that an implementation is bug free.

What if doctors get both, the untouched originals and the images with the artifacts removed? Seems like it solves the problem you're concerned with?

The xerox scanners had a setting to disable compression as well. People are lazy and don't enable the compressions. Although they are highly skilled, radiologists don't have time to inspect each image, so why bother looking at the raw originals?

The question is rather: does this feature improve diagnoses? Sure, the images look nicer now. But that's not why they are being created. MRI images are made for inspection by trained radiologists who are already filtering out artifacts. So is this tool better at this job, or does it actually worsen the ability of the radiologists to read the images like those xerox scans?

Maybe I'm a bit paranoid, idk. After all, diffusion MRI is already being used for surgical planning even though it has several shortcomings. But in that instance there are probably no good alternatives, while here the alternative is the trained eye of a radiologist.

Re: FastMRI leverages adversarial training to remove image artifacts

#12

Post by ska »

yboris wrote: post #9
est31 wrote: post #8

I'm no fan of this. What if it treats a tumor as an artifact? This reminds me of the xerox scandal about broken OCR that erroneously deduplicated parts of images that had different contents. This module might work well, but the modules by cheap competitors might have such behaviour, and it's extremely hard to test that an implementation is bug free.

What if doctors get both, the untouched originals and the images with the artifacts removed? Seems like it solves the problem you're concerned with?

Not really. This because the idea is to aid with acceleration, in which case the "untouched originals" were never taken, they are dealing with the impact of not gathering all the data in the frequency domain in the first place, and this is a trade off between "here is the image with artifacts" and "here is the result of an artifact correction algorithm".

Re: FastMRI leverages adversarial training to remove image artifacts

#13

Post by ska »

est31 wrote: post #11
yboris wrote: post #9

Earlier quoted context omitted.

What if doctors get both, the untouched originals and the images with the artifacts removed? Seems like it solves the problem you're concerned with?

The xerox scanners had a setting to disable compression as well. People are lazy and don't enable the compressions. Although they are highly skilled, radiologists don't have time to inspect each image, so why bother looking at the raw originals? The question is rather: does this feature improve diagnoses? Sure, the images look nicer now. But that's not why they are being created. MRI images are made for inspection by…

It gets even worse than that sometimes. For example, I remember a study from back when digital xray was getting going, where radiologist were asked to say which processing they liked better (since none of them looked quite like the very non-linear film versions) and scored on performance.

They didn't perform best on the types they liked best. This wasn't a great study in terms of power, but it was interesting.

I've met plenty of rad-oncs and radiologists who are convinced they can "read through the noise" just fine, and want consistent imaging more than artifact reduction. I'm not sure how empirically this has ever been tested.

Re: FastMRI leverages adversarial training to remove image artifacts

#14

Post by ska »

mustachionut wrote: post #4

Even without anything fancy, is there a speed vs clarity parameter(s) when doing an MRI? It seems an easy improvement would be to spend more time getting a clear picture of the specific area of interest, vs now where the whole scan seems to be done at full clarity.

Worse, there is a whole family of parameters.

It's worth thinking of an MRI as a programmable machine for doing certain types of physics experiments.

Sometimes you have an area of interest, sometimes you don't. A lot of the practical (i.e. clinical level, not research work) on specific areas of interest is still in coil design, since body coils often don't do well.

There are all sorts of things that make it difficult (e.g. imaging is in frequency domain, localizing things with gradients can be time consuming in ways not entirely directly related to clarity, etc.)

This sort of thing is addressing issues that come up with acceleration techniques that rely on redundancy in the sampled space to "cheat" and not capture everything. The obvious concern with a ML approach here is that it may replace something interesting with something more normal.

I'd hate to be the one tasked with V&V for this, honestly.

Re: FastMRI leverages adversarial training to remove image artifacts

#15

Post by prostheticvamp »

yboris wrote: post #9
est31 wrote: post #8

I'm no fan of this. What if it treats a tumor as an artifact? This reminds me of the xerox scandal about broken OCR that erroneously deduplicated parts of images that had different contents. This module might work well, but the modules by cheap competitors might have such behaviour, and it's extremely hard to test that an implementation is bug free.

What if doctors get both, the untouched originals and the images with the artifacts removed? Seems like it solves the problem you're concerned with?

So... they have to examine the originals regardless. The new image adds nothing.

Re: FastMRI leverages adversarial training to remove image artifacts

#16

Post by Brakenshire »

est31 wrote: post #8

I'm no fan of this. What if it treats a tumor as an artifact? This reminds me of the xerox scandal about broken OCR that erroneously deduplicated parts of images that had different contents. This module might work well, but the modules by cheap competitors might have such behaviour, and it's extremely hard to test that an implementation is bug free.

Is it extremely difficult? I’d have thought quantifying the error rate for a particular application would be relatively easy.

Re: FastMRI leverages adversarial training to remove image artifacts

#17

Post by lostlogin »

prostheticvamp wrote: post #15
yboris wrote: post #9

Earlier quoted context omitted.

What if doctors get both, the untouched originals and the images with the artifacts removed? Seems like it solves the problem you're concerned with?

So... they have to examine the originals regardless. The new image adds nothing.

It’s even worse than that, it detracts. The whole point is to save time. Running a 10X faster scan and the original scan would make things slower.

Re: FastMRI leverages adversarial training to remove image artifacts

#19

Post by lostlogin »

mustachionut wrote: post #4

Even without anything fancy, is there a speed vs clarity parameter(s) when doing an MRI? It seems an easy improvement would be to spend more time getting a clear picture of the specific area of interest, vs now where the whole scan seems to be done at full clarity.

> It seems an easy improvement would be to spend more time getting a clear picture of the specific area of interest, vs now where the whole scan seems to be done at full clarity.

This is exactly what is done already.

Every method of one can name for reducing scan times is used, and some we can’t name are used too. Speed nearly always comes at the expense of quality, although some acceleration techniques and tech developments have lead to improvements that are pretty much without time penalty. These include signal digitisation at the coil and other methods of getting more for for less (note that this equation doesn’t include money!).

Re: FastMRI leverages adversarial training to remove image artifacts

#20

Post by lostlogin »

viraptor wrote: post #7
throwaway4220 wrote: post #5

Earlier quoted context omitted.

Yes, definitely true for many artifacts! Although due to Nyquist, ghosting artifacts sometimes require you to increase the field of view. What bothers me here is when the artifacts hide underlying pathology, and these algorithms "learn" what a normal knee mri looks like and just show you that. IMO it is a medical liability that must be addressed.

Yeah, I'm worried how any automatic correction which is not completely specified can be used in medical imaging. We sometimes fail to even compress images correctly (remember the scanners changing numbers due to compression?), so trying to automatically remove artefacts sounds dangerous. We already teach doctors about the artefacts and how to handle them. The image doesn't need to be pretty - just functional.

This is mostly handled by MR techs and it is their job to sort this out. Many of the automated tasks are pretty good, and those that aren’t get rejected fast. We don’t tend to get a new sequence/tool/parameter and just run with it, it’s used with the old one until a degree of trust and understanding is established. I’m an MR tech shirking off.
Post reply on HN