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

Machine Learning for MRI Image Reconstruction

rhotter.github.io

Post reply on HN
Print view View original

41–49 of 49 posts

Re: Machine Learning for MRI Image Reconstruction

#41

Post by londons_explore »

Could this be taken one step further... Use the ML in-the-loop during an MRI scan, to look at the data collected so far, then decide which frequency should be measured next to most improve the quality of the result?

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!

Re: Machine Learning for MRI Image Reconstruction

#42

Post by 01acheru »

tangoed wrote: post #40
01acheru wrote: post #12

Can’t wait to do an MRI and hear the doc say “You’re all set, good to go!”, only to discover that I actually had a tumor but that really clever ML algorithm thought that it was noise and should’ve been smoothed out… I don’t want to be part of it, thanks

You'll be surprised how many well-known doctors miss a ton of non-obvious anomalies in scan results. There's no way a doctor would have seen all prior records of confirmed diagnosis and their corresponding scans. 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 stay…

I totally agree with you on this one, but it is not the topic at hand. The article is not about using ML for feature detection, but on enhancing subsampled data.

I actually find what you are saying it to be a much better usage of ML in this sector.

Re: Machine Learning for MRI Image Reconstruction

#43

Post by bick_nyers »

tangoed wrote: post #39
tqi wrote: post #3

> This makes it hard to predict when and how deep learning methods will fail (there are no theoretical guarantees that deep learning will work). 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 unexpe…

I'd argue that knowing fairly well and theoretical guarantees are significantly different. 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 guara…

Agreed. I work in medical imaging, and people in the industry are very weary of existing technology that does have theoretical guarantees. Upscaling via bicubic/lancoz, or lossy compression (even if it has guaranteed 0.99 SSIM or NCC). Then they go ahead and do reads on 512x512 pixel CT scans. Even with a theoretical guarantee on bounded error ranges, you still have the cultural perception problem to deal with. Only if the improvements from a feature perspective are an order of magnitude better will it see any adoption imo.

Re: Machine Learning for MRI Image Reconstruction

#44

Post by bick_nyers »

vitorsr wrote: post #33

> Though compressed sensing can improve the image quality relative to a vanilla inverse Fourier transform, it still suffers from artifacts. 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... […

This is actually quite interesting and currently relevant to me, thanks for sharing

Re: Machine Learning for MRI Image Reconstruction

#45

Post by lostlogin »

notarandomer wrote: post #38
01acheru wrote: post #31

Earlier quoted context omitted.

My opinion is pretty much worthless but I think this is a much more sensible approach, using the strengths of ML but putting constraints on the outputs. 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…

"Default MRI" (i.e. fully sampled) should definitely be acquired when possible when testing this out to compare to gold standard. But the benefit of using ML methods in the fully sampled case would be minimal (maybe some denoising), whereas they have a much larger effect when acquiring highly undersampled data that traditional reconstruction methods fail at. It's also not always possible to get fully sampled referenc…

> "Default MRI" (i.e. fully sampled) should definitely be acquired when possible when testing

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.

Re: Machine Learning for MRI Image Reconstruction

#46

Post by lostlogin »

ryan93 wrote: post #13
01acheru wrote: post #12

Can’t wait to do an MRI and hear the doc say “You’re all set, good to go!”, only to discover that I actually had a tumor but that really clever ML algorithm thought that it was noise and should’ve been smoothed out… I don’t want to be part of it, thanks

Why would the ML algorithm necessarily change the scan. The radiologist could still look at the unadulterated MRI.

MRI is completely adulterated at every stage. Algorithms and filters make the final result palatable. The raw data is a k-space data file. It’s not really human readable (though you can spot noise spikes etc).

Re: Machine Learning for MRI Image Reconstruction

#47

Post by notarandomer »

lostlogin wrote: post #45
notarandomer wrote: post #38

Earlier quoted context omitted.

"Default MRI" (i.e. fully sampled) should definitely be acquired when possible when testing this out to compare to gold standard. But the benefit of using ML methods in the fully sampled case would be minimal (maybe some denoising), whereas they have a much larger effect when acquiring highly undersampled data that traditional reconstruction methods fail at. It's also not always possible to get fully sampled referenc…

> "Default MRI" (i.e. fully sampled) should definitely be acquired when possible when testing 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 ma…

Thanks for the comment! You're right, I was oversimplifying saying that default MRI would be fully sampled. My main point still stands, you can't just chuck ML onto current protocols to do a direct comparison with ML and more conventional reconstruction methods to give clinicians access to both and expect an improvement (beyond potentially denoising) because the conventional scans are already very good at what they do. Where ML can help is in cases where we can't produce conventional scans (e.g. with very short scan times or high temporal resolution).

Re: Machine Learning for MRI Image Reconstruction

#48

Post by lostlogin »

notarandomer wrote: post #47
lostlogin wrote: post #45

Earlier quoted context omitted.

> "Default MRI" (i.e. fully sampled) should definitely be acquired when possible when testing 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 ma…

Thanks for the comment! You're right, I was oversimplifying saying that default MRI would be fully sampled. My main point still stands, you can't just chuck ML onto current protocols to do a direct comparison with ML and more conventional reconstruction methods to give clinicians access to both and expect an improvement (beyond potentially denoising) because the conventional scans are already very good at what they d…

Those striving for shorter scan times (eg functional) go to such massive lengths that it blew my mind when I encountered it on a research magnet. Every millisecond counted.

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.

Re: Machine Learning for MRI Image Reconstruction

#49

Post by vitorsr »

bick_nyers wrote: post #44
vitorsr wrote: post #33

> Though compressed sensing can improve the image quality relative to a vanilla inverse Fourier transform, it still suffers from artifacts. 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... […

This is actually quite interesting and currently relevant to me, thanks for sharing

The following query might also interest you then:

    "510(k)" "deep learning" site:accessdata.fda.gov/cdrh_docs
Or alternatively replace "deep learning" by either another distinctive theory/methodology employed or trade/device name.

I do remind you to cross-check what material product is being reviewed.

Post reply on HN