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

511–520 of 927 posts

Re: Midjourney Medical

#511

Post by someothherguyy »

rzwitserloot wrote: post #490
convnet wrote: post #287

Earlier quoted context omitted.

It's a controversial and complicated idea. The downside, and the reason why most doctors do not recommend full body scans, is that every human body is a bit weird and there will almost always be something "wrong" that will be visible in a full body scan. This can lead to unnecessary testing, anxiety, and even unnecessary procedures. Many of these oddities flagged by the scan would never have caused any actual issues…

One obvious alternative plan, presupposing that Full Body Scan is dirt cheap, is the following protocol: - At 25 years old or whatever you get a FBS. Pretty much no matter what, this FBS will not be used to do more checks, procedures, and so on. - ... and now we give you another FBS every so-many years, and only those things that are different from the previous scan are investigated. There's still an issue with needl…

> - ... and now we give you another FBS every so-many years, and only those things that are different from the previous scan are investigated.

The diff can be meaningless as well. All sorts of benign things develop with age.

The resolution is the problem. You can't do the type of cytology and histology needed to understand all disease with just scans.

Re: Midjourney Medical

#512

Post by vrganj »

So the device itself seems cool and potentially useful as a low cost high volume alternative to MRIs that might be worth it for just like regular checkups at doctors offices before referring to more serious imaging if it detects something.

The whole spa angle is cringe at best, a glaring red flag at worst. Why not market this as a serious medical device if it actually works? Who asked for a spa with a novel computer imaging thing?

Re: Midjourney Medical

#513

Post by ixaxaar »

alpineman wrote: post #506

Great, a hallucinated output that only the super wealthy can afford, only to waste doctors' time with the need to run every test again at huge expense. Can we not leave medicine to the professionals? Creating a ghibli rip-off is not the same as diagnosing cancer.

Well healthcare needs its own DLSS 5!

Re: Midjourney Medical

#514

Post by dkbrk »

arcticbull wrote: post #273
tgsovlerkhgsel wrote: post #233

I think a lot of medical diagnosis could be solved with mass data collection if it was cheap enough. Right now, blood draws are somewhat routinely done because they provide a lot of human-interpretable indicators from a small number of values, and there is some evidence that e.g. "dogs can smell cancer" etc. (i.e. some diseases cause detectable odors). With a big enough data set of [all kinds of bio values, including…

Don’t make me tap the sign. Bayes Theorem: https://en.wikipedia.org/wiki/Bayes'_theorem There’s a very good reason we don’t test asymptomatic people in low incidence populations. Basically all positives are false positives when you do that, no matter how accurate the test is. When you’re testing healthy randos for everything the odds of a positive being false have so many 9s it would make an SRE weep. Unless this is…

You've got that completely backwards. Correctly applying Bayes' theorem, if an anomaly is observed you incorporate the prior into the calculation of the posterior probability. You don't just give up and say "the prior is miniscule so the likelihood is useless".

And then, even that's not enough. Decision theory needs to be applied to decide what action to take. That means taking into account the expected QALYs, cost and inconvenience across the distribution of possible outcomes. There's a whole spectrum of possible decisions, from immediately performing surgery, performing an invasive test like a biopsy, performing other less invasive tests, scheduling a follow-up non-invasive test at a later date, or just following a regular schedule of non-invasive tests and looking for any evolution along a longer time period.

The real problem is the binary thinking of either "we think you have X" and therefore tests must be performed or "we think you don't have X" and therefore tests shouldn't be performed. If medical organizations adopted empirically grounded decision frameworks, by applying them consistently doctors would be able to see something anomalous, assess that the risk isn't high enough to warrant immediate investigation, and be protected from a lawsuit in the unlikely case it was, in fact, something. And then we could do away with this "if we look we might find something" nonsense, which is pure fallacy.

Re: Midjourney Medical

#515

Post by A_D_E_P_T »

justaguyonline wrote: post #204
unholiness wrote: post #119

So, on the one hand, this is interesting! Reducing radiation from CT scans is a noble cause on its own. If on top of that it could make tomography cheaper and easier, you could imagine getting earlier detection of aneurisms, fibrosis, cirrhosis, thrombosis, stenosis, even plausibly cancerous masses (along with plenty of over-detection). On the other hand, nothing here substantiates this promise. We've got a video ren…

AI hype aside, this is one of those projects I'd like to know the open source stack of and the academic research behind. It's actually overlaps with an idea that started circling around in my head back when (deep) neural networks were the new hype cycle. What's the relation between sensor density and resolution? If their array could give femtometer resolution, how much could you drop the density when you only needed…

> femtometer resolution

The diameter of a carbon atom is 154 picometers. Nobody's going down into the femtos. And you're not going to get atomic resolution, either, because humans move around too much and things like scanning electron microscopes need very stationary samples. Even microscopic vibrations can blur the final image.

Which isn't to say that you couldn't get very good resolution...

Re: Midjourney Medical

#516

Post by Jabbles »

This is comparable to datacenters in space. We have no idea whether:

a) it is possible to construct such a scanner

b) the results of a scan would be able to diagnose anything

c) the false-positive rate would be low enough to make this useful

But it is probably very good as a source of speculation to hype the valuation of the company, because iff the above issues are solved, then this could be very valuable.

Re: Midjourney Medical

#517

Post by leothetechguy »

raindropm wrote: post #365
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…

The pivot to do things they want as AI research lab is perfectly understandable, but also..weird, like their loyal userbase are mostly creative people, and this pivot have ZERO things to do with those audience at all. It also gives a vibe that they gives zero damn about to those creatives audience, or the things that made name for them in the past anymore, or that what I feel as their subscriber... I know that David…

to be fair I wouldn't call people operating AI Image generators creative people. At best they're people curious about the technology itself, anybody willing to learn and do it for the sake of being creative does it themselves.

Re: Midjourney Medical

#518

Post by alpineman »

ixaxaar wrote: post #513
alpineman wrote: post #506

Great, a hallucinated output that only the super wealthy can afford, only to waste doctors' time with the need to run every test again at huge expense. Can we not leave medicine to the professionals? Creating a ghibli rip-off is not the same as diagnosing cancer.

Well healthcare needs its own DLSS 5!

I would just add that my wife is a doctor and in the age of AI it's truly unbearable. In addition to super long hours and stress they now have to deal with patients coming and thinking they know better than people who spent more than a decade in education because of what some chatbot told them.

Re: Midjourney Medical

#519

Post by dwroberts »

ccheney wrote: post #32
noobermin wrote: post #22

Clearly something like this would need to be approved by the FDA, it is literally irresponsible to promote something like this as being more powerful than a MRI.

Are you implying soundwaves are dangerous?

Focused ultrasound is already used as an actual surgery method and they have to carefully balance the parameters so it does not produce heating and damage [unrelated] tissue. Obviously a scanner would not aim for the same power/effects but it is possible to cause harm, yes

Re: Midjourney Medical

#520

Post by femto »

Aromasin wrote: post #510
z7 wrote: post #500

Earlier quoted context omitted.

"I just tested my hand in a mini version of this scanner. Images that are higher quality than MRI, whole body captured in https://x.com/SebastianCaliri/status/2067452733356122303

I help engineers design traditional scanners (Philips, GE, Siemens, etc). To be frank, this statement stinks like utter pig shit. Some PE bro preaching miracles about a technology that I am sure they are in some way invested in making profit from does not convince me of it's legitimacy. My base instincts, from the unfortunate experience of working daily with PE bros, tell me the opposite in fact. It gives déjà vu of…

As someone in the medical imaging field, are you aware of anyone working on passive sonar for medical imaging? I'm curious, as it's something that I've always thought would be fun to work on.
Post reply on HN