Does anyone know how this differs from what Subtle Medical is doing? https://subtlemedical.com/
Similar approach, although Subtle Medical are not using adversarial training, just plain old conv-nets with a non-adversarial loss.
FastMRI leverages adversarial training to remove image artifacts
41–50 of 53 posts
Re: FastMRI leverages adversarial training to remove image artifacts
#42Earlier quoted context omitted.
I think I'd prefer radiologists use both computationally filtered and this. Computational filtering has also advanced over the years.
This _is_ computational filtering. It's not philosophically any different. Every filtering method algorithmically guesses what's important or what's real and what's not.
I agree with your earlier point, but disputing the usage of the term computational filtering here is truly pedantic. Yes, by definition machine learning approaches are a subset of computational approaches, but there are clear differences in terms of (at least) failure modes between machine learning and other techniques. In context, "non-machine-learning based filtering methods" is what was being referred to.
Importantly, the internals of non-machine-learning based approaches are more readily understandable and their output is much more predictable.
Re: FastMRI leverages adversarial training to remove image artifacts
#43Earlier quoted context omitted.
I think I'd prefer radiologists use both computationally filtered and this. Computational filtering has also advanced over the years.
This _is_ computational filtering. It's not philosophically any different. Every filtering method algorithmically guesses what's important or what's real and what's not.
> It's not philosophically any different.
I disagree. I think using techniques that work by attempting to model physical processes that we understand are philosophically different from ML approaches that are learning arbitrary functions.
Re: FastMRI leverages adversarial training to remove image artifacts
#44I just gave a talk on similar work being done in microscopy: https://leapmanlab.github.io/nihai/jan20/ .
The tl;dr (in microscopy but apparently also in mri) is AI imaging can evidently enable new concrete solutions to intractable imaging problems, but the failure modes are really treacherous. The example on slide 39, taken from another excellent review paper, does a great job illustrating the problem. I think these methods will get more trustworthy, but i wouldn't stake my life (or my paper's prestigious research results) on them at the moment.
Re: FastMRI leverages adversarial training to remove image artifacts
#45A lot of people here are rightly concerned about the dangers of falsely marking something as an artifact, but let me present additional data that will hopefully sway you a little bit... If you need an MRI or a CT of an area adjacent to orthopedic implants, you are currently 100% SOL because distortion or reflection artifacts from the metal completely destroy the imagery across a medically significant distance. There…
I remember coming across this in a kaggle challenge:
https://twitter.com/jeremyphoward/status/1184453643287683072...
Re: FastMRI leverages adversarial training to remove image artifacts
#46This is a bad idea, neural nets upscale by "hallucinating" in the details. That's fine for videos for entertainment, not for medical imaging. And this is distinctly different from compressed sensing which uses a high frequency and mathematical basis.
I went to a medical imaging workshop recently, and the consensus was that deep learning approaches will completely replace classical compressed sensing. They are using the same principles of acquiring randomized samples, so it's still compressed sensing, they just produce dramatically better results than classical CS techniques.
> They are using the same principles of acquiring randomized samples, so it's still compressed sensing,
See the second part of my comment. This is only in principle. In practice compressed sensing uses a higher frequency basis and more importantly, this basis is generally not learned, preventing common case bias. Ie a rare condition won't be ignored because it isn't statistically common enough for the NN model to learn.
Re: FastMRI leverages adversarial training to remove image artifacts
#47Earlier quoted context omitted.
This _is_ computational filtering. It's not philosophically any different. Every filtering method algorithmically guesses what's important or what's real and what's not.
> It's not philosophically any different. I disagree. I think using techniques that work by attempting to model physical processes that we understand are philosophically different from ML approaches that are learning arbitrary functions.
I agree there is a gulf of difference between modelling based on physics and mere empirical modelling fitting functions to data
Re: FastMRI leverages adversarial training to remove image artifacts
#48Please don’t make sweeping, generalizing opinions on the implications of the work. It’s a subjective problem to solve, so if are not a radiologist who has first-hand experience with this issue, stop. Here are the results from the paper: The radiologists ranked our adversarial approach as better than the standard and dithering approaches with an aver- age rank of 2.83 out of a possible 3. This result is statisti- call…
Intuitively I don't see that there's much value in asking radiologists to subjectively "rank" the images. Surely the thing that needs to be tested here is patient outcomes?
That needs to be tested eventually - there's a reason we go from petridish testing to animal testing to human testing with medicine, it stands to reason that medical tools should follow similar stages.
Re: FastMRI leverages adversarial training to remove image artifacts
#49A lot of people here are rightly concerned about the dangers of falsely marking something as an artifact, but let me present additional data that will hopefully sway you a little bit... If you need an MRI or a CT of an area adjacent to orthopedic implants, you are currently 100% SOL because distortion or reflection artifacts from the metal completely destroy the imagery across a medically significant distance. There…
Computational filtering techniques are difficult for a good reason. In the case of CT, high density objects like metal implants produce beam hardening by preventing the low energy photons from reaching the detector. With adversarial training, you can train a network to recognize and remove the artifacts, but you won't be able to reconstruct structures for which there is no physical measurement.
There were similar discussions a few year ago when deep learning was not commonly used yet and compressed sensing was the hot topic of the moment. It can reconstruct MRI or CT images from limited data (and thus allows for quick MR scans or low dose CT) but you have to satisfy a sparsity condition that is seldom granted. There are a few use cases (like MR angiography) where the data is sparse enough and compressed sensing works great.
For deep learning techniques, you need to be very cautious about which structures your network may remove or introduce.
Re: FastMRI leverages adversarial training to remove image artifacts
#50A physician's $0.02 - The clinical relevance of FB's work is clearly stated in the blog post: "While state-of-the-art facilities today use 3 Tesla MRI machines, scanners with lower-strength magnets (1.5 Tesla, for example) are still commonly used around the world." Considering that a 1.5T MRI machine costs about $1M less than a comparable 3T model (+/- the cost of warranty, support, and installation), FB's work in th…
> 2) healthcare providers in developing countries will effectively get a low-cost "upgrade" to their existing equipment
I am VERY pessimistic about this. I don't know how well you know medical equipment providers but this will never be sold as a low-cost "upgrade" to existing machines. It will be sold with new equipment only and with a hefty surcharge as an option enabling higher patient throughput.
There is no real money in upgrades. Most equipment lasts only 8-10 years anyway.