Dr. Unk

@forallcurious I wouldn’t either

🚨: Norway shipped over 1,000 kg of food for its world cup team because they didn't trust U.S. food

@jasonryanmd Great place

Me: Whole body scans in healthy people have no evidence they prevent disease. Twitter: OMG why do you want people to die!!!!!! Also, Covid! I love this app.

@Evan_ss6 Yep this definitely happened

Response from radiologist who read MRIs for over 4 decades

@DrPhiltill What are the counter arguments

I’m already totally bored with the skeptical takes on the Midjourney ultrasound body scan tech. All the arguments were made in the first half tweet and since then it’s been just repetition and refusal to address the counterarguments.

@specialkdelslay God I hope so, will be nice to retire

@CRA1pf may u be replaced by a robot 😊

wondering if doctors can stop posting their copes on the midjourney scan thing three types of people will even be interested in a scan at all: 1) health nuts who want to analyze all health data for themselves & take a holistic approach. they won't be bothering u. who cares. 2) hypochondriacs, which is who you really fear here, since they will subject themselves to needless invasive tests & procedures for their made up malady. those exist now. ur worried that will scale & u will...make more money? who cares. 3) someone who knows something is wrong but can't figure out what. for those patients, this type of tech reduces the barrier & time to treatment, actually life/death for such cases. so this type of tech is good for them & good for u since "doctors" lost the art of diagnosis decades ago. basically any doctor posting this type of cope makes the assumption that most ppl are #2 when actually most ppl are ambivalent or #3, which is why so many mistakes in medicine happen and ultimately makes this tech necessary. lol, doctors owned again

@NoContextHumans What they mean when robots will replace human jobs

This machines level of confidence is amazing

@lvjin1993 The rusted knife though

虽然它已经尽力伪装，但依然逃不过吃货的眼睛！

@prompterminal The images are quite good you say….

Not a doctor etc to comment on the safety issue, but again it's well known Ultrasound is non invasive. It moves particles to generate waves is non-ionizing unlike CT. MRI is non ionizing as well and it is in a similar safety regime as ultrasound. That said, I don't feel like there's a revolutionary AI component to enhancing the hardware sensing part of the scanner. The imagination wants to go there. As I said, if you're imaging, you're relying on the fidelity of hardware and the physics of capturing the ultrasonic signals, you can't impose new data with generative AI on what you grab from your transducers (it would be hallucinatory, unethical). What makes this scanner special is the RING system of array elements that sees every point with multiple samples. If you can resolve the weakest point (the highest depth being in the centre of the body) due to 360 degree redundancy afforded by the ring, then you can resolve every other point fine. Looking at the full body image slice from their 2024 submission is quite good and the post processing analysis can be significantly enhanced by AI, which is where I believe Midjourney comes in, in other words, only after the hardware has done its (very nice) work.

@moreisdifferent Do you think those Us tomography images have diagnostic utility

Whole body ultrasound. A big paper came out about this in Nature Biomedical Engineering about three weeks ago. nature.com/articles/s4155…

@russelljkaplan What?

Besides full body ultrasound CT, just wait until solid-state nanopore sequencing reaches industrial maturity and we get cheap, abundant at-home DNA/RNA testing. You'll know exactly what's causing your cold, what kind of mold that is, which antiobiotic to take, what's wrong with your micriobiome... The future is gonna be great.

@doodlestein I’m all for new tech, but you MUST understand the inherent limitations of the imaging modality. US cannot be used to screen every organ system

When you see the doctors coming out in hordes to confidently argue against new scanning technologies powered by advanced math and statistics, just remember that the vast majority of them are borderline innumerate and can’t even understand what p-values are:

@SkyeSharkie @midjourney It’s precisely because we DO know how bad ultrasound is since we know the inherent limitations, just stick to posting on X

I don't think people acting overly skeptical about @midjourney's medical device understand just how bad the existing ultrasound imaging field is. Have you ever heard of a Fibroscan machine? A fibroscan is a $25,000-$35,000 dollar device that doctors have to spend 15-40 minutes manually using to produce a NUMERIC result from an ultrasound, not even an image. Because of how much manual work it costs, the use of the machine runs from 200-2000 per session by hepatologists. Midjourney medical doesn't NEED to compete with MRIs or CTs to provide an infinitely more accessible and affordable device/experience to contemporary medicine.

@chrissyfarr Knowing that would not have helped the anesthesiologist with your block, sorry

I got a whole body MRI and discovered I had mild scoliosis. Not an earth shattering finding. But when I got a spinal block for my c section a year earlier, it took the anesthesiologist quite a while to find the epidural space. I didn't know I had scoliosis then. It was very painful. This is the exact kind of mostly "inconsequential" finding that many point to. But it would have been nice to know for me as a patient. And I paid out of pocket, so there was no added cost to the system for me to do it.

@DrAdamBat Yes yourself included

Unfortunately doctors have never been good at understanding new technologies

Ultrasonic CT false positives are one thing. I’m more worried about the false negatives. Lot of misinformed folks will be quite devastated when they find out US is useless for almost all bowel pathology, plus lungs, brain and bone/marrow tumors to name just a few….

@rheum_ai Only 1-2?

I think that tech people tend to underestimate the complexity of most medical/biological problems by 1-2 orders of magnitude.

@jasonljin You have no stake in human lives so your opinion is invalid sorry

doctors are melting down over midjourney's medical imaging tech, despite it making knowledge about your own health cheaper + more accessible it's very clear where the public stands and who can't read the room over their elitism about knowing best as a sovereign individual, you deserve to access your own data, understand risks & make informed decisions about your health

@perrymetzger Whatever you need to tell yourself to sleep better at night

I’ve seen this trope posted by a lot of doctors in the last 24 hours. The claim from doctors is that Midjourney’s cheap full body scanner is bad, because people would get treated unnecessarily for harmless conditions, and that would increase death rates. Now, I have a lot of skepticism about Midjourney’s announcement (a lot of skepticism) but I think that the doctors are failing to look in the mirror. What they are saying is, in effect, that they cannot be trusted with having more information about patients. That, if you give doctors too much information about a patient’s condition, they may kill the patient by treating them unnecessarily. This isn’t a problem with inexpensive full body scanners. This is a problem with doctors and medical practices.

@heacockmd @midjourney What do doctors know anyways? - the riff raff majority on X

Apparently, yesterday @midjourney pivoted from AI image generation to...whole body ultrasound , presumably AI-augmented. I spent some time trying to find hard data and did not come up with much beyond the video. Some thoughts based on the X reactions today. 1) "Nobody's ever done this before." This seems to be a variant on ultrasound tomography, with Butterfly sensors arranged in rings. Ultrasound tomography is not new, with commercial systems available for breast imaging. The system proposed here seems very similar to Garrett et al 2024 (pmc.ncbi.nlm.nih.gov/articles/PMC11…) which provided fuzzy images of the abdomen and extremity. By collating sound wave return from the ring array the system can attempt to minimize artifact from bone and gas. So, we have known this is possible since 2024. 2) "So easy for the patient." The system requires the patient to submerge themselves in water. For commercial breast UT, this simply requires laying on top of a shaped tank, but not going fully in water. As some people have difficulty lying on a DEXA or CT scanner (the latter of which can image in seconds) I will be interested to see how this is received by patients. 3) "This will revolutionize medical imaging." Ultrasound is limited by bone, air (lung, stomach, bowel) and depth of penetration. In the abdomen, this system can "see" around bowel and spine by adding together the full set of images. There is no workaround for the head or lungs and you'll notice that's why they didn't offer any pictures of those areas. It also means it won't be great at screening inside the stomach, intestine, or colon. I also note the volunteers appear fairly skinny. Ultrasound is always more limited in heavier patients. 4) "But AI can fix it!"...not really. Current DL-based reconstruction techniques require at least some undersampling of a region in order to reconstruct the image. You'll get a lovely picture of the outside of the skull. I can AI-upsample a fuzzy photograph but that doesn't mean what comes out of it actually existed. We have a variant of this issue already with MRI DL reconstruction. 5) "But this is better than MRI in the 1970s!" Yes, true. But the competition is not 1970s MRI, it's modern CT/MRI/US and most especially low-field MRI. For brain, for example, low-field MRI is already diagnostic quality and doesn't need shielding. A low-field scanner costs 50k and can be used in an ICU or put in a van. Why would I send a patient to get an experimental full body US when there's whole body MRI available that's already diagnostic quality? science.org/doi/abs/10.112… 6) "The FDA has no idea how to regulate this." This one made me laugh. There's an entire set pathway for this. Commercial ultrasound tomography already exists as an easy reference of a similar technology in the application. If they haven't submitted to the FDA, it's because they plan to try at a later date, or because they're not planning on submitting it at all. Do I think this is new and exciting? Yes. It looks like it's going to be great for body composition, and I do think there will be improvement in the future. Is it currently medical-grade diagnostic quality? No, not based on what they showed us. Apparently in-person there was a great hand demo. I don't see why that would be an improvement over routine US or MRI in visualizing hand soft tissues. To quote @khakrish: "It feels like all the same problems as full body MRI with the added problem of an unproven imaging modality and no FDA clearance."