Hacker News Reader

Comment by ryan93 | Hacker News Reader

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

There is no unadulterated result, you are doing less sampling and relying on ML to fill the gaps. So you either have the ML reconstructed result or a subsampled MRI.

Healthcare is an area where we need good and clean data as much as possible, let’s use ML reconstruction somewhere else.

Interesting. Would love to see an example of a tumor so small a radiologist could see it but that a ML algorithm would smooth out

It is not about big or small, I don’t think you understand how ML work.

And by the way, tumors can be really small.

Out of interest, do you understand how MRI reconstruction works?

If your question is literally “you understand how it works?” the answer is yes, I do.

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.

Not obvious the human chosen function for reconstruction is necessarily better than the ML one. The human function doesn't save all the data either.

A lot of the problem comes from the use of generative neural networks. If the prior is that the reconstructed images should "look" a certain way, then the algorithm will favor that. Some of our colleagues did early work with DL and got scared off of generative models due to finding issues with nonphysical results (read: broken layers of cortex in the brain, completely non-physical anatomy) that these models can generate from the undersampled raw data.

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.

There are definitely ways to work well with subsampled data, see Lester Mackey's recent work.

Could please share a link to the work you are referring to? I would really appreciate it (not ironically, it would be truly appreciated).

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.

http://stanford.edu/~lmackey/papers/thinning-slides.pdf

Thanks!

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).

Reply on news.ycombinator.com