Midjourney Medical | Hacker News Reader

Midjourney Medical

midjourney.com

1,377 pointsricochet11878 comments

https://www.midjourney.com/medical

Video: https://x.com/midjourney/status/2067422898407837797

Some initial thoughts as a practicing radiologist:

- This looks really cool and I hope they keep innovating on this. I love seeing new modalities develop and despite my (many) reservations and criticisms, if even one good use case comes out of it that truly helps people, it's tech money well spent imo.

- They show the reconstructed images as though they are a low resolution CT, and promise that quality will improve as they iterate. This is cool, but ultrasound is not CT. Ultrasound cannot image the lungs, as they are filled with air. You cannot find bone lesions, as the sound waves do not penetrate the cortex. You cannot image many structures in the abdomen if they are surrounded by gas-filled bowel. The brain is encased in bone, so you might get some penetration but it will be very limited. Even with theoretically perfect AI reconstruction, these scans will not be true "full body" in that there will be structures that are not reliably imaged. Imagine paying for weekly full body scans for years, everything looks fine, then its the lung cancer surrounded by air and invisible to ultrasound that kills you (that's why we use CT for lung screening!)

- The images they show are very cool, and do appear to show the correct structures. I realize this is early, but fuzzy shapes of organs is very, very far from medically useful. The whole point of screening is to identify problems early, often by definition, small. This technology looks like it will be best for seeing large, superficial (close to the skin) structures, whereas for effective screening, you want the opposite - small, deep structures.

- "Incidentalomas" or unexpected, probably benign, findings are annoying to physicians, but I in general have no problem with people collecting data on themselves where they can. To me it's similar to heart rate monitors or home blood pressure cuffs. The main issue here is education, so that patients know what the data is and is not telling them. The more complex the data, the more difficult that is.

- Many people mistakenly believe that early diagnosis is the final boss in medicine, that if only we could find every cancer early we could prevent all those deaths. There are, in fact, many, many other hurdles and bottlenecks. Many chronic, expensive diseases do not have clear imaging manifestations. The claim that "it's completely possible that with enough early imaging in the future, the world could avoid 30% of all deaths and 50% of all healthcare costs", I think, to any practicing physician, would sound completely divorced from reality.

> The brain is encased in bone, so you might get some penetration but it will be very limited.

Radiologist as well. Remember this is full wave inversion not pulsed wave B mode. You can get much more useful information from both high low frequency and capture transmitted waves.

There is promise with this and we use it for example with MRgFUS. With advanced computational models or patient specific CT/ZTE MR aberration correction it is theoretically very feasible to image the brain with ultrasound, whether that’s more useful than say portable low field strength MR is a different question altogether.

> This is cool, but ultrasound is not CT.

Not to be pedantic but since this is a tech forum I would clarify that FWI US is computed tomography by definition (at least in this and many applications). Gas degrades conventional CT too, it’s just worse with US as you have little to no forward propagation and of course innumerable interfaces in the lungs to reflect and scatter.

I do a lot of MRI analysis including segmentation of small structures in the hippocampus called the hippocampal subfields. To collect these segmentations, we collect partial-field-of-view high in-plane resolution T2-weighted images on a 3 or 7 Tesla magnet. These sequences are generally only included in research protocols if the research specifically cares about hippocampal subfields...therefore they are rarely collected. There have been attempts to enable segmentation of these small structures using lower resolution T1-weighted scans, leveraging deep-learning or other models trained on concurrent T2w high resolution scans and the lower resolution scans within the same subject, allowing the model to predict the higher resolution information from the lower resolution inputs. This produces spectacularly beautiful segmentation on shitty data. Data whose resolution is about the same as the thickness of the structures you are segmenting or less. The problem is this: 1. The lower resolution image barely has any information in it on these smaller structures 2. The accuracy of the resulting segmentation depends entirely on how much the person fits the training distribution. But much research is on specific populations: children, autism, etc. 3. Some big names in imaging analysis tools have published these tools, lending their credibility to them. 4. The beautiful segmentations and (3) tend to convince non hippocampal experts that the resulting data is trustworthy, especially to an eager beaver researcher trying to maximize the impact of their already collected datasets.

I've rejected a number of papers for this.

But my point is this. Midjourney Medical might train a model to produce pretty images with this technique, but the more they need to depend on deep-learning models to get usable data, the more that the match between the training distribution and patient will matter.

I'm not a medical doctor at all, just an engineer who works in medical devices and I'm definitely sceptical about this.

I'm not totally sure of the value of an imaging system that only gives you very low resolution images if they're not accurate enough to determine anything from. You'd need a secondary CT or MRI anyway so why not skip to that?

My real concern is the dependence on external servers to reconstruct the images

Edit: From reading other people's comments, people are acting as if this is the first device trying to sell itself as improving pre-diagnosis imaging and this is totally revolutionary. This is not, and if any of the other products have convinced the entire medical industry that frequent imaging is beneficial then neither will this

Not a physician. Some observations on these statements.

The predicate is "given how we practice medicine and the limits of humans ability to interpret the imaging modalities we have."

The more specific predicate is "for my specialty would this replace or prove superior to the tools that I have?"

Both of these are totally reasonable, however the history of medicine, and science in general, is that creating new ways to look at things has a tendency to reveal information that we never knew we needed.

For example, for years I thought of blood sugar as something that was either in a good or bad range. Then I tried a continuous blood sugar monitor. The full picture of the body's response to specific foods that I ate was eye opening. There's so much more to learn when you get a higher resolution (temporal in that case) view into your body.

Another wonderfully hopeful example is the retinal imaging ML work done by google. A completely non-invasive image of the retina for diabetic issues, that also happened to be able to predict things like age, sex, smoking status, previous cardiac events and more! Just take high-res pictures of things! The body is interconnected in ways that you can infer from one system so much about others.

So while I don't think anything the Dr. said is "wrong", I think it represents a very common blinkered mindset of pragmatic practitioners who need to deliver reliable performance daily.

this is why i always come to hacker news for the expert opinions. thank you for being critical yet optimistic.

> ultrasound is not CT

They're using "CT" in its literal sense: tomography*, using computers. In this case, ultrasound is the penetrating wave rather than x-ray. It is of course a very different thing than what the medical world knows as "CT" today.

*https://en.wikipedia.org/wiki/Tomography

I'm far more willing to trust someone in the field every day (you), over keyboard warriors who want to validate their new toy is alive.

> "Incidentalomas"

Good word for it. We were a bit worried about something that showed up my my mum's scans, as if an inoperable tangerine-sized lung tumour wasn't a big enough problem. It was a round dot about the size of a pea on her adrenal gland that lit up like crazy in contrast dye. Now, that as you probably know was a worry because oh shit, lymphatic system involvement, that's going to spread like crazy.

But after two years of immunotherapy, and about six years after being detected while the lung cancer is gone, the pea is still there, still as bright as ever, neither getting bigger nor smaller.

No-one is in a hurry to poke at it and see what it is, just in case that turns out to be a mistake.

89 this year and at least got to see her grandchildren start primary school, so good work from your lot and the oncologists!

Now I know it's an "incidentaloma" :-)

They spent a lot of time selling the spa, and not a lot of time showing us the data.

> Many people mistakenly believe that early diagnosis is the final boss in medicine,

True. My more nuanced take on it: For most chronic conditions (including cancer) diagnostics have improved but resolution has not. The PR machine of course hypes things to make it seem like we have more cures today that in the past. What is have is more diagnostics and more procedures.

> "Incidentalomas" or unexpected, probably benign, findings are annoying to physicians

For a lot of these things I wonder why they don't just do multiple scans just to see how things develop. Is it a cost issue?

I have a friend who may be dying. It's not cancer but equally dangerous. They caught it early but they're powerless to do anything. We're just watching, waiting, and hoping.

Couldn't have said it better.

> You want as much data as you can get about your health as quickly and as cheaply as possible. In other words, you want a technology optimized for getting as many “megabytes per second per dollar” of information about your body.

This is so far from my vision of what I want from healthcare. I want a healthcare system that is optimised around A) proactively keeping me healthy, and B) reactively helping get back to healthy when I am not. I do not care about the amount of megabytes of data I have about my body.

The way we figure out how to catch issues before you notice them (i.e. proactively keeping you healthy) and figure out the best ways to fix them (i.e. reactively helping you get back to healthy) is by having more data from more people in more situations, so we can make those determinations.

I understand some of the current fatigue around biohacking and chasing perhaps-irrelevant metrics, but takes like this surprise me. Do you think people said the same kind of things before the blood pressure cuff became widely available? Or heart rate monitors? Or bathroom scales?

Do we just want to walk around with blinders on because we think we feel OK right now? More data is the only way to get better at this stuff.

Aren't they serving the same thing? Proactively and reactively keeping you healthy requires understanding your body, both the baseline of how it functions when you're healthy, and how it functions when you're not.

Right now we're often in a situation where the only data you have is expensive tests ran when you're sick enough to justify them, when it may already be too late.

Yeah, I want something which is optimized for getting me actionable and more importantly accurate information, preferably without flagging every outlier as the harbinger of a disease that'll kill me within the next six weeks.

How do you keep robustly pro active without data? Of course megabytes of data isn't a direct measure of health. That also isn't what medjourney is proposing be the metric. They didn't say "doctors will review the storage requirements of your available data and be able to tell you...". It's a straw man. Comprehensive imaging isn't a full insight into health. Neither are many questions in a medical history. But accurate and easy to obtain medical imaging is certainly a strong addition. Neither are complete, both are extremely useful and important. It's defense in depth. Included in an annual physical, imaging from even existing methods would have saved the lives of more than one family member who died of cancer gone undetected despite following existing best practices for preventative health. It's also impractical and expensive, though cheaper than years before. Faster cheaper and more accurate seem better still when it will be an additional channel of information.

The fact that you're not naming any cost related variable reflects your own current personal situation (privileged, I'd assume). But this is NOT the situation for most people in the world.

Don't get me wrong, I'm also privileged. I can pay for pretty much any type of medical intervention that I'd need. So my variables are usually "comfort", "speed", "convenience", etc. But I know that this is NOT the most common scenario for everybody.

After an injury, you may want to get an MRI to help you recover and determine best course of action. If an MRI cost a million dollars, or a single MRI scan took an entire day (which means every machine within driving distance will be booked years in advance or will be reserved for only the most critical cases), you won't benefit from an MRI image.

"Megabytes per second per dollar" may not be the optimal way to phrase this, but cost and efficiency are a real concern.

I want to give my money to actual individual doctors who studied this for a decade, have the work and life experience to make informed judgements and decisions to reason about my health. I dont want to pay a company to digitize my body and then sell the data back to me

> A) proactively keeping me healthy, and B) reactively helping get back to healthy when I am not

You want technology to train you how to avoid environmental factors and then give you treatment?

we're still very far away from eliminating humans in the loop from medicine.

All I want is the safety that, if something is wrong, treating it won’t bankrupt me.

That's like saying you don't care about the hundreds of kilobytes of your DNA biome you can obtains nowadays for nearly free, you care about being healthy.

My man, YOU USE THOSE bytes for that purpose exactly.

>A) proactively keeping me healthy,

This will never happen and arguably should not be the *medical* system's problem. It is just not feasible

Everything you want in your desired healthcare system can be stored as data.

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 [Name] with Midjourney and this medtech company as separate subsidiaries.

3. AI imagery companies suddenly making medtech products and spas feels very “we don’t know what to do, so we’re going to throw spaghetti at the wall.” That doesn’t necessarily mean it’ll be bad, just that it’s not typically what you’d do if you’re working on something super successful already.

4. AFAIK they are entirely self-funded and so this really isn’t about VC scaling or anything like that. But that doesn’t mean they’re immune to the same cultural pressures.

Midjourney is not actually an AI imagery company. It's a research lab that happened to do AI images first.

The founder is a hardware guy who made enough money to retire young off of the sale of his company, Leap Motion. But, he decided what he really wanted to do was cool research with cool people. So, he started Midjourney. The goal for the AI image generator was to be cool research, pay for itself, and grow the lab. It ended up making far more money than ever expected.

I was a Discord mod for Midjourney when it was still in private beta. I got to participate in some of the discussions of "WTH are we doing and how should we do it?" DavidH is very much a smart hippie idealist. He isn't really motivated by even more money beyond how it enables more fun research. MJ actively refused investment. And, actively refused partnerships that would make them money but wouldn't help build the community or the lab.

So, put together: I can totally see how this looks weird from the outside. But, having spent a few years peeking inside, I'm only surprised it took so long for them to branch out like this.

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.

> we don’t know what to do, so we’re going to throw spaghetti at the wall

My opinion is that the money is in the verticals as the models and harnesses built around them become commodities. Specializing in a vertical, especially where hardware is involved, creates a buffer between companies and the frontier labs. The frontier labs are spreading themselves thin trying to capture verticals like finance or legal but aren’t narrow enough to be as competitive as a company that is going for a more targeted approach.

> “we don’t know what to do, so we’re going to throw spaghetti at the wall.

this is pretty normal, i mean you have OpenAI and Anthropic trying the same as well. OpenAI is working on legal stuff [1] and also rolled out (or said they'll roll out) ChatGPT Health [2]. Then there was Sora etc.

These companies need applications for their tokens and someone has to build them. If they can win even with one, that's a net benefit for them no?

1 - https://www.artificiallawyer.com/2026/06/02/openai-targets-t...

2 - https://openai.com/index/introducing-chatgpt-health/

quite the opposite. it feels refreshing that ppl with talent and money can do inspiring things with it.

The branding choice is crazy to me. “Midjourney” is pretty much synonymous with “generated images that aren’t real”. Which is the opposite of what you want when it comes to medical imagery and data.

yeah. they could have called it Medjourney.

In a sea of AI products, the brand is still powerful though. Would I have clicked this if not for the Midjourney name? Probably not

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 Holz have his own unique way of doing things but it's still...weird!

oh, and the hypetrain on X. yikes..

“To the man with a new hammer, all problems look like a nail.”

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 somewhat of a distraction -- that's just giving us amplitude information, which is comparatively less important than correlated time/phase across the 100k sensors. They do later on state ~mm resolution, which is still great!

Doppler and motion blur may be an issue (e.g. heart beating), as one slice requires a full ring of sequential exposures. But still way faster than MRI, so probably fine.

On a lighter note, it could seriously change the meaning of get FUCT (Full body Ultrasound Computational Tomography)!

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?

Ultrasound researcher working on fast microvascular imaging here. Depends on the datarates, you can generally get pretty good blood flow data pretty fast, with <.5 seconds per slice if you do it with appropriate algorithms. A lot of this depends on motion though as you said, as the issue is generally getting a high-enough SNR (blood flow is generally 30-40 dB below tissue in energy, except for the biggest of vessels). Generally, higher frequencies have less of a separation between blood and tissue, but they have issue with attenuation. But I think with enough SNR (and with their element count that may indeed be possible), they could get pretty good blood flow data across the whole body.

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.

Why can't we do full body scans, learn about these "quirks", and document them in the wider science literature?

I understand there are many benign tumors that doctors prefer to ignore in people, but eventually when scanning becomes portable and safe enough having regular access to scans could really help a lot of conditions.

Overdiagnosis can be a problem. On the flip side, I wonder if adding the time dimension to the data (i.e., you could realistically have scans from every few weeks over the course of years) could significantly change that.

Instead of looking at a single snapshot of a person, you're now looking at trends over time. We probably don't have the analytical tools to effectively evaluate medical imaging with that time dimension at such scale (because I assume it would be rare for someone to get MRIs so frequently), but maybe with more data and study, we'll be able to more definitively distinguish benign quirks from real concerns.

Rather than a human comparing a couple of scans five years apart, you're talking about computationally identifying outlying regions in the data (a motion picture of the entire body) that are trending towards areas of concern.

If this becomes cheap and widespread, there'll likely be an initial iatrogenic spike, of course--but how could you think that having an enormous amount of precise, quantifiable data about a lot of bodies, and the ability to analyze all that data, is a bad thing in the long run?

I thought the same. There are papers analyzing data about that.

https://www.wiserhealthcare.org.au/too-much-of-a-good-thing-...

> As well as being unlikely to be beneficial, full body general health checks in asymptomatic people can potentially be harmful. The main harms are overdiagnosis, detrimental psychological effects, negative effects on health behaviours (for example, failure to quit smoking due to reassurance of good health), complications related to follow-up tests, and unnecessary treatments.

MedLifeCrisis the youtube channel has a great video [1] on why you shouldn't full body scan. He's a consultant (highest level of doctor) in the NHS in England (and has done a PhD and research as is common in the UK medical system).

[1]: https://youtu.be/BJ9soFmzYO8

> chances are that the scan will show something unusual

Something unusual in a single one-off scan vs something unusual and changing over the course of multiple scans give two different views.

I learned this from watching House. I am certain that it's true, but I also kind of wonder how much backpressure there is against this kind of thing because the scanners are also insanely expensive to run per minute.

"We shouldn't collect information because we don't know how to fit it into our care playbook" might be rational for a single patient, but it's a policy that will lock you into your current playbook.

Our medical industry is set up to only evolve via highly centralized research that fully situates a diagnostic within a particular treatment path. This approach makes it more and more expensive to improve care for narrower and narrower populations - driving medicine towards being a luxury good.

I'd like to see midjourney say more about price, but I love the idea of starting some new diagnostic pathways with different principles. There are probably all sorts of low hanging fruit to be found about new treatment strategies... It just takes some faith that nature hasn't hidden all of her secrets in the one place we already know how to look.

>> But I'm not convinced about their view of having people casually going to a spa every week and getting a full body scan.

People are already doing this monthly with DEXA scans!

Another reason is that we don't actually know what negative effects regular "scans" might have.

Actually in some cases we do know. Regular xrays are harmful, for example.

Agreed, If you look for issues, you'll find them.

Anecdote: My wife had a high risk pregnancy. They did more than the usual scans and tests, and at one point we were told to go immediately to the NICU, spent 48h there , more tests. None of the tests really showed anything other than she was different than the normal pregnancy (I won't get into the specifics).

In the end, we have a healthy child but it was a lot of pain just going through test after test just because things were out of bands (my words).

SOTA ultrasound devices are still very expensive, with e.g. a custom 3D probe with a few hundred piezo elements costing well over 10k. IF they want to use MEMS probe instead of piezo (which is implied by them saying that they will use a chirp), that's going to be even more expensive, considering the lack of manufacturing know-how. When sufficiently scaled, I wouldn't say it is an exorbitant price for large research hospitals, but I am a little skeptical of rolling these out as a health checkup "spa" service outside of areas with extreme wealth concentration (e.g., Silicon Valley? Sure. London? Yeah; Minneapolis? not so sure.)

I know you are right but it just sounds so dumb. In theory it should be possible to do a scan and then realize most things you find are likely not a problem and don't worry about them.

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 render of what a hypothetical device could look like. It's probably more than nothing (they got exclusive license on these butterfly chips in 2025, and it's at least plausible that the best solution to the data bottleneck in an absurdly noisy system like this is real-time AI image processing)... But it's certainly less than something. It's a hype video that doesn't prove feasibility of anything, yet.

EDIT: This is all in reaction to the second video on the announcement post[0], which is much more informative than anything on the page currently linked.

[0]https://www.midjourney.com/medical/blogpost

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 to detect forearm muscle movements through the skim.

The way Ctl-labs was trying achieve the same results always seemed like it had fundamental physical limitations due to the nature of electromyography (to this software engineer...)

"I just tested my hand in a mini version of this scanner. Images that are higher quality than MRI, whole body captured in <1 minute, virtually free to run. This is going to change medicine."

https://x.com/SebastianCaliri/status/2067452733356122303

> Reducing radiation from CT scans is a noble cause on its own

Is it? Linear No Threshold has largely been rejected at this point. https://jnm.snmjournals.org/content/early/2024/06/21/jnumed....

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.

that's not a video render of a hypothetical device, that's a real video of the real working device, fwiw

This reeks of peak bubble, it’s ok say that.

> Beyond that, regulation is the next limit. 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.

This is just not how the FDA works. At all. You can't just email them slideware and marketing materials to keep them in the loop.

You have to hire an army of expensive compliance people (cheap ones aren't nimble enough for startups), develop the whole thing start to finish under strict design controls, and usually throw a lot of time and capital into convincing regulators your very innovative and disruptive new R&D endeavor is actually derivative enough to draft behind some existing medical device.

For reference, OP is talking about the 510(k) process. One of the issues with that process is that an approved medical device may end up with a whole tree of "derivative" devices approved through the 510(k) process. If that original device is then found to have problems and has its approval removed, those derivative devices do not also become unapproved.

It sounds like they are trying to fly under the FDA thresholds for regulation as a medical device and be considered a low risk "wellness device" which makes no medical diagnostic claims and has low risk. This is why it is in spas and not doctor's offices.

https://www.fda.gov/regulatory-information/search-fda-guidan...

> FDA may consider certain products that use non-invasive sensing (e.g. optical sensing) to estimate, infer, or output physiologic parameters (e.g. blood pressure, oxygen saturation, blood glucose, heart rate variability) to be general wellness products when such outputs are intended solely for wellness uses, and provided they:

• are non-invasive and not-implanted;

• do not involve an intervention or technology that may pose a risk to the safety of users or other persons if specific regulatory controls are not applied;

• are not intended for the diagnosis, cure, mitigation, prevention, or treatment of a disease or condition;

• are not intended to substitute for an FDA-authorized, cleared, or approved device;

• do not include claims, functionality, or outputs that prompt or guide specific clinical action or medical management; and

• do not include values that mimic those used clinically unless validated (e.g. manufacturer testing, peer-reviewed clinical literature) to reflect those values

That may be true, but the FDA is no longer run by fiduciaries of the United States.

do they need FDA approval to have a good impact? it doesn't need to be a licensed medical device for me to interpret the data, and then verbally tell my doctor what's wrong

this is similar to how people get a lot of medical value out of chatgpt today

This is ridiculously optimistic. The technology, USCT with full waveform inversion, is not new.

It’s already used in breast imaging (SoftVue) and hasn’t replace mammography. A body part ideally suited for ultrasound.

More compute many minimize some of the fundamental limits of sound waves (bone and gas) but I would be shocked if they have useful images of 90% of the body parts we image with CT or MRI and even beyond that I question how much it’s more useful than B-mode anyway.

Quite slow which means most things abdomen and chest will be motion degraded.

This may be useful in superficial areas but then why do whole body anyway. Might be some new niches and interesting research but hardly revolutionary in my opinion.

Exactly, try can get a very limited FOV which is probably why they showcased it on arms/legs first

I don't understand how people can hate on this. It's probably the most novel & ambitious consumer health device ever? Plus they're doing it fully bootstrapped. Let them cook!

It seems like the radiology equivalent to a blood testing machine that could be deployed to walgreens and detect 100 diseases with a finger prick.

Not hating, but there's no way resolution gets as good as MRI with ultrasound computed tomography (https://en.wikipedia.org/wiki/Ultrasound_computer_tomography). Doing something like searching for room-temperature semiconductors so that MRI scanners are much cheaper to operate would be a more worthy goal.

Ultrasonic imaging is definitely not novel. And it requires you tolerate being fully submerged. And all you get is an image that is the SAME quality as an MRI. Except now you are soaking wet.

As a consumer health device, we haven't even gotten the population at large to wear biometrics and the CGM fad is over. Full body scans that cannot be used by a physician are not generally useful. If they aren't targeting FDA approval right off the bat, they are wasting their time. This is not solving any current problem in healthcare- you can get an MRI for $2K cash out of pocket and you get to keep your clothes dry

what's the novelty? mixing healthcare together with a spa is an idea older than Christ. USCT is decades old.

Their butterfly chips might be cool, but it's not like the article says anything about that. There's only one other comment in the whole thread that even mentions it.

How old are you? I've been conned all my life by tech companies selling us "deliverance from work", "permanent Mars bases", "asteroid mining", "AR/VR everywhere, for everyone, all the time", "crypto will replace money", "3d TVs are the new hot shit", "self driving cars for everyone in 2 years tops"

I don't understand how people are so gullible? How do they keep falling for it?

I think I hate any single product announcement that involves "We have nothing, but we'll have something next year, and then we'll have 50k locations worldwide just two years later!"

In my opinion the issue is that many (maybe most) people who've heard of Midjourney associate the brand with AI slop imagery. Whether that reputation is fair or not is beside the point.

Totally agree.

This community can be much better than that.

> enough to give regular, monthly scans to a billion people.

There is a part of me that thinks it would be cool to get cheap full body scans. I like being able to see inside of myself. I can think of a lot of situations where the low-fidelity images coming out of this (they're not good compared to real medical imaging, if you've ever looking at MRI/CT up close) could be useful for coarse analysis of certain conditions that come and go or need to be monitored over long periods of time.

What I don't like is the idea of getting people to do full body scans every month just to be safe. This might sound like a good idea if you haven't looked at the literature on preventative full body imaging. Looking for bad things inside the body sounds like a great idea on the surface.

The problem is that imaging, especially when it's as rough as these ultrasounds, and possibly worse when augmented by AI guessing at what it's seeing, can lead to a lot of unnecessary procedures. The net effect can even become more harmful than the number of real problems it catches. There's a long history of research on this as many companies have tried to commercialize full-body scanning in the past. It frequently leads to situations where there's an unknown or ambiguous spot on the imaging that the person reading the scan can't rule out, which turns into a lot of anxiety and eventually more imaging, biopsies, or unnecessary surgeries. It's easy to think "better safe than sorry" until you realize how often these benign but ambiguous findings show up on full body imaging.

So my initial thoughts on this are that it would be good to make cheap ultrasonic imaging accessible as an as-needed service to use for specific conditions. I do not think it's a good idea to go down the road of trying to scan the entire population once a month and then run it through AI to see if anything pops up. The number of false positives would be overwhelming and lead to a lot of unnecessary procedures to calm the resulting anxieties.

This style of argument has always bothered me, because the correction to misdiagnosis or mistreatment is not to stop looking, it's _git gud_.

For sure, we have to be realistic about what processes will systematically have error, and if we can't stop a doctor from doing bad things with a piece of data we should shield them from it, but the tools to make scalable, calibrated risk estimates based on large data dumps is getting better every year.

> The number of false positives would be overwhelming and lead to a lot of unnecessary procedures to calm the resulting anxieties.

If the scans are cheap and fast enough, the solution is to not do anything until you’ve observed the mass in question grow over time, not just be there.

I love how people wait for some kind of technological God or magic silver bullet to """cure""" them, but when it comes to eating clean, exercising, not sitting 8 hours in front of a fucking screen every single day, getting good sleep, and all the other low hanging fruits you can act on right now, it's radio silence even though it would solves the majority of health issues

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 ones considered irrelevant for that disease] labeled with diagnoses, I suspect we could get very fast and accurate automatic diagnoses, even from a limited data set currently considered uncorrelated. Rather than going to your primary care physician, you'd go into the standardized, mass-produced and thus reasonably cheap everything-scanner, and you could likely get a more accurate diagnosis (or at least "things to check") than the average doctor would be able to give you under the practical constraints they typically operate under (time, available information/diagnostics).

This goes in that direction, and I'm really excited to see where it goes. I could imagine that given enough training data, ML models will be able to pick up on minute details that make it possible to diagnose diseases that weren't historically considered ultrasound-diagnoseable from this kind of detailed ultrasound.

I think combining it with gas chromatography/mass spectrometry of e.g. breath or blood/sweat/urine samples would also have the potential to be a cost-effective diagnosis method - lots of data, probably not all too useful for human interpretation, but would open the potential to walk up to a machine, breathe into it, spit into it, pee into it, give it a swab, and have it come up with an accurate diagnosis without invasive testing. If mass produced, the cost of something like this could easily drop below the cost of a typical doctor's visit. (I googled it and it seems like GCMS is already used for some diagnoses, but screening only for a few specific diseases rather than "throw ML at it and try to diagnose everything").

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 had the patient never been aware.

While there are many individual stories of full-body scans detecting early-stage cancer before it became symptomatic, there seems to be a general sense among doctors that implementing full-body scanning on a population level would lead to overall more harm than good. The thinking is that it is better to do regular targeted screenings for diseases that you're in a risk group for (e.g. colonoscopies, mammograms, cancer marker blood tests, etc.) rather than full-body scans.

I'm not a doctor, and I personally do find the idea of full-body scans very appealing, but I also know that if the scan detects a possible cancer, I wouldn't be able to just ignore it if the doctor tells me it's likely ok. Any time I felt any pain or any sort of symptom in that general area, I know I would worry about it. Maybe that's worth it for the potential life-saving results, but it definitely is a cost of this type of scan that needs to be acknowledged.

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 accurate to a degree previously unheard of in medical science it’s a boondoggle, and I can’t help but notice there’s no mention of accuracy.

Unfortunately that’s just basic statistics.

Even at a smaller scale, I was shocked to go to the hospital in China and literally the first thing done was a blood sample, scanned under about 30 metrics, took about 15 minutes after the same was take. The results were sent straight to my phone. That sample had some horrendous results, so I then skipped the queue and got straight to see a doctor who already had all my numbers up on screen before he spoke to the for the first time, meaning he could immediately put me on an antibiotic drip.

The problem is: Since we don't regularly full-body scan healthy people, we don't know how healthy, or say, still ok, looks like. This will create a lot of false positives and potential harm from unneccessary follow-up procedures and treatments.

There is this infamous DANCAVAS study [1] in which they ran cardiovascular screening on older population and found absolutely no benefit in doing so. Note that while the linked study claims there was a benefit to screening (reduced mortality in men aged 65-69), the apparent effect was caused by improper statistics (primary endpoint did not show benefit, only subgroup analysis, which however lacked statistical power to be reliable). And indeed, their follow up study showed that there was no benefit in the subgroup. [2]

Many a dollar is wasted every year on trying to prove population-wide screening prevents mortality or increases patients’ quality of life and every time we don’t cheat with statistics we get the same answer - population-wide screening isn’t effective.

1: https://www.nejm.org/doi/full/10.1056/NEJMoa2208681 2: https://www.escardio.org/news/press/press-releases/No-signif...

There's a ton of variation within medical testing and tons of different conditions affect test results in similar ways. VERY FEW tests (test classes maybe: biopsy, microbiology, skeletal Rö) can yield diagnoses in the first place. Most testing is used to support (not confirm!) and reject possible interpretations.

This non-invasive everything-scanner sounds more like science fiction.

false positives are a real problem

> With a big enough data set of [all kinds of bio values, including ones considered irrelevant for that disease] labeled with diagnoses

> > labeled with diagnoses

I know you’re not suggesting this is easy, but I can absolutely promise that the land of medical reporting, diagnosis and imagery is about a 1000x more complicated and unhinged than you might expect.

What does "solved" mean here? Identifying "the disease" correctly every time? On average identifying the right course of action? For each individual identifying the right course of action? Probabilistically or with certainty?

> pee into it, give it a swab, and have it come up with an accurate diagnosis without invasive testing.

Somebody should make a startup based around the idea of diagnosing diseases through eg. a drop of blood. Probably need a bunch of big name investors though

In the rest of the world diagnostics aren’t expensive at all and medical data is centralized already (blood, MRI are almost routine for hospital visits, all data stored in govt systems).

During Covid it was useful for improving protocols.

> walk up to a machine, breathe into it, spit into it, pee into it, give it a swab

Maybe take it out to dinner first?

Theranos2

> ... It starts by stepping into a shallow pool of golden light. > ... Together they act as both a choir and an audience

I think I'm not the target audience. I guess they are going to need to sign up a lot of people, to train on their scans + their medical outcomes. So the article is talking to people who will get enthused by it, which is more difficult after the question of 23AndMe data sale.

I’m a weirdo who vaguely enjoys my MRIs. I’m moderately claustrophobic, but they still don’t really bother me. And I love the warming feeling that makes me feel like I’m getting microwaved.

Almost nobody here is a doctor, and it shows...over diagnosis, over treatment, those are all terms that doctors learn about in medical school.

Image segmentation is a real problem, and achieving better precision is a good goal. The "golden" standard these days is likely https://github.com/wasserth/totalsegmentator, if someone can make it even more accurate, that would be very very good. But yet again, there are infinite amounts of variations in human bodies, which means even the best models focus only on segmenting known organs, and leave anything unknown alone.

This is more true than people realize. My wife and I got full body MRI scans.

Both showed "possible" medical issues. My though was "Great, I have a baseline, in two years I'll get another one and compare".

My wife on the other hand got a bit obsessed about her results and had what was probably an unnecessary procedure to biopsy something, which turned out to be benign.

I suppose you could argue that another way...better safe than sorry...but the stress that is caused by known uncertainty vs unknown uncertainty can be too much.

Not a doctor, but the overdiagnosis concern is at the intersection of three phenomena:

1. Imaging is expensive, just in dollars and time, even without analysis

2. Imaging is not without impact -- CT scans, especially full body scans, expose the body to ionizing radiation

3. Imaging is time-consuming

The net result of these means that full body scans are difficult to interpret. If a doctor given a patient complaint suspects a condition that is sufficiently non-specific that a full-body scan is required, then the scan will be interpreted through the lens of the known progress of the differential diagnosis. And typically these scans must be done without a healthy baseline, so minor findings in this context might have significant diagnostic power when combined with history or other findings.

But on a healthy patient, minor findings are very likely to be noise, because we don't have a great deal of experience with scans of healthy people, for the reasons above.

This technology, if it pans out, gives a way of inverting 1, 2, and 3. If every healthy doctor visit includes one of these scans, then the medical field gets experience interpreting them, and more importantly, when new symptoms occur, previous scans can be compared to determine whether a particular finding in the current scan is new or has changed.

If something like this became commonplace (and accurate enough), then it could be fantastic for research: enabling us to map out what variations are common and which aren't in a way that hasn't previously been feasible.

They've lost the plot, especially with the spa. And a billion scans a month is absurd.

Is this some AI hallucination post?

I had to check the date after seeing the headline, and again after opening the page. Thought it was April Fools.

Regardless, as a doctor and full stack engineer, I'm looking forward to learning more about their methodologies, their approaches, but I don't think this is going to be displacing MRIs or remotely close, based off the cursory initial glance. If their vision is to be able to provide end users with more actionable data with some kind of "low fidelity" medical imaging data that is somewhere above zero and or standard imaging and high fidelity modalities like CT/MRI, then this could be somewhat interesting.

Not a radiologist and not medical advice. Just my two cents.

Gives me the strange impression of a product that was vibe-brainstormed, vibe-engineered, and vibe-announced.

There are 100M pregnant women right now. If it works for just for the vanity use of seeing your baby grow (forget the medical imaging aspect) and can be as casual and relaxing experience as they put forward, then I can see such a spa being wildly successful.

This is an ambitious idea, but it’s pretty misleading to lump MRI, CT, and ultrasound into a single “body scan” category. They do different things and explicitly do not serve as replacements for each other.

Inventing new, affordable early detection devices is incredible, but being so misleading in their positioning is going to kill long-term trust in this and other new scanning tech.

First of all, this is incredible. Like genuinely insane. Also I bet you can do crazy things with that tranducer. If stuff like this keeps coming out, we have nowhere near enough compute

Neko Health has been doing this now for a few years. What I heard is that ultimately it doesn’t solve much (other than them privately collecting all your data) because there are lot of false positives and these false positives are deferred to the general healthcare system, which is a major bottleneck.

radiologist here - example images don't look great

It's obvious why they're doing this: there's a lot of money in healthcare.

What there isn't is good evidence that these full body scans actually improve outcomes.

FWIW, I tried the prototype. It's very real. I scanned my hand and arm. It showed realtime images of slices of my hand as I dipped my hand in the water. Really amazing IMO. I think this will be a game changer when it comes out. It's just so easy to scan yourself.

I think it's a bit odd to compare this to an MRI. The physics are totally different and there are things it fundamentally won't image in the same way because it's basically just ultrasound.

The approach sounds like something which appears in a few research articles from the 2010s (ultrasound computed tomography), although submersion to make the ultrasound transmission more efficient seems novel.

It's possible the "spa" approach is used because it's hard to achieve the level of cleanliness required in a typical health facility using a shared bath.

https://x.com/midjourney/status/2067422898407837797?s=20

Companies are awfully confident of advertising "revolutionary" ideas that don't even have a testable prototype. I too have a dream of world peace and eternal human prosperity that I would like to sell. Any interested investors?

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.

In the early years of X-rays, doctors found all sorts of patients with major organ displacement, and performed surgery to, for example, hold the liver or kidneys “up”.

It took a while to realise that textbooks since Leonardos time had drawn and based anatomy on (dead) patients lying on a slab. But X-rays were taken with (alive) patients standing up. So of course there was a lot of “your kidney has slipped!”

I fully support and applaud this kind of medical innovation (even if … why midjourney?) but we need to be careful of the medical term VOMIT (victim of modern imaging technology). At some point we need a human doctor to say “calm down, live your life, eat right, exercise right, and accept that somethings don’t need to be panicked over yet - come back in six months”

A problem with large scale "screening" is the explosion of false positives (even at very high specificity) and the follow-ups that those generate will overwhelm our current healthcare systems.

So any machine that does something medical must address this. Either that, or don't be medical. But then you might just as well tell people: "Move around a bit more. Talk to other people. Eat real food, not too much, mostly plants."

But we are always attracted to solutions that fix us in easy ways. The problem is that the issues are often with our behaviours, and those are hard to change. Or perhaps we are finding easy ways now with GLP-1 agonists and our future health and happiness is in drugs... But then why do we need this machine...

I watched the whole video thinking it was generated by Midjourney, the product, and that the announcement was related to fidelity in images/video around human anatomy. This seems like a very strange pivot for them indeed.

> You want as much data as you can get about your health

The device looks very cool, but I strongly disagree with the premise, and think this statement is rather misguided.

1. Most people who feel unhealthy don't do so because of a lack of data but because of bad habits around meals, exercise, sleep, social interactions etc.

2. If you measure and scan all the time, every blip above or below the normal curve will start generating anxiety. One of the most frequent pieces of advice for people waking up in the middle of the night is to not look at the clock. Information can be stressful.

Not sure why people keep posting links to X videos when they are available from at the official announcement post: https://www.midjourney.com/medical/blogpost

World's first trillionaire doesn't need more money or influence in destroying people lives, let's do a small step at a time and not use X.

I'm sorry, a billion full-body scans a month?

For what possible reasons? Are people going to be doing these things recreationally? Cause otherwise you're talking about scanning the entire world's population, including the very young, the very old, the mobility-impaired, and those without easy access to US-based facilities (i.e.... people who are part of the small fraction of the global population who do not live in the US), twice over, every 18 months.

What possible use could there be for doing this?

I recognize that the presser says the scanners will be deployed "around the world," but let's be real, this will probably be 80% US.

That video gave me ESB Han Solo carbon freeze vibes. Not sure if that was the stylistic intent they were going for. I guess there's a good chance those who worked on the video weren't even born when it was released.

Looks like an array of ultrasound probes which is fine.. how does this deal with bone obstructing windows? the example with an abdo is feasible and fine but you cant do that with brain or easily with heart /lungs

I'm giving them the benefit of the doubt and interpreting it in a charitable way because they sound earnest about it, this is incredibly ambitious and cool-sounding, and I wish them all the best. It's something that's some sort of pipe dream, a noninvasive diagnosis machine that is able to use certain generic measurements and then derive insane levels of data from it. We've of course seen Theranos, but the holy grail remains.

Of course, there's always the tradeoff between research data collection and access vs user privacy, and striking that balance is incredibly hard. To make anything like this even remotely feasible you'll need a shitton of data and have it fully available to your researchers as well, while somehow safeguarding individual users. anonymizing medical data is impossible without rendering it near useless. Hoping they can figure that out! (Also, with human bodies being so different from one another, combatting bias is probably an eternal challenge)

I have thought that extremely accessible, portable, non-radiation imaging would be revolutionary. Imagine every doctor - or even every person - had a handheld thing they could wave over your affected area to get a high res 3d image of the issue. Of course we have mri, xray, and ultrasound, but those are big and expensive. Obviously there are engineering reasons that is the case, but It seems like a concerted effort to make imaging more portable and accessible, coupled with ai to help analyze could bring about all sorts of follow-on health improvements. Your regular practitioner could check you for heart blockages, clots that lead to stroke, cancers etc as a matter of course. I’m not sure stepping into a golden vat of water is what I have in mind but medical imaging does seem like a possible area for drastic innovation.

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 discharges from ~3,999 other people (assuming the machine is maintained daily), I think I might have to wear protection and you must not lower me beyond my mouth.

But, if the claim is real, then yea, it could really help. So many health problems can be discovered early with ultrasound scan, only if it can be made easy, cheap and fast. Not sure about resolution and other specs, if it can be as good as CT, then more lives can be saved.

I don't really understand the connection; they went from image generation to medical scanning?

Super cool. Reminds me of Mary Lou Jepsen's (who did One Laptop Per Child) company Openwater, which is using some kinda infrared holography, also as an alternative to MRIs.

Supposedly they can be made lightweight and wearable.

https://www.ted.com/talks/mary_lou_jepsen_how_we_can_use_lig...

https://en.wikipedia.org/wiki/Mary_Lou_Jepsen#Openwater

April fools 2027 is gonna be nuts

We live in an era where the daily news stories are so crazy topping them is going to take some creativity

This is a full body ultrasound?

Medical I don't care about futuristic sounding stuff. Just show me evidence based and clinically useful testing.

Use AI and new scans to help sure but prove it works otherwise this could be another dead end.

After reading this first, it looked almost like a joke, like how Google used to do Google- TISP Toilet Internet Service Provider https://archive.google/tisp/install.html

Even now without Xrays it is very hard to really even see if there are blocks in your artery usuing ultrasound (Echocardiography alone). Ultrasound is used indirectly by measuring blood flow difference between stress and rest - not a spa session anyway. Looks like a prank really

This is very ambitious and commendable. They are putting their bootstrapped money into something incredibly cool and potentially useful. Regulatory will be hard, but perhaps they can do something like a class 1 device which doesn't diagnose anything / is used by physical therapists and they sell them to gyms. I also expect the resolution to increase rapidly. If they can convert profits from generating weird ai images into new medical technology thats a win. Good luck! They will probably fail but this is what ambition looks like!

I had to check whether this was some kind of an april fool joke.

It looks like a legit attempt. Wow. This is insanely innovative.

I've worked optimizing MRIs trying to make them faster and more accurate, they're amazing machines (distinguish white matter from grey matter in the brain is very non trivial), but super complicated and expensive. To me, the paradigm change that could come from greater accessibility and throughput to analyze all that data would be having longitudinal baselines (scans every x months), which right now only very few people can access, and for the same reason there's not a lot of data to build accurate models.

slide 28

https://s27.q4cdn.com/524696391/files/doc_presentations/2026...

Interesting choice to draw "inspiration" from the chambers of Niander Wallace, the main antagonist in Blade Runner 2049.

https://architectureofsilence.wordpress.com/2018/02/13/archi...

I used to work in ultrasound, and full body scans with the body underwater is definitely feasible and probably a good idea. Bit of a weird direction for them to take though??

Also there's absolutely no way that it will be as good as MRI. In general ultrasound imaging is shit. The main reasons it is used are because it is very cheap and completely harmless. The actual images you get are mostly just speckle. If MRI was cheap then nobody would use ultrasound. Full body ultrasound will definitely give better images because you have a wider aperture and can do fancier beamforming (probably "full matrix capture" and then beamforming in software; normally ultrasound probes do it in hardware). But it's still not going to be as good as MRI.

The exception to that is pregnancy - that is a super ideal case because you are imaging a nice clean interface in a fluid and there are no pesky bones in the way. Most of the body isn't like that at all.

Very unexpected but also really uplifting to see that they would spinoff a division to tackle this - it's ambitious. Obviously they've identified that the vertical is big enough and that they have the expertise or novel approach to tackle it, but i'm really curious to know how this came about internally.

This will be really interesting for brain imaging I think -- particularly for non-penetrating trauma (blast, crash, falls) in environments where MRI is unsuitable/unavailable, or where potential injuries are very common and thus per-scan cost is critical.

If you scanned every American Football player before/after a game, it would probably lead to an end of the sport. Similarly with boxing, and soccer heading practice.

Also would be super useful in war zones -- you can't MRI due to metal fragments, and can't CT over and over again due to radiation, and right now most of the guidance is "don't get injured again" and is broadly ignored. Being able to scan people near point of injury (or just after high risk activities) would be great.

(Obviously lots of other uses for this in disease screening, etc.; difficulties with ultrasound due to bone, gas, etc.)

Impressive vision. Excited to see how 'Ultrasonic CT' handles real-world clinical validation challenges.

Genuine question.

Outside of providing access to their core AI products at a free or discounted rate, what philanthropic initiatives are OpenAI and Anthropic pursuing to improve the lives of people in developing countries?. I can't recall seeing anything on their blog recently about it. Happy to be corrected.

So if it works: Awesome.

The spa approach is a little weird. FDA workaround?

Signal versus Noise ratio cried in her grave.

I won't have an opinion until Brian Johnson tells me how much younger this makes him.

Massive Theranos vibes.

You don't market medical imagery to the regular public and build a random wellness spa and talk about "shallow pools of golden light" if it actually works well. You write academic papers and sell to hospitals.

The tech may be good, but if you want me to trust you you shouldn't do what every snake oil salesman does.

This is pretty, but it's goals make it sound under-thought and somewhat silly. Typical "SF is coming to save the world" stuff.

> Our ambitious goal is by 2031 to have a fleet of over 50,000 scanners worldwide - with a total scanning capacity of a billion scans a month - enough to cover a huge percentage of the global population, or enough to give regular, monthly scans to a billion people.

> What This Leads To

> Whether or not our scanners are a service that everyone uses, to us, the most important thing is that everyone will be able to use them.

There is no way these will be available to a billion people. This is a luxury product for rich people, which is fine, but they cannot afford to run these for a billion people every month. Think of the infrastructure—both human and physical—to provide that. Think of the distribution of wealth across the world. Come on.

There are so many small, boring details that will have to be ironed out: many Americans won't fit in that machine, kids will not sit still, you'll have to clean them constantly (people pee in warm water), buying and re-tooling property for spas with zoning and licenses is arduous and jurisdiction-specific, etc. etc. etc.

What they are pitching and focused on (data, models, tech) is the fun part. It's not nearly most of the problem.

I'm not sure if they believe this (naïve, unserious) or if they don't (lying). Either way doesn't build trust.

Midjourney people are talented people within image generation but this is giving me some really serious theranos vibes.

I presume that Theranos had some talented people as well and some strong figures back at its time as well. It isn't the strongest of indicators.

It's been a really long time since I heard the name of Midjourney again. their name got a bit unheard of after LLM models like Chatgpt and nano banana started supported image generation, so I am unsure if this is being done to get known again or to pivot from image generation itself.

There are tons of factors which make me a bit skeptic about the whole ordeal.

Awesome work. The second video is great. I don’t know enough about medical science to consider viability and shortcomings, but I’m impressed by the dream. Keep cooking.

And even if the device fails, I’m sure the spa will be nice.

It's great to see money made in one of the few remaining unregulated fields like math and software applied to problems in the heavily regulated healthcare industry. There is an asymmetry in healthcare innovation that nobody ever got fired for blocking a good thing, but you can lose your job for approving a bad one.

I'm also following the very inspirational journey of the former Gitlab CEO who battles cancer by founding companies with his own money [0].

[0] https://sytse.com/cancer/

If this all works, and becomes widely available, I wonder if people would get a lot of health anxiety. Now they can see stuff that is normal, but strange or unexpected.

I’m no doctor by any means, but what if, as an example, an organ fluctuates in size, or composition, naturally. A medical professional would know these things, but a random person off the street might get stressed out and start to panic, or perhaps overcompensate with their diet or something.

I think more data is generally good, but data without context or insight can be problematic.

I would have expected a lot more focus on privacy from something designed to regularly and casually create detailed 3D images of humans. The word 'privacy' doesn't even appear in the text.

I can only applaud. Regardless of whether this device is possible, or economically viable, this is a brave move and a bold vision. Taking bigger risks is what what makes the advances possible.

This would be really cool if it comes to fruition and works in the way they want it to.

Given the source, I will treat it as nonsense science fiction until it’s built, functional and scientifically tested.

People on here really need to understand what the incidentalome is.

I think getting more medical data could prevent a lot of health problems, and collecting it in a relaxed and frequent environment could be interesting. This announcement is honestly just... a bit weird. They're talking about wanting to do a billion scans a month, but they haven't even mentioned what the ultrasound data can tell you about your health, nor have they showed a physical demo of the product. I think the latter is the most important part, does it actually work?

I prefer to interpret this in the most generous possible light.

Is it early-stage tech initially targeted at data-obsessed rich techies with unproven health benefits? Sure.

Is it also smart people trying to do something novel and hard by making an expensive and inconvenient diagnostic tool much more accessible, with the possibility of preventing (or diagnosing earlier) some terrible and deadly medical conditions? Yes.

I don't know why you wouldn't want to adopt lens number two.

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?

> But suddenly, you have a huge library of data about your health.

With "you" being a VC backed startup aiming for the next $1T IPO. What could possibly go wrong?

>"Like an MRI but at 100 times the speed."

Is speed the limiting factor of an MRI? Do we need faster MRIs? It doesn't seem like there's a backlog of folks waiting for a continuously running MRI machine. How does the imaging compare to an MRI? How about the cost? I think it's a really fascinating project but I don't understand what problems it solves.

So it's what, computational ultrasound? Why are they making it sound so much like they're going to steal my kidneys?

Will there be a way to use this scanner for people that are unable to stand up because of a disability or medical condition?

So how exactly is the scan counter going to hit their target of a billion per month? Are they scanning us while we sleep?

> Today we're gonna announce something a little weird and a little crazy, but also spectacular and filled with hope.

Why is that almost every LLM generated article sounds like a LinkedIn motivational post?

(this is not a rhetorical question, I would really like to know why, from all the writing styles, this is the most prevalent one)

Wonderful stuff, good job Midjourney.

An AI can be trained on body scans to detect diseases, tumours etc. Ideally this can be trained on real scans with real diseases but you could also train on synthetic data (synthetic bodies and/or synthetic diseases).

You can also focus ultrasonic waves to destroy (vaporise or cook) diseased tissue.

Here is the music from the video: https://music.apple.com/us/album/on-an-evening-at-the-lake-f...

I have zero medical knowledge, but assuming that they go through a good regulatory approval process, why is everyone so negative?

These are smart people trying something new. They are bootstrapped.

How is that not cool? Isn't this exactly the type of thing that should be exciting?

> As you descend you pass through a ring made of half a million tiny squares each the size of a fine grain of sand, and each capable of acting as both a tiny speaker and a tiny microphone.

Is this actually possible? It seems really ambitious to aim to open by the end of 2027.

This is next level "never let them know your next move" type of play. I hope they win.

Hypochondriacs everywhere rejoice

This is interesting & ambitious!

Not a physician, I wonder about the general efficacy of random scans vs more boring traditional things like bloodwork. That is: is there more clinical power in doing blood + urine labs monthly or body scans like this?

> But suddenly, you have a huge library of data about your health.

Why don’t they approach this as a regular medical product?

With this spa angle I’m worried about hidden motives; perhaps data collection is a major goal. Or maybe this tech is not reliable enough.

They should ask their LLM for fun things to do in prison! Or ask Elizabeth Holmes.

This is one of the creepiest "big AI" product launches I've read. I know it's becoming a meme, but that spa looks like something from a Black Mirror episode.

If they were just creating a new less-invasive and differently informative alternative to fMRI / PET / EEG / CT for researchers and doctors to use in hospitals, where experienced human doctors were given agency in finding out how best to use the tool and interpret the results (understanding all the caveats that go for full body scans, false positive rates and so on[0]), then that would be amazing, a tiny step forward for the human race. But packaged like this, eww.

[0] https://news.ycombinator.com/item?id=48580255

Imaging is not preventive care. Exercise is. Good food without chemicals is. Good sleep is.unfortunately these important parts cannot easily be monetized to provide stock options to the insiders/

https://www.medbridgenz.com/post/phased-array-ct-china

Remind me of this, radar based.

Always trump with the savior card when bad PR¹ starts creeping in.

¹https://news.ycombinator.com/item?id=48573332

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.

MRI & CT go from captured data -> displayed image via real provable hard math.

This seems to imply that there is an LLM layer involved. Which means hallucinations. No thanks.

There's a certain type of people the Midjourney folks are involved with in SF. They're high on their own supply. See also hacker houses etc

Midjourney out there making the pool rooms a reality

> Midjourney Spa

Those visuals look straight out of the Backrooms

This is absolutely a scam. Seems incredibly fishy.

"when you're looking for things, you find them" - my physician explaining excessive reliance on diagnostic imaging

Sounds like programmers woke up from a fever dream and decided they can come up with an idea and flesh out the details later.

Hell yeah, my AI image generation company is now running an alternative medicine AI MRI-alternative imagine spa. Hell yeah.

This looks like straight from a sci-fi movie. Crazy how fast things are becoming to look like alien tech. Pretty amazing.

Well that's certainly an interesting pivot, when Midjourney where set to announce hardware, who predicted this?

Can someone with expertise explain what kinds of medical imaging are theoretically possible with this kind of sensor?

Bravo for this vision. I wish them well and hope they succeed. I look forward to the first real technical reports.

Isn't this how MRIs and stuff already work, they just use waves with much more appropriate wavelengths...?

Part of me is super excited about this.

The other part wonders if this is the next clinkle.

MJ has shipped stuff before though so I’m optimistic.

This is surely trolling? "Fullbody Ultrasonic Computational Tomography" has quite the acronym..

So... Rampant point of care ultrasound?

Sounds good to me.

I have seen AI projects to convert a tomography into actual 3D models.

Not easily, but not an unexplored field either.

I thought this was a satire at first

If this can image a fetus in utero they're already cutting themselves off from India as a market

Can one buy it anywhere? At what cost? Would be cool for real-time biohacking and immediate feedback.

one nice thing may be way to enhance penetrative ultrasound eg smaller immersive ultrasound tomography in smaller dip tank hey stick your leg in this thinner immersive tunnel , e.g., extremity up-close immersion or trunk wrappers vs just wand-based?

I'm sure I read that 30% will be immortal there, but suddenly the blog post changed... :)

I just cried watching that intro video!

It's like, wow, us humans have a new tool to help us be our best!

Beautiful!

Thank you very much, Midjourney.

If some of my doctors were software engineers I probably would be dead by now.

Or mid-dead.

There is no way I am letting an AI image generator take scans of my naked body

How much is a scan going to cost? The video motions petabyte per scan? These types are scans (medical images) are extremely dense and large in size, storing short or long term images sounds like its going to be extremely expensive when combined with AI analysis, etc. Not to Mention the cost of operating a Spa is not cheap, especially if your buying real estate, and the cost of the machine itself.

Is this a dystopian Spa, where full scans cost 50k, and basic ones are 1-5k?

my first reaction: this pivot makes no sense at all to me.

my second reaction: maybe it does? did they hire up an army of physicists to make better diffusion models or something and they actually have people on staff who can do this?

I really wasn't expecting a hardware device from midjourney! Incredible!!

Need an update from Elon about what he meant when he said "Midjourney is not mid" and what he thinks now https://x.com/minchoi/status/1766131045177409784

AI is about to find out the difference between talking and doing. Exciting!

Good luck. Had a friend do a startup that was using similar algos to how Google Maps detect roads in satellite imagery to detect cancer in tissues. Actually worked pretty well - ended up dying in the super long FDA approval phase.

The images and description of the launch seem like they are behind where my buddy was 10+ years ago - so I expect a pretty difficult road ahead, between getting to where it's actually medically viable, and then stomaching the FDA process.

Where is the belly button?!

Why not have 5,6 rings at different levels and do it live in 3D?

Health data in the hands of some AI company, what could go wrong

Isn’t modern ultrasound already ultrasound CT, just localized?

For those who think this is a joke, there's no differnce between this concept and data centers in space concept, that's worth $2T. Both are not yet proven to work yet. At least they're not screwing the pubilc.

The math does not math

Are we at peak AI yet?

AI company announces AI thing using AI video mock up

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.

Welcome back theranos

At the surface level, this sounds very similar to Theranos's mission: create a non-invasive testing method that replace traditionally invasive/costly testing methods so successfully that it becomes silly not to gather and sample as much of your health data as possible, in the hopes that more data will eventually translate to better diagnostics.

Of course Theranos failed because they faked the testing tech (and allegedly also the test results) during their failed journey in developing their novel testing tech. Ostensibly, Midjourney is not going down that path, but I wonder why Midjourney thinks its brand is valuable when introducing this product? Because if someone were to accuse Midjourney of being the next Theranos, then Midjourney's fame for a AI-image generation service would slot in perfectly with a grift selling miraculously cheap body imaging tech.

20 or so years ago while working for a Startup in the Home-Health EMR Space - it was my job to develop and integrate the proper processing of incoming visit forms. After an outage, I performed an audit of our incoming forms and noticed some anomalies in the billing patterns of doctors belonging to one clinic. In other words, these doctors either had the highest concentration of extremely sick patients - or they were committing Medicare fraud.

At the end of the post mortum with the CMO, as I was getting ready to leave I decided to bring this to his attention. I’ll never forget the change of mood preceding the dressing down I received: “do not ever put yourself in a position to make clinical decisions.”

3 months later, the charting anomalies were so egregious that the CMO’s spot-checks led him to sit the medical director of that physicians clinic down for a chat. They were good doctors, but they were over-billing. A year and a half later their practice goes under pre-payment review, and four years after I wrote a script that noticed an anomaly - the head MD of the practice was sent to prison for 4 years after collecting millions of dollars in over-billed house calls.

I loved working in healthcare, and I still miss it to this day. I don’t know where I am going with this, but right now I believe there is a diagnostic technology out there that is being used in veterinary science or piloted in some other country that could save a statistic level of lives …. However, due to the fact that doctors practice medicine and we don’t, as a group they act as defacto gate-keepers (which they are entitled to be as clinicians), the best thing you can do is to incentivize them with money (like Obama did) with Medicare bonuses for using an EMR that logged CCRs and alerted the doc if the patient didn’t have certain vaccine information in the elderly.

If the first guy to wash his hands was seen as a lunatic, the first geriatric practitioner to give over an iota of their clinical practice to automate Rx dispersal while navigating poly pharmacology concerns will go to jail for a narcotics crimes or will be labeled to heretic until Medicare pays them all for it.

Anyone know the song that's playing in the demo?

So this is the purpose of building the backroom pools

Will they also sample a single drop of blood? That would be fitting.

ER Nurse here:

This produces images as good as an MRI- did I get that right? We already have those- they are relatively cheap ($2000 if you paid cash) and have already been scaled.

The only difference seems to be the speed of the test. But how long does it take to be lowered in and out of the water, not to mention the fact that you are soaking wet afterward. An MRI of the brain takes 15 minutes, only requires you to lie flat on a table, and then you can go about your day.

So we already have this technology- ultrasound is well understood, and free to perform, a bedside ultrasound is around $40k.

These are not medical grade images, so I am not certain how they will reduce medical costs by 50%- no FDA clearance means the images cannot be used for medical diagnosis. Meaning if it finds something serious, you will STILL need imaging at the hospital for the finding to be actionable.

Baby boomers are about to hit the healthcare system hard- and none of them will be able to tolerate being dunked underwater. This technology cannot scale to hospitals, the main consumers of medical imaging.

I appreciate the hopeful outlook, but creating a more elaborate and expensive way to have an MRI done seems like a bit of a fools errand, especially when 50% of bankruptcies in America are due to medical debt.

What are the metrics this will report? What information does it provide that is not already available via other existing means? What is the benefit of daily or monthly full body MRIs? What are you monitoring? How will this achieve the goals they claim 'cannot be overstated' but also cannot be enumerated...

Access to better imaging technology is not a barrier to obtaining medical care, there are imaging centers on every corner. MRI and ultrasound technology are already as advanced ad this, utilize the same ultrasonic technology to obtain images, and are already manufactured at scale.

I am really struggling to figure out the problem this is trying to solve

They will do everything but not release the API

Elysium is playing out right before our eyes

Interesting but many issues which have been listed here are valid. This is my take on the largest of them.

Preventive testing is not always positive. False negatives creates a false sense of security and false positives drives unnecessary medical procedures. For example, what if this instrument sees "something" and a doctor then follows up with a biopsy, x-ray or explorative surgery. These will all have negative side effects. There has even been a debate of if mammography is a net positive. I think it might be but I'm just saying that even such a thing is debatable. The question is not only if the these early tests find anything, its also a question of whether detecting it early changes the prognosis. Maybe its untreatable anyway? Or maybe it would still be treatable if detected later? And then comes the cost of course, is it economical to do these scans on a population level relative to the alternative cost.

Building medical systems is not for the faint of heart. I was part of a startup building a Micro CT system with the long term goal of using it to detect tumors in biopsies live during surgery (1 um resolution for cm-sized samples) without waiting a week for the normal analysis. We also started with non-medical instrument (general research) and we never got to the medical instrument before we ran out of money (we engineers were too bad at sales). But we did study up on the (European) standards quite a bit. They are not crazy in any way. Its simply that you follow good engineering practice BUT it is hard to move from building a non-medical system to medical system after the fact. The standard is a process standard so it basically says "You should have followed this process when you designed your product". And you need be real careful setting your Intended Use and showing that you have Verified and Validated that your system can be used for the intended use. So most likely they need to build one product now (Body Composition Analysis), use that for research and then set up their Quality Management System before they rebuild everything from requirements to risk analysis to test plans to hardware to software. 10 years is probably on the low side for this and quite the cost.

This is like the plot of the movie Elysium

Upcoming IPO or acquisition by any chance?

TL;DR: "Your body passes through a ring of underwater sensors, each acting like a dolphin, using its echolocation. The sensors send ultrasonic sound waves through your body from every angle. With enough waves, and enough angles, we form an image of what's happening inside your body."

Dolphins aside, is this basically a new angle on https://en.wikipedia.org/wiki/Ultrasound_computer_tomography?

they call it Promethean Spas... Zeus chained Prometheus to a rock where an eagle daily tore at his liver.

This is pretty exciting. I hope it works.

Is this company public? Can I short them?

They made the opening credits from Westward.

Congrats!

I personally have been dealing with an elbow injury for over 3 years. I have been to all the known places in the bay area and shown it. One surgery, countless doctors (some who took MRIs), and many physiotherapy sessions later the problem still exists.

I believe if a willing doctor takes images all over the elbow, and looks carefully, they will find the cause. But they aren’t willing.

Disappointed with the healthcare here, I for one, would love a solution that takes comprehensive data of my body and tell me what’s going on.

THERANOJOURNEY Why put a person in A Wallace Corp. water tube thing when you can deduct all that from the drop of blood?

You don't need to build a perfect med spa, you only need to control the patents of the key pieces of a med spa.

This is nothing more thab a prophylactic patent grab to stifle competition and progress in this space for the next decade and/or hoover up patient data behind a paywall where they will gladly lease the weights and bias cure to you own disease back to you in the form of a subscription.

But why? It doesn’t say why?

1) what?

> It starts by stepping into a shallow pool of golden light. You then begin to descend into the water. Your body passes through a ring of underwater sensors, each acting like a dolphin, using its echolocation.

...what. You descend into water and it scans your whole body? How do you breathe? How do you come out the other end?

Have they actually invented some type of novel scanning technology, or is this just AI slop gone wild?

Who needs a head anyway?

This is the most insane thing to happen to medical imaging

To understand Midjourney Medical (MM), think about current major options: - CT/X-ray: harmful if done too much && can't do for pregnant women - MRI: slow, have to stay still, no metal - Ultrasound: really low fidelity

Midjourney Medical is fast, high fidelity, and perfectly safe!

The holy trifecta.

Insane vision. Insane work. Hats off to the team

Strong theranos vibes

i want a full body scan from the friendly discord app.

This is an old April fool’s post guys, don’t waste time arguing about it

How are people possibly taking this seriously?

> That, collectively, we can begin to change our relationship with our bodies and start to ask questions like: if we can catch things early, can we change our lifestyles to correct them?

We can already ask this question...

> And seeing our bodies change over time, alongside our actions, how much can we improve our health, our minds, and our lives?

Again, we can already ask this question

> We think it's completely possible that with enough early imaging in the future, the world could avoid 30% of all deaths and 50% of all healthcare costs. The cultural, physical, and mental health benefits of all of this are hard to comprehend, but also hard to overstate.

What? I have no idea what is meant here by "hard to overstate".

Thanks for including the "megabytes per second per dollar" unit breakdown, I didn't understand the first sentence at all without that!

> And we live longer, healthier lives, better lives.

More AI slop

> When you step into the water, you’re standing on top of a platform. The platform is connected to rails and begins to descend into the water - an elevator gently lowering you at around 2 inches, or 5 centimeters, per second.

More AI slop. You'd only be done in 60 seconds if you're exactly 5 feet tall

It has been said in this thread that we shouldn't scan healthy people because false positives. That's a good point. But I also think we are still looking at the small picture: catch diseases.

The slightly bigger picture is to prevent them, and there early warnings can help a lot.

At a yet slightly higher level, some people think that we are about to enter the age of superintelligence. That's a separate debate but it's not something I would disregard entirely. In an age of superintelligence, our goals and tools for healthcare can be different. I'm very much doubt that the medical establishment and we as a society will embrace a world where each person has some model of their metabolism running on some hardware and being updated and monitored 24/7, but this is already a reality in many industries where it is called "digital twins", so maybe this is something you'll go for if you are a trillionaire.

Zooming out and flying higher, the goal is of course to be young forever and let your body stay away in state space from most diseases. Is that something superintelligence can do?

It's a plot twist no one expected coming, to say the least.

HN is so negative, they are genuinely making a interesting move instead of just generating BS images, they are actually trying to make something that could benefit humanity. Whether they succeed or not, who knows, but great that they are trying.

Dipping into the pool of piss is a curious design choice.

we're hitting the hype peak shortly

They'll get so much money, all the 60 year old billionaires in SF are so desperate not to die.

What the hell is wrong with companies these days?

> you want a technology optimized for getting as many “megabytes per second per dollar” of information about your body

No, I fucking don’t, Chad, and you’re weird for thinking that I do.

> "Fullbody Ultrasonic Computational Tomography"

FUCT, huh? Genius marketing move.

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.

This is the most "getting high on your own supply" I have ever seen.

What the hell are they talking about. This is no way real and a late April fools joke right? Right?

This is not the AI branding I would associate with medical technology.

Oh hey look, I have the spleen of an elf! And my bones have a really nice cottage motif now.

The app known for making shit up (as in: that's it's whole shtick)... Getting into medical advice?

We are at pets.com stage of AI bubble. This time the business model is LLM-generated, though.

Yesssssss, AI overlords put me in your dolphin technology powered human deep fryer.

This looks remarkably dystopian.

This is kind of cool shit that makes Silicon Valley great. Thanks for switching it up!

I wish them all the best and hope they succeed, but can’t help but suspect they’ve fallen into deep LLM psychosis. Even if you assume they can build this thing and it works as described and then get past all the regulatory hurdles, the scale of infrastructure they’re talking about is enormous.

Theranos 2.0?

The scans take 60 seconds, but at their stated numbers each machine would need to do a scan every 30 seconds 24/7. At this point I stopped reading because I don't have time to parse slop.

This shit is immune to parody, it’s the most California thing to ever exist. “We’ll fix your health problems with an AI spa”. A spa. Give me a break.

At least it isn't yet another AI wrapper product and it is a bet on useful hardware.

What the actual fuck

Medical Doctors: scans on healthy patients are not a good idea

Tech bros: hold my beer…

Assuming it all works 50k scanners running nonstop at 60 seconds a scan is 2.1 billion scans a month. Assuming they aren't lying/exaggerating about anything, and assuming there is no downtime/setup/etc. in between. In other words, reeks of massive bullshit.

spa as a regulatory bypass is clever, body comp data first and diagnostics later. 500k transducers doing full body ultrasound in 60s is a massive hardware bet for an image gen company tho

I assume this is like Theranos until proven otherwise.

But hey if not, actually cool.

I just want more people to take on crazy big bets.

Wait is this just an ultrasound tomographic scanner?

Any which way we can get to the Torrent Nexus fastest <thumbs up emoji>

Amazing. Unless you’re in a wheelchair or can’t stand.

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.

Hmmm… such a slow rollout. In this age of AI assisted development I would expect them to move faster. I would be concerned about Chinese tech replicating this and then selling it to competing wellness spas.

I guess some type of software platform would add some competitive distancing?

I get the benefits of regular scans although I also know that they tend to catch a lot of otherwise benign tumors that can cause a lot of stress.

It's interesting to see an AI company need to pivot so hard in order to find revenue. I guess this means there is very little easy money to be made as more and more models get created, shared and downloaded by others.

Just an crazy idea, but if I were an unethical AI company that wanted to make better AI generated images of people's bodies, I might be tempted to offer very cheap full body scans in an unregulated fancy looking pop-up "med spa" where I could just use my AI to generate fake but impressive medical-looking pictures and then tell everyone who came in the results were inconclusive and they should get themselves checked out by an actual doctor in a hospital "just in case".

Maybe I'd even underpay a few people in developing countries with experience reading ultrasounds to check over the images so that if the humans detected anything suspicious I could give my sucker/client something more specific to tell their doctor about. That'd probably get me some good PR on social media as people post about how my fancy spa found their massive tumor or whatever.

Then I'd use their body scans as training data for my image generating AI. The waivers I'd have people sign to use the service would make sure that I wasn't at risk of any thorny legal issues from the use of all those images for training unlike the rampant copyright infringement method I'd been using previously and would also make sure I couldn't be held responsible for anything my scans found or didn't find.

Less cynically, maybe this thing will be nothing at all like that and one day it'll end up being used by real doctors in actual hospitals and save a bunch of lives or something. Who knows.

Reply on news.ycombinator.com