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

Ultrasound imaging of the brain

alephneuro.com

Post reply on HN
Print view View original

81–90 of 133 posts

Re: Ultrasound imaging of the brain

#81

Post by Unearned5161 »

The imaging stuff is cool but the homepage is making me wince.

There's a compelling argument to be made that the level of detail in "mind reading" they are gesturing at is plain unrecoverable with hemodynamics. There's an irreversible loss of dimensions that occurs the instant you start recording blood instead of spikes on the neural circuits themselves, and it's not at all clear that what a VC reading the words "telepathy" is imagining even survives that transformation.

What you have is food delivery data for a neighborhood, this can tell you a surprising amount, including when they might throw a party. What it can't tell you, however, is who wore the best outfit and what was talked about over dinner. The information simply does not survive across the interface.

There is a spectacular canyon between "informed interpretation" and "mind reading"

Re: Ultrasound imaging of the brain

#82

Post by 9dev »

janalsncm wrote: post #69
thaw13579 wrote: post #38

Cool work and proof of concept, and very excited to see where this goes. However, I do think there is enough exaggeration and missing information here that it warrants some critical appraisal. What's really missing is a comparison and validation with any existing medical imaging tech. Whole brain, contrast-free neurovascular imaging is essentially solved with MRI, why not run a scan and compare? Ultrasound is of cour…

As the article says, their ultrasound machine costs about as much as a smartphone. It’s about $4000. An MRI machine costs roughly 1000x as much.

Not your point, but… Do smartphones cost $4000 dollars now??

Re: Ultrasound imaging of the brain

#83

Post by cyber-anderson »

ogundipeore wrote: post #27
nico wrote: post #10

Is this the same tech the Midjourney scanner device is using?

Yeah, they’re using butterfly network chips for the ultrasound but with some additions. (IV with microbubbles that they can trace as it flows through the brain & some extra imaging algorithms)

[dead]

Re: Ultrasound imaging of the brain

#84

Post by fc417fc802 »

joezydeco wrote: post #64
CWuestefeld wrote: post #61

Earlier quoted context omitted.

Scarcity demands some means of rationing out the product. Setting higher prices is one means of doing this, so only those with some means of paying can get it. Another approach is via wait times, where only those who can wait and afford the time penalty can get it. There are other variations, but there's no such thing as a free lunch.

The scarcity comes from waiting to get preapproval from your physician and health insurance. If you are willing to pay out of pocket, there are many private MRI clinics that will scan you to your heart's content, as quickly as you want, as long as the payment clears. Granted, anything you find in that reading won't be accepted by your physician or insurance company, so it's more of a checkup for you and you alone. An…

> anything you find in that reading won't be accepted by your physician or insurance company,

Surely that it isn't the norm? Where do you live that the (I assume government run) health system dismisses evidence when its collection wasn't sanctioned by official channels?

Re: Ultrasound imaging of the brain

#85

Post by fc417fc802 »

9dev wrote: post #82
janalsncm wrote: post #69

Earlier quoted context omitted.

As the article says, their ultrasound machine costs about as much as a smartphone. It’s about $4000. An MRI machine costs roughly 1000x as much.

Not your point, but… Do smartphones cost $4000 dollars now??

No but that's the order of magnitude. The high end is commonly a bit over $1k.

Re: Ultrasound imaging of the brain

#86

Post by fc417fc802 »

thaw13579 wrote: post #78
lostlogin wrote: post #72

Earlier quoted context omitted.

There are big costs. The hardware, the facility (RF cage and chillers), power, water, staff, RIS/PACS etc etc. I can’t see how you can do it for $50. Does the ‘universal healthcare’ bit mean that the government is paying most the bill and it’s $50 out of pocket?

Yes, $50 was a rough out-of-pocket estimate, the amortized cost per scan for operation alone is probably on the order of hundreds of dollars per scan, assuming high utilization. One funny thing about MRIs is the magnet is always on, so there could be some clever ways to reduce costs running them after hours.

> there could be some clever ways to reduce costs running them after hours.

It seems like a dedicated round the clock facility housing at least dozens of MRI machines ought to offer significant economies of scale. I wonder if I'm wrong about that or if there's some other reason we don't see this approach taken by governments.

Re: Ultrasound imaging of the brain

#87

Post by fc417fc802 »

trevor-e wrote: post #66

Not trying to sound alarmist at all but I am wondering if ultrasounds are safe to be used like this? My understanding is it's basically a high-frequency sound wave which is probably fine for most tissue usage, however here it says it's scattering off of red blood cells. I don't know why that feels so unsettling to me.

Waves scatter off of everything so that's not of concern. Depending on the intensity, frequency, and tissue in question ultrasound can have an effect. Someone elsewhere linked to a couple academic papers on the topic.

I share your hesitation about using this on the brain, at least barring exhaustive long term animal model trials. Subject a mammal to this every day for 10 years and show that there are no negative effects relative to the control.

Re: Ultrasound imaging of the brain

#88

Post by robbiep »

scratcheee wrote: post #50
thaw13579 wrote: post #44

Earlier quoted context omitted.

I completely agree that's an issue, although more of an economic / public health policy issue than a technical one. There are low field MRI systems, such as the one made by Hyperfine that are, like you say, an order of magnitude cheaper and simpler to run. We should have these everywhere, IMO https://www.hyperfinemri.com/

MRIs are fundamentally expensive. Yes we can bring the price down a bit, and we can set more money aside for them, but they’ll always be limited by their price. Even if this technique is much worse (I can certainly believe it is) the price might allow uses that would never be practical with MRI even with the best financial support. For example, ultrasound might be viable for use in GPs or small medical facilities whi…

The methods described in the main article refer specifically to neurovascular imaging. In order to have a higher resolution, they’re making use of microbubbles (which need to be prepared and injected just prior to imaging).

There is no world where vascular imaging with a methodology like this is better than what I can do today in a GP clinic with a handheld GE or butterfly (or similar) US probe for anything that matters:

- for dvts and thrombus I can already image them

- if it’s in the brain the last thing that is useful for you to do is fuck around in a small clinic when you should be getting to a major tertiary centre as soon as possible

Re: Ultrasound imaging of the brain

#89

Post by tokyovigilante »

fastball wrote: post #79
tokyovigilante wrote: post #73

This is complete nonsense. Ultrasound can’t effectively penetrate the skull. The entire thing (and Midjourney’s) is vibed-up nonsense. The only reason this even exists as a brainfart and hasn’t been immediately laughed out of VC funding is because other imaging modalities require either ionising radiation (illegal to produce without source licences) or an enormous magnet (would be wildly unsafe in the hands of what a…

Ultrasound can penetrate the skull, esp if through a thin part of the skull (like the temporal bone, which going from the graphic on the website is exactly where they are targeting these waves) and with targeted frequencies. You are misinformed.

I am a consultant radiologist. Tell that to my 6-month old infants who require MRI with GA because their fontanelles are closed. Transtemporal can give you a poorly resolved image of the 3rd ventricle at a pinch.

“Targeted frequencies” - righto.

Re: Ultrasound imaging of the brain

#90

Post by lostlogin »

fc417fc802 wrote: post #86
thaw13579 wrote: post #78

Earlier quoted context omitted.

Yes, $50 was a rough out-of-pocket estimate, the amortized cost per scan for operation alone is probably on the order of hundreds of dollars per scan, assuming high utilization. One funny thing about MRIs is the magnet is always on, so there could be some clever ways to reduce costs running them after hours.

> there could be some clever ways to reduce costs running them after hours. It seems like a dedicated round the clock facility housing at least dozens of MRI machines ought to offer significant economies of scale. I wonder if I'm wrong about that or if there's some other reason we don't see this approach taken by governments.

The staffing costs then skyrocket. 1.5x or double time. However, the main obstacle is a lack of staff. Good staff are hard to find and worth what they cost. And they usually don't want to work out of hours. The economies of scale are interesting. Eg PACS/RIS cost very little more when you increase scans done, and rent is a fixed cost. The best thing that happens are you increase scanners at a the management of no-shows. Patients fail to turn up regularly (a 'did not arrive', DNA). With more imaging going on, you just grab the next available patient, the gap ends up later on, then you make a new booking. The record at my site is 6 DNAs and no slots missed. I run a small MRI service.
Post reply on HN