Machine Learning for MRI Image Reconstruction(rhotter.github.io) |
Machine Learning for MRI Image Reconstruction(rhotter.github.io) |
I actually think we know fairly well how deep learning methods work (and what the shortcomings are), we just have no way to interpret the models it produces. Wouldn't ML techniques to reduce scan times fail at the most critical moments, ie when patients had unusual or unexpected ailments? Using ML in on downsampled MRI images feels akin to having an artist with a lot of familiarity of human anatomy touch up a scan.
That implies that doing something is always better than doing nothing. Unless we're talking things like antibiotics, I'm not sure I'd agree. Medical error is a nontrivial cause of death, increasing that significantly could probably be worse than what you're trying to treat.
As an example, you can run a million simulations on a satellite with different initial conditions to test your new control algorithm. However, you have infinitely many possible initial conditions, and you can't simulate all of them. If you however show that the closed loop system in stable sine sense, it's a more rigorous guarantee.
This proposal basically says using ML we can quarter the number of frequencies we sample and still get good looking scans. But the full resolution is made by inventing details based on statistics from a biased input (most MRIs are taken due to something being wrong).
Again, as with super resolution, ML cannot add detail that isn’t there, anything it creates is simply based on the statistical model it formed from the training set.
[*] For example, by measuring the quality of reconstruction of a known image (e.g. a real or digital phantom) or, in the ideal world, by evaluating clinical outcomes.
Odd remark. FDA approves compressed sensing products (e.g., [1], [2], [3], [4]) precisely because it is possible (and provably so) to quantify and/or characterize such “artifacts” up to substantial equivalence.
[1] https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn...
[2] https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn...
[3] https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn...
[4] https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn...
"510(k)" "deep learning" site:accessdata.fda.gov/cdrh_docs
I do remind you to cross-check what material product is being reviewed.
I don’t want to be part of it, thanks
This can also all be simulated offline without an MRI machine to test on with just access to a few full scans... So could be a good weekend project for someone here on HN, and your technique might even be in use by the time you need an MRI scan and will mean your doctor can get results slightly quicker and you get better healthcare, together with hundreds of millions of other people!
Note, I am biased because I research MRI acquisition and reconstruction methods and I am rolling out trials of fast MRI methods (that use some ML in the reconstruction) to find out how robust the methods actually are in practice.
It looks like you are proposing some kind of mixed approach, not a simple “less data, faster scan, ML to the rescue”. I understand how MRI works but you are surely and obviously much more knowledgeable than me, so I simply wish you luck!
My problem with the article comes from reading that someone telling about using generative models on health data, I don’t think is time for this yet.
In an ideal world, a deep learning algorithm should provide an independent report of potential features of interest to a doctor to let him know if something that he could have missed. However, I hope it stays in the intended role and doesn't make the doctor less careful.
I actually find what you are saying it to be a much better usage of ML in this sector.
Healthcare is an area where we need good and clean data as much as possible, let’s use ML reconstruction somewhere else.
Also I don't think we're talking about special hardware here. Couldn't we just have a software package produced by someone (university, company in a wealthier country) that is used by docs everywhere? Could be done without the need of a dedicated local engineer? Perhaps the WHO could approve certain software packages for universal use in very specific cases.
Just a simple question: to achieve a guarantee that those results are at least equal or better than the ones we have now on our battle tested setups, shouldn’t we use the same sampling we use on a “default” MRI? I mean… using those reconstruction algorithms to try to achieve a better result, without downsampling so that a standard reconstruction can still be performed to be checked against?
That said, there are other great ways to incorporate DL into MRI other than recon. I'm more interested in the use of DL for image segmentation, feature detection, potentially denoising, or other techniques on the image processing side. Those make a lot more sense as "top down" tasks that are well suited for neural networks.
And by the way, tumors can be really small.
I know we can work around subsampling, actually we have always been very good at it since our sampling data back in the day was way smaller than what we refer as subsampled today.
It seems unlikely you wouldn’t appreciate this already, but clinical MRI has not fully sampled in a long time. Between the old and the new - reduced phase resolution (image plane and slice plane) parallel imaging, compressed sense (or sensing), reduced frequency resolution with partial echo techniques, high reconstruction max trim with low acquisition matrix, the list is quite long.
The changes in resulting artefacts as acceleration techniques change (eg high compressed sense values) is a bit of a change to how people work. Very digital looking artefacts are just gross.
Thanks for your work! We need more speed.
Watching the mental gymnastics used to deal with multi band/simultaneous multi slice (or whatever vendors call it) with functional MRI was impressive to me.
Using ML to work out voxel results in such low spacial resolution scans has got to be scary.
If your question is more nuanced to mean “do you really really know how it works, meaning you could work on it tomorrow?” the answer is no, it is not my field.