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

Midjourney Medical

midjourney.com

Post reply on HN
Print view View original

551–560 of 927 posts

Re: Midjourney Medical

#551

Post by zarzavat »

ben_w wrote: post #505
moffkalast wrote: post #441

Earlier quoted context omitted.

Yeah I'm wondering where exactly people think we'd find the millions of additional MRI machines and technicians to run them to make this somehow viable, as if the current ones are not pretty much at 100% capacity at all times.

The website is calling for their full-body MRI-replacing ultrasonic scanners to be so cheap they're part of a spa session. TBH, this is already a red flag for me, like so many other "tech bro invents X" stories, though I am also aware of stories were "company realises Y is overpriced in medical purchases, makes Y cheaper, finds all hospitals think it is a scam and refuse to buy unless they raise prices".

Conventional ultrasound scanners are already cheap. Why can't a big ultrasound scanner be cheap too?

What makes MRI machines expensive is that they are big helium-cooled superconducting magnets that have to be continuously kept at a few Kelvin.

Re: Midjourney Medical

#552

Post by lambdaone »

intoXbox wrote: post #362
mNovak wrote: post #254

This is really interesting! And perhaps surprisingly doesn't trigger any immediate major technical red flags (as someone who has worked with MRI and phased array beamforming), as many HN HW articles do. My only criticism from the tech video would be that they spend some time lauding the nanometer deflection sensitivity, which might lead some to believe that's indicative of the image resolution. It's not, and it's som…

MRI physicist here as well. I have a basic understanding of ultrasound, and this looks like an array of transducers organized to perform tomography, just as CT did for Xray. However Ultrasound quality depends highly on transducer-skin contact. Any physicists here to comment on the effects of sonar through liquid and the effects on image resolution and field of view?

This is precisely why you do it in water - the water-skin contact is effectively perfect, as is the water-transducer interface, and the body of water is easily characterizable; in effect you are scanning one large object that consists of a body of water that just happens to have a human body in it, and then extracting the body from that scan.

Re: Midjourney Medical

#554

Post by throwawayben »

tptacek wrote: post #50
jdw64 wrote: post #39

Why is everyone so negative about this? Getting a CT or X-ray and then having AI do early screening on cases that doctors can pass along doesn't seem like a bad idea to me.

It is in fact very probably a bad idea. A good search term here is "incidentaloma". The balance of evidence currently appears to suggest that full body scans for asymptomatic patients are a net negative for health.

couldn't it be different when scanning becomes very cheap and quick and it's the delta over n scans that gives signal?

Re: Midjourney Medical

#555

Post by Topfi »

This is very concerning:

> Normally, for every diagnostic medical capability you need FDA approval. We’re starting by just giving you detailed body composition maps — and we’ll be submitting regular test results to the FDA for increased capabilities.

Ah yes, just "detailed body composition maps", nothing major. It's just radiology, not like people spend years of extensive education and have to sign off on every finding, often lying awake at night that they may have missed something. It's easy, don't let the Doctorpolice tell you otherwise. Seems very ̶T̶h̶e̶r̶a̶n̶o̶s̶ familiar. Also, not saying em dash automatically denote LLM writing, but come on, this whole thing reads very slopgenerated.

I have questions in general.

Why Midjourney? Do they have expertise? Even if so, why reuse a name that doesn't exactly denote reliable, consistent or trustworthy output? Why start as a spa with fancy LED lights clearly focused on experience over selling/leasing the whole-body implementation to third parties? Is the latter actually theres, how exactly does the licensing deal look and again, why them? Have they got any type of independent data to back up any of their findings? This just has the smell of something that, a few years from now everyone will be astounded that anyone ever believed this to be possible, for it is so patently ridiculous.

Never been a fan of image generation models for a variety of reasons, but this is downright dangerous, no way about it. Even if the technology as licensed works well, there are very good reasons why operating an MRI and seeing patients is not something you can do, just because you can afford to buy one. There is expertise needed here that, if this was coming from an established Medical Clinic and backed by research I'd be skeptical for such a spa setup to overcome, but again, this isn't even that. Best case scenario, this causes a VC to go bankrupt before the "spa" open and gets a front page on the goop magazine, worst case, patients are harmed, families destroyed and a comparatively minor penalty is administered/a pardon bought.

Not an assessment on the underlying concept/technology mind you, just the way Midjourney of all people are going about this.

Re: Midjourney Medical

#556

Post by andy99 »

keiferski wrote: post #348

I have a mixed response: 1. It kind of makes sense that an AI imagery company would apply that to other novel applications of imagery and computing and try to do something cool with it. 2. Midjourney as a brand is all over the place and this feels - off , somehow. I think from a branding pov they should have just started a different company with a different name. Perhaps a single image-focused umbrella company named…

On the “we don’t know what to do”, I think it’s cool that they are trying something medical with it. Success obviously isn’t assured, probably it isn’t even probable, but I’m happy to see companies try this rather than launch yet another whatever or start a consulting business. I hope as the field (AI generally) matures, more people decide to try life changing stuff with it.

Re: Midjourney Medical

#557

Post by laserbeam »

someothherguyy wrote: post #538
nirui wrote: post #392

I watched the video first without reading the text and thought, wow, Midjourney has gotten really good, they generated debris in the water exactly like what would happen in real life if the water is reused enough. Then I started reading the text, and realize it's not an ad for their video generating tool? Cool if each of it can do ~120000 scans per-month. But if I have to step in to a tank filled with debris and disc…

water filtration seems like the easy part

No, water filtration sounds like the first part the device will cheap out on to cut costs.

Re: Midjourney Medical

#558

Post by Levitz »

autoexec wrote: post #270
kibibu wrote: post #224

Earlier quoted context omitted.

I'm not putting my head under. How do we know this won't cause aneurysms? Damage eyes and ears? Getting a medical device approved takes time because of concerns like this.

It might not actually cause harm or strange effects to people's bodies, but I'd certainly feel better if it was tested and used by doctors in a hospital and not some "spa" since those tend to be poorly regulated and where all kinds of quackery takes place ( https://www.aafp.org/afp/afp-community-blog/med-spa-industry... ). The safety of the device itself is a concern, but so is the trustworthiness of the output. Midj…

>Midjourney already has some very questionable history with medical imagery (like this totally legit image of rat testicles published in "Frontiers in Cell and Developmental Biology" https://upload.wikimedia.org/wikipedia/commons/c/cc/AI_gener...)

I don't think "someone used their tool to produce a silly result and used it" qualifies as Midjourney having questionable history at all.

Re: Midjourney Medical

#559

Post by zarzavat »

theparanoid wrote: post #402
wkoszek wrote: post #382

Earlier quoted context omitted.

All doctors say this, and that sort of drove me away from healthtech. As if there were absolutely no way to take a step in a direction of fixing it. The faster and earlier we start to scan everyone regularly, as long as scanning methods aren't invasive, the more certainty we'll have what to warn people about and what not to tell them. Perhaps with the regular screening (imaging quarterly, if the scan is fast) you cou…

The targeted scans and tests that we already do offer surprising little benefit. Mammogram screening based on randomized-trial all-cause mortality, has not shown a measurable reduction in total deaths. Randomized colonoscopy screening has not shown a statistically significant all-cause mortality reduction.

> Randomized colonoscopy screening has not shown a statistically significant all-cause mortality reduction.

My grandfather went to the doctor complaining of chest pains, they gave him a colonoscopy, and he died of a heart attack a week later! Clearly colonoscopy doesn't reduce mortality!

There's no reason for almost any medical intervention to have a statistically significant effect on all cause mortality. That doesn't mean it doesn't have any effect on mortality of individuals.

Re: Midjourney Medical

#560

Post by GTP »

I find the technology side intriguing and worth a deeper dive.

But I'm not convinced about their view of having people casually going to a spa every week and getting a full body scan. AFAIK, some doctors tend to avoid full-body scans. The reason is that each body is different and has its own quirks. If you do a scan for no reason other than "I can do it fast", chances are that the scan will show something unusual. But, at the same time, it is likely that it isn't a problem. And now, you will be stressed about the chance of having some health condition and spend time and money digging into a rabbit hole of what the issue could be, only to find out it was nothing.

They also don't say anything about the price of such a machine. If they really envision a future where everyone can easily get a scan, this is a crucial factor.

Post reply on HN