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

A low-cost and shielding-free ultra-low-field brain MRI scanner

nature.com

Post reply on HN
Print view View original

81–90 of 151 posts

Re: A low-cost and shielding-free ultra-low-field brain MRI scanner

#81

Post by simcop2387 »

TheMagicHorsey wrote: post #72
lostlogin wrote: post #67

Earlier quoted context omitted.

I had a friend automating a production line and he needed to detect the level of peanut butter in a vat. He settled on an ultrasonic device as basically anything else ended up caked in peanut butter. It was an impressive setup, all done in Arduino.

I wonder if its practical to DIY your own production line automation today with Arduino. Like if I had a simple product, could I buy stuff off the shelf and integrate it myself in my garage and end up with a little mini-factory? Exciting to think about.

Probably not impossible, but I think the bigger thing will be the time to research the mechanical design of whatever you're doing. That and finding reasonably priced sensors that will be reliable.

Re: A low-cost and shielding-free ultra-low-field brain MRI scanner

#82

Post by jart »

scratcheee wrote: post #12
a-dub wrote: post #5

woah. woah. woah. hold on a second here... are we comfortable enough with understanding all of the behavior of deep learning models to where we can confidently put them in the pipeline for diagnostic clinical imaging? i'm okay with using them for image analysis, but denoising and other image production tasks seems dangerous. how do you know what you're looking at is real as opposed to something that just looks convin…

Exactly my thoughts too. I'm fine with a simple noise-removal pass, but if the AI is context-aware, what's to stop it saying "hmm, this brain would look more like a normal brain if I remove these tumors". Obviously, they'll test for that, but that only handles common cases they concider, it's always going to be a risk for more unusual sceanrios, and the danger with altering the data is that anyone looking at the resu…

How do you know? They're both based on neural networks. JBIG2 was also responsible for the Pegasus FORCEDENTRY thing.

Re: A low-cost and shielding-free ultra-low-field brain MRI scanner

#83

Post by lostlogin »

endymi0n wrote: post #77

Apart from the potentially massive significance to low-income countries and health costs, does someone has a good grasp on the applicability of the algorithmical advances towards classic MRI? My current gut feeling is like: If 0.055 Tesla can create this kind of image quality, what could we possibly expect at 1.5 or more?

You can expect a lot and you get it. It's truely impressive what a bog standard 1.5 or 3T magnet can do and how fast it can do it. A standard brain protocol will often include whole brain imaging at 0.8mm x 0.8mm x 0.8mm voxel size or thereabouts. It takes about 4-5 minutes. A leg angio done from start to finish in 20 minutes. This is without more advanced processing, and some clever processing is coming into clinical use now. Deep Resolve (Siemens) and Compressed Sense/Sensing (Philips/Siemens) are what I'm thinking of. Faster scans, or more resolution in the same time. It's a good time to be using MRI.

Edit: Compressed sense/sensing is not some AI/Machine learning thing. It's pretty neat though, a PR video here. https://www.siemens-healthineers.com/magnetic-resonance-imag...

Re: A low-cost and shielding-free ultra-low-field brain MRI scanner

#84

Post by omarhaneef »

wforfang wrote: post #44
omarhaneef wrote: post #7

Don't they already have something like this in the field? https://hyperfine.io

This exact product is mentioned in the article as evidence for clinical/market demand. It also shows precedence for FDA approval of a pretty similar instrument for clinical diagnostics. Although, its interesting to note that the hyperfine MRI (at least ostensibly) seems to do the same thing in a smaller/more portable form factor.

I missed it, but I guess my underlying question remains: what is the innovation over previous attempts that gets the paper into nature?

Re: A low-cost and shielding-free ultra-low-field brain MRI scanner

#85

Post by lostlogin »

qrian wrote: post #78
qrian wrote: post #76

Can this also do fMRI? I'm already trying to build DIY fnirs machine for cogsci research but if this does fMRI too I might build this one too.

> First, these scanners rely on complex superconducting electromagnet/cryogenics designs and ever increasingly powerful electronics (including gradient and radiofrequency power systems) for fast imaging and/or advanced imaging features like brain functional MRI and diffusion tractography, yet routine clinical uses only necessitate a small portion of these imaging protocols. I guess this implies not?

That's talking about a conventional scanner, the article is about a permanent magnet and a more straight forward design.

Re: A low-cost and shielding-free ultra-low-field brain MRI scanner

#86

Post by lostlogin »

VikingCoder wrote: post #26
a-dub wrote: post #5

woah. woah. woah. hold on a second here... are we comfortable enough with understanding all of the behavior of deep learning models to where we can confidently put them in the pipeline for diagnostic clinical imaging? i'm okay with using them for image analysis, but denoising and other image production tasks seems dangerous. how do you know what you're looking at is real as opposed to something that just looks convin…

That's a valid risk. You're asking a cost-benefit question. The cost of an invalid diagnosis is indeed high. The cost of no diagnosis at all is also high. This device will not replace the MR at your local hospital. It will be the first MR device in hospitals that have never had one before.

Veterinary MRI may be another application.

Re: A low-cost and shielding-free ultra-low-field brain MRI scanner

#87

Post by lostlogin »

axg11 wrote: post #46
a-dub wrote: post #5

woah. woah. woah. hold on a second here... are we comfortable enough with understanding all of the behavior of deep learning models to where we can confidently put them in the pipeline for diagnostic clinical imaging? i'm okay with using them for image analysis, but denoising and other image production tasks seems dangerous. how do you know what you're looking at is real as opposed to something that just looks convin…

Whether you’re comfortable with it or not - it’s already happened and in production. Look up Subtle Medical and GE AIR Recon.

Literally just purchased this - Installed tomorrow: https://www.siemens-healthineers.com/magnetic-resonance-imag...

Re: A low-cost and shielding-free ultra-low-field brain MRI scanner

#88

Post by lostlogin »

jcims wrote: post #10
petra wrote: post #9

Earlier quoted context omitted.

It's better than nothing. Let's start with those situations, and slowly build a database proving or disproving this technology.

>However, MRI accessibility is low and extremely inhomogeneous around the world. According to the 2020 Organisation for Economic Co-operation and Development (OECD) statistics, there are approximately 65,000 installations of MRI scanners worldwide (~7 per million inhabitants) Given that my little podunk hospital in the midwest seems to have roughly 5x the worldwide average number of MRI machines, totally agree.

MRI is also a massive revenue generator. That's a key reason they buy them.

Re: A low-cost and shielding-free ultra-low-field brain MRI scanner

#89

Post by lostlogin »

aidenn0 wrote: post #45
VikingCoder wrote: post #29

Earlier quoted context omitted.

That's not "unfortunate." Sparse observations save lives. A quicker MR. Less X-Ray exposure. It's totally valid to worry about validation, but to the degree you can validate image processing algorithms of any kind - AI or otherwise - they absolutely save lives.

NMRI use microwaves, not x-rays.

Yes, and when a quick MRI is available, it can remove the need for a CT. Fast brain protocols are now less than 5 minutes. This makes things practical that weren't before.

Re: A low-cost and shielding-free ultra-low-field brain MRI scanner

#90

Post by lostlogin »

MauranKilom wrote: post #6
a-dub wrote: post #5

woah. woah. woah. hold on a second here... are we comfortable enough with understanding all of the behavior of deep learning models to where we can confidently put them in the pipeline for diagnostic clinical imaging? i'm okay with using them for image analysis, but denoising and other image production tasks seems dangerous. how do you know what you're looking at is real as opposed to something that just looks convin…

Agreed, but I believe "using AI for inference from sparse observations" is unfortunately a thing already.

It's not unfortunate, it improves acquisition times and image quality - I use it daily.
Post reply on HN