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

Whole-body magnetic resonance imaging at 0.05 Tesla

science.org

Post reply on HN
Print view View original

21–30 of 159 posts

Re: Whole-body magnetic resonance imaging at 0.05 Tesla

#21

Post by deepsun »

alwa wrote: post #12

I can’t access the full paper, but from the abstract, is it accurate that they’re using ML techniques to synthesize higher-quality and higher-resolution imagery, and that’s the basis for their claim that it’s comparable to the output of a conventional MRI scan? Do clinicians really prefer that the computer make normative guesses to “clean up” the scan, versus working with the imagery reflecting the actual measurement…

My understanding as well. That... will bias towards training data, and will miss more anomalies. And anomalies is the point of scanning.

Re: Whole-body magnetic resonance imaging at 0.05 Tesla

#23

Post by cornholio »

> We conducted imaging on healthy volunteers, capturing brain, spine, abdomen, lung, musculoskeletal, and cardiac images. Deep learning signal prediction effectively eliminated EMI signals, enabling clear imaging without shielding.

So essentially, the neural net was trained to what a healthy MRI looks like and would, when exposed to abnormal structures, correct them away as EMI noise leading to wrong diagnostics?

I won't be very dismissive of this approach and probably deep learning has a strong role to play in improving medical imaging. But this paper is far, far from sufficient to prove it. At a minimum, it would require mixed healthy / abnormal patients with particularities that don't exist in the training set, and each diagnostic reconfirmed later on a high resolution machine. You need to actually prove the algorithm does not distort the data, because an MRI that hallucinates a healthy patient is much more dangerous than no MRI at all.

Re: Whole-body magnetic resonance imaging at 0.05 Tesla

#24

Post by eig »

A few months ago there were articles going around about how Samsung galaxy phones were upscaling images of the Moon using AI [0]. Essentially, the model was artificially adding landmarks and details based on its training set when the real image quality was too poor to make out details.

Needless to say, AI upscaling as described in this article would be a nightmare for radiologists. 90% of radiology is confirming the absence of disease when image quality is high, and asking for complementary studies when image quality is low. With AI enhanced images that look "normal", how can the radiologist ever say "I can confirm there is no brain bleed" when the computer might be incorrectly adding "normal" details when compensating for poor image quality?

[0] - https://news.ycombinator.com/item?id=35136167

Re: Whole-body magnetic resonance imaging at 0.05 Tesla

#26

Post by londons_explore »

brnt wrote: post #8

Medical imaging devices and medical devices in general are a racket. There are only a few companies and they are legal and lobbying departments first and foremost. This isn't the first time radical and radically cheaper prototypes have been proposed, but the unsolved bit it actually convincing anyone to buy. A colleague had a device and a veteran adviced him to 10x the price.

> the unsolved bit it actually convincing anyone to buy.

Surely a lot of small hospitals would jump at the chance at a small cheap MRI? I don't understand how the incumbents have much legal leverage here...

Re: Whole-body magnetic resonance imaging at 0.05 Tesla

#28

Post by eig »

alwa wrote: post #12

I can’t access the full paper, but from the abstract, is it accurate that they’re using ML techniques to synthesize higher-quality and higher-resolution imagery, and that’s the basis for their claim that it’s comparable to the output of a conventional MRI scan? Do clinicians really prefer that the computer make normative guesses to “clean up” the scan, versus working with the imagery reflecting the actual measurement…

I can say that most radiologists would not want a computer trying to fix poor scan data. If the underlying data is bad, they would have recommend an orthogonal imaging abnormality. "I don't know" is a possible response radiologists can give. Trying to add training data to "clean up" an image would bias the read towards "normal".

Re: Whole-body magnetic resonance imaging at 0.05 Tesla

#29

Post by atoav »

eig wrote: post #24

A few months ago there were articles going around about how Samsung galaxy phones were upscaling images of the Moon using AI [0]. Essentially, the model was artificially adding landmarks and details based on its training set when the real image quality was too poor to make out details. Needless to say, AI upscaling as described in this article would be a nightmare for radiologists. 90% of radiology is confirming the…

This is one aspect about machine learning models I keep discussing with non-technical passengers of the AI-hype-train: They are (in their current form) unsitable for applications where correctness is absolutely critical.

Re: Whole-body magnetic resonance imaging at 0.05 Tesla

#30

Post by BobbyTables2 »

eig wrote: post #24

A few months ago there were articles going around about how Samsung galaxy phones were upscaling images of the Moon using AI [0]. Essentially, the model was artificially adding landmarks and details based on its training set when the real image quality was too poor to make out details. Needless to say, AI upscaling as described in this article would be a nightmare for radiologists. 90% of radiology is confirming the…

The Samsung phone wasn’t a technological advancement, it was sheer fraud.

A camera is supposed to take pictures of what it sees.

Imagine going to a restaurant, ordering French onion soup, and getting a bowl of brown food coloring in water.

Post reply on HN