Eric Topol highlights how a Midjourney-generated full-body ultrasound scanner concept runs into hard physical barriers, since ultrasound waves cannot cross the adult skull to produce usable brain images, leaving any claim of complete coverage unrealistic even if the device could handle other body sites effectively.
On the @midjourney "Full Body Scanner" A nice idea that could add to our imaging capabilities, especially building on the power of ultrasound. But it's not full body. You can't use ultrasound to image the brain. My published smartphone ultrasound medical selfie in 2018 https://www.science.org/doi/10.1126/scitranslmed.aaw7610 Moreover, there are the same concerns about incidentalomas as with full body MRI. And we've yet to see a publication.
This longstanding acoustic mismatch between bone and soft tissue means standard ultrasound has never delivered detailed adult brain scans, a constraint Topol underscores by referencing his own earlier handheld imaging work that deliberately skipped the head.
The concept carries no peer-reviewed performance results or clinical trials, so its practicality stays untested and the incidentaloma risks of any full-body approach remain unaddressed beyond the core imaging flaw.
Positive users praise the sober expert analysis of Midjourney's full-body scanner concept and its ultrasound limits, while negative users insult the researchers and dismiss the project as hype or grift.
No Digg Deeper questions have been answered for this story yet.
@EricTopol @midjourney But it is full body?
On the @midjourney "Full Body Scanner" A nice idea that could add to our imaging capabilities, especially building on the power of ultrasound. But it's not full body. You can't use ultrasound to image the brain. My published smartphone ultrasound medical selfie in 2018 https://www.science.org/doi/10.1126/scitranslmed.aaw7610 Moreover, there are the same concerns about incidentalomas as with full body MRI. And we've yet to see a publication.
@EricTopol @midjourney This is published already in Nature Biomedical engineering: https://www.nature.com/articles/s41551-026-01660-4
@EricTopol @midjourney Same gut feeling this morning. First post I saw and said great. Then saw dozens of hype posts without any understanding of physics and clinic which irritated me.
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 (https://pmc.ncbi.nlm.nih.gov/articles/PMC11275691/) 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? https://www.science.org/doi/abs/10.1126/science.adm7168
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."
@heacockmd @midjourney Interested to see if the proposed means of improving image quality well help deal with echotexture (for liver parenchymal disease)? echogenicity (for hepatic steatosis)? determine cystic from solid lesions? Very interesting/exciting times. Definitely watching this space.
@EricTopol @midjourney Is it using this tech?
https://www.nature.com/articles/s41551-026-01660-4
@heacockmd @midjourney This was a fantastic breakdown. Thanks for writing it. The perspective from an expert was needed here and appreciated.
@heacockmd @midjourney If this is slated for near future, that means there should be residents/fellows/consultants training as we speak to use the tech by then?
@EricTopol @midjourney You’re right. It can’t do the brain so we should just dismiss it. Interesting take
For anyone that made it this far, I am actually generally pro-whole body screening, love novel imaging techniques, and my research is in AI for ultrasound, MRI, and mammography.
If Midjourney gives us a whole bunch of actual data would love to reconsider this post in that context.
@heacockmd @midjourney Awesome summary, thank you Laura!!
@heacockmd @midjourney The real question/elephant in the room->who will read (validate/put their name on the report/risk their professional/medical license for) the images?
@EricTopol @midjourney - @midjourney a Powered-By-Butterfly Partner -
Midjourney built the machine.
NVIDIA provides the compute.
@Butterfly provides the eyes.
40 $BFLY ultrasound-on-chip sensors in every scanner.
Ultrasound has a tradeoff between spatial resolution and depth. Better chips may improve spatial resolution but won’t fix depth. You can crank up the power and punch through bone/increase depth but at the cost of cooking the tissues, so there’s no value there.
Sound waves, X-rays and MR are complementary but not interchangeable. I would bet on low field MRI before this — it’s proven, has much better resolution and signal-to-noise ratio, no depth or air issue. But happy to see what the company develops next.
@EricTopol @midjourney Preprint (possibly related) from 2024 https://pmc.ncbi.nlm.nih.gov/articles/PMC11275691/ (Preprint does not require a journal sub)
Final https://pubmed.ncbi.nlm.nih.gov/42032040/
@heacockmd @midjourney “If Midjourney gives us a whole bunch of actual data”. That’s it! Come on Laura, we have a COLORFUL AI GENERATED VIDEO, isn’t enough? 🙃
@heacockmd @midjourney Legitimate question, CET, Generative physics etc. I think the path BFLY is taking with the chips in time will lead to a convergence where these type of systems are just as well as the MRI, just my .02 but I’m not a Dr, or physics, just a tech junky.
@heacockmd @midjourney Nice, this is a pretty sober take. Many doctors (even with a background in deep learning like yourself) seem to have knee jerk skepticism.
@JusDayDa @EricTopol @midjourney Thx for sharing. Cool tech, but less impressive image quality wise that the axial section of the femur they showed..
@EricTopol @midjourney It’s destined for the griftosphere
