FastMRI leverages adversarial training to remove image artifacts
1–10 of 53 posts
Re: FastMRI leverages adversarial training to remove image artifacts
#2Could be useful for SAR and SAS imagery as well perhaps.
Re: FastMRI leverages adversarial training to remove image artifacts
#3Isn't this basically SRGAN?
Edit: sorry I guess since there's an explicit rotation module it's closer to SRGAN+deformable convolutions.
Re: FastMRI leverages adversarial training to remove image artifacts
#4Even 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.
Re: FastMRI leverages adversarial training to remove image artifacts
#5Even 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.
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.
Re: FastMRI leverages adversarial training to remove image artifacts
#6Even 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.
Yes, although currently scans are typically done at "full clarity" following a "standard" clinical protocol that is the same for everyone. It's generally thought that in the future the field will move towards using scans are are more tailored to each particular patient.
Re: FastMRI leverages adversarial training to remove image artifacts
#7Even 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.
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.
Re: FastMRI leverages adversarial training to remove image artifacts
#8I'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.
Re: FastMRI leverages adversarial training to remove image artifacts
#9I'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?
Re: FastMRI leverages adversarial training to remove image artifacts
#10Isn't this basically SRGAN? Edit: sorry I guess since there's an explicit rotation module it's closer to SRGAN+deformable convolutions.
The adversary in this work never sees non-reconstructed images, so it looks like it's completely unrelated to SRGAN.