“There are approximately seven scanners per million inhabitants and over 90% are concentrated in high-income countries. We describe an ultra-low-field brain MRI scanner that operates using a standard AC power outlet and is low cost to build.”
This is fantastic. What a sentence to get to write.
Yea, the way they turned the bleak situation into something sanguine is fascinating. I still remember how expensive is MRI. I used to earn like $150 usd and the cost was around $200 usd. I hope such inequality shall perish in the future, so people can at least get proper treatment.
I'm curious what makes them expensive. In Japan they are basically free (covered by national insurance for which the price is low). I believe at one point Japan had the most MRI machines per capita. I think the government just decided they were worth while and got a bunch where as in the USA they were seen as a money source and they generally charge $1k to $10k ?!?!?!
I'd love for the expensive ones to be disrupted. The dream is we get some attachment for our smart phones and turn them into Tricorders.
I worked for a medical company that did RF tumor ablation. In Japan we sold a machine that cooked small tumors as an out-patient procedure, because their easy MRIs would spot them early. In the US, we sell more complicated machines that work on bigger tumors because we find them later here - when they get too big, you have to be very careful not to damage surrounding tissue.
I live in a Russian city of 100k people and there are at least 3 medical MRI machines nearby that I visited, of a total 8 offers that maybe share the machines (though likely not), all of them of 1T field strength or above. I can get a brain MRI this week for some $70, or a full-body MRI (the most expensive as per the price list) for $400. If anything, these services got some 30%-50% cheaper in the past decade. Barring some African hellhole, the argument to scarcity or expense of these machines is complete and utter bullshit. It's just that HN is America-centric, and American healthcare is a cesspit of waste and corruption.
The images are better that I expected.
The ‘FLAIR like’ image is not particularly FLAIR like. FLAIR are nicer to look at when fat saturated (not everyone agrees with that), but that’s probably not feasible at that field strength and adding scan time would be a problem on these long sequences.
Voxel sizes of 2x2x10 are pretty terrible resolution, but if the alternative is nothing, I guess that’s ok.
The static field is so low, I’m impressed it works at all.
This is precisely what saved my father's life last year.
16 years ago he had some kind of brain cyst. Totally benign. But as a follow up, the doctor ordered yearly MRIs, much to his annoyance.
Last year those yearly routine MRIs spotted a brain tumor- before it had time to get dangerous or cause any damage to him. It was growing quickly though and was right near his eye. Quick surgery got it out.
I want to live in a world where everyone has access to that.
PET scans are limited in resolution when you get down to the sub-5 mm or so range due to scanner technology and fundamental limits of the physics of positron/electron annihilation & photon emission.
A typical MRI (i.e. alas, not what this article is describing) can usually resolve something at that size and identify characteristics like diffusion restriction or contrast enhancement which can confirm metastasis.
Also, in the brain, PET scans (at least the most common, FDG, which is based on glucose) are extremely limited in utility because of the baseline high glucose metabolism of the brain, which makes it hard to distinguish from the metabolic activity of a tumor.
The flip-side of that is that PET is vastly multiple orders of magnitude far more sensitive than MRI. So while PET may not be able to localize as well as MRI, it can detect smaller things if the targeting of the radioisotope is good.
FDG PET/CT is not used to stage intracranial metastases due to background brain activity significantly reducing sensitivity. You’re likely only detecting lesions 1cm or greater in the brain, or ones which demonstrate low metabolic activity and appear dark.
MRI is much more sensitive and specific and is the standard of care for staging in my practice and as per the NCCN clinical guidelines. I haven’t been to any institution or heard of one where PET is used for staging of brain metastases.
I probably wasn't clear in context because different meanings of sensitivity seem to have crossed paths. I was referring to the physics of signal detection in MRI vs PET, not clinical disease detection. MRI only detects signal from an extremely small fraction of the protons in the sample. You have no chance of detecting individual protons. MRI makes up for that with brute force of proton numbers in tissue.
Modalities like PET can detect events from a far greater fraction of the isotopes present. But they are limited in spatial resolution by the physics. This is why MRI is said to be a very insensitive modality.
See for example the discussion about MRI vs other modalities here:
which notes that MRI has a sensitivity around 10^−3 to 10^−5 mol/L whereas PET is many orders of magnitude more sensitive at 10^-11 to 10^-12 mol/L.
So what I meant was if there's an analogy that you're looking at a skyscraper, MRI can "see" which which rooms have floodlights turned on. PET could detect whether there's a single candle burning somewhere in the building, but it can't tell you which room it's in.
I am unsure of the exact state of play but believe that small mets (eg a few mm in size) are better seen with MRI. MR is probably easier to get than PET too.
There are usually a few radiologists lurking here and they would have better knowledge than me (I’m an MR tech).
That's absolutely true. We work with a lot of technical founders who are turning their research into a diagnostic medical devices. One of the first questions we always ask is: how will the information produced by your device help clinical decision making? More data is _nice_ but if it doesn't alter the course of treatment, it's pointless. Sometimes it's okay if the doctor doesn't know if the problem is A or B if the treatment for A and B is the same.
I’ve spent a long time around scanners and re-read this book before helping students. It’s remarkable easy to lose track of the fundamentals, though maybe that’s just me.
(vastly simplified) MRI basically functions on two fundamental mechanisms--"spin echo" and "gradient echo". Spin echo signal is described by T1 and T2. Gradient echo signal is described by T1 and T2*. The difference between T2 and T2* relate to local magnetic properties of the tissue which is called "susceptibility". Blood contains iron so its presence alters T2* and this is exploited clinically. A good example of T2* imaging used clinically is susceptibility-weighted imaging (SWI).
T2* effects increase with higher MRI main field strength. From what I can tell so far these ultra low-field scanners have to rely on spin echoes.
These are different MRI sequences that are weighted differently to produce a specific contrast that show different characteristics of the tissue that is imaged.
I really liked ‚MRI made easy‘ as an introduction to MRI physics. Just google it, it’s a free Book
I think it is amazing that they're getting decent ADC maps - diffusion imaging is fundamentally about measuring how much the image gets dimmer (due to diffusion sensitizing gradients), so it's always running up against SNR limits. This is so darn cool.
For some reason it reminded me of the crazy project where some team used the earths field as the static field and just added gradients and the RF stuff.
I can’t find the article I remember but this project looks similar and scans a capsicum rather than an apple.
I am surprised that there isn't open source alternatives to Simulink, Stateflow etc.
One reason Matlab is popular in academia and industry is because someone who don't know C/C++ (mechanical engineers etc.) can use something like Simulink to program real-time systems on microcontrollers and FPGAs.
There is Xcos, but IIRC it's pretty poor compared to Simulink. Honestly Simulink is super niche. I'd guess there are 10 times more MATLAB users than Simulink users. Not surprising there aren't many alternatives.
I think a bigger reason MATLAB is popular is that it works really reliably, it is very well documented, it has a ton of complex algorithms and functions built in (or available in toolkits at least) and the interactive GUI works very well.
There isn't anything anywhere that comes close to MATLAB's plotting abilities. And scientists do a hell of a lot of plotting.
> The lead author, Dr. Craig Bennett, wanted to get something fresh, so he headed in to the grocery story first thing in the morning. At the fish counter, he spoke the words that will echo down the centuries as a testimony to the dedication and drive of neuroscientists throughout the ages:
>"I need a full length Atlantic Salmon. For science."
That reminds me of the day that I needed a strong lightweight cable for a silica-fiber melting/drawing apparatus. After some puzzling, I realized that bicycle shift/brake cabling would probably be perfect for the task.
I'll never forget the puzzled look at the bike shop -- "What kind of bike are you putting it on?" "I'm not, I just need some brake cable for a science experiment...." As I recall, I think we finally settled on some precut cabling for a GT Zaskar of some kind.
Similar things came up the day that I needed a valve that switched faster than our dedicated micro-switching valves. A similar light-bulb went on, and I went down to the nearby auto shop for a fuel-injector.
"What kind of car do you need it for?"
"I don't, but there are a couple of different valve-switching protocols, some that latch open and others that accept straight TTL at reasonable currents. I need one of those."
That experiment was brought to you by an injector for, I believe, a Dodge Caravan, and later, when I needed another, an injector for a Ford Mustang. Fuel-injectors are really good valves.
Some of the automotive stuff is really great to get started. Was working on an agriculture robot and needed a good way to detect a level of something. In short a IP65+ hall effect sensor that can get wet and dirt no problem.
The solution was a $12 ride sensor from a Cadillac SUV of some type. Worked perfect!
I had a friend automating a production line and he needed to detect the level of peanut butter in a vat. He settled on an ultrasonic device as basically anything else ended up caked in peanut butter. It was an impressive setup, all done in Arduino.
I wonder if its practical to DIY your own production line automation today with Arduino. Like if I had a simple product, could I buy stuff off the shelf and integrate it myself in my garage and end up with a little mini-factory? Exciting to think about.
I obsess over this concept. I am a robotics engineer and my dream is local manufacturing with small DIY machines. But it's a lot of work! When I have a little more time I want to teach community robotics classes and build machines that makes shoes and hot food and other important goods, designed and built as a community. I designed a cheap large format laser cutter [1][2] and now I am designing shoes that can be made with a 3D printer, the laser cutter, a sewing machine, and some basic tools. [3]
> I wonder if its practical to DIY your own production line automation today with Arduino.
Computation is rarely the problem.
It's all about sensors and actuators.
One of the best college projects ever was to make a "drink pouring machine". You have a half-dozen bottles of various alcohols and other liquids, a circular table, and a glass. Now, pour a martini. Now, pour a gimlet. etc.
What a nightmare! The liquids have different viscosities and consequent pour rates. And shutoff is rarely clean. And don't rotate too fast or you will mess up your glass position. It goes on ... and on ... and on.
Everyone who did that project came out ... changed.
The person I was describing runs a food production line and has modified various bits of equipment for speed, efficiency, safety and ease of use. They have got great results. They have no formal training, have no software background and basically go to https://www.dfrobot.com and get what they need, then hack.
Probably not impossible, but I think the bigger thing will be the time to research the mechanical design of whatever you're doing. That and finding reasonably priced sensors that will be reliable.
Made a a pretty sick vacuum tube in high school with clear acrylic and put a shrader valve on it so it could be easily decompressed with an auto shop ac recharge machine. I won the shit out that science fair showing a feather drop like a rock
At $20k estimated cost, you are getting into territory where the TAM of non-medical uses may be higher.
Sports physio / trainers would kill to be able to do regular MRI on their athletes. Being able to do pre/post workout imaging, and the kind of training programs this level of visibility would unlock, are quite exciting.
Assuming you can generalize from brain to whole-body, I think you could sell one of these to every major sports team in the country, and making it a non-medical device (ie skipping the FDA) would let you iterate much faster. A couple more halvings in price and this is accessible to every sports physio office and gym in the country.
I interpret musculoskeletal MRI studies in my practice. Small joint (what this would be used for) ligaments and tendons are incredibly difficult to see and assess even at ultra high res studies performs on 3T magnets.
With the spatial resolution of this you would be way better off using ultrasound.
It would help with scale if practically every well equipped gym and veterinarian had one. Also, a large supply of used machines will eventually exist so even poorer locations can afford one.
This might have some interesting industrial applications as well (checking composites for defects, food packaging, etc). There might be some other applications that are currently unknown as MRI machines are too expensive (eg: checking beams in bridges).
Being able to use this around metal is also huge. It means you can use it on patients with metal implants or bullets in them, to guide surgery in real-time, in the surgical suite, at the same time as other medical instruments, at the patient's bedside instead of in a dedicated room that you have to transport the patient to, etc.
This is even more evident in the time of Covid. Currently Covid patients have to do imaging at the very end of the day so Covid sanitizing protocols don’t have to be repeated over and over all day. It may seem minor but delaying imaging can delay other procedures and therapies for an entire day. Having the option to transport the equipment instead of the patient has many clear benefits.
People with metal implants and bullets can often still have MRIs with some additional screening/safety measures. There may be advantages to operating under live MRI guidance but I'm not aware of any research on that. Even with low fields, you still would get artifact from having metal near your target of imaging.
woah. woah. woah. hold on a second here... are we comfortable enough with understanding all of the behavior of deep learning models to where we can confidently put them in the pipeline for diagnostic clinical imaging?
i'm okay with using them for image analysis, but denoising and other image production tasks seems dangerous. how do you know what you're looking at is real as opposed to something that just looks convincing? (like deep neural nets are famous for producing)
This project doesn't use AI to improve the image, they use it to estimate the EMI noise from the surroundings. So they're not "filling in the gaps" in the actual resulting 3D voxel volume with fantasy voxels (which I hope will never ever fly in a clinical setting).
"To tackle the EMI signals from the external environments and internal low-cost electronics during scanning, we developed a deep learning driven EMI cancellation scheme"
So it's kind of using deep learning to improve the SnR in the RF reception. Of course this could theoretically also lead to "fantasy voxels" but due to the nature of MRI decoding, I'm willing to guess that bad predictions of the EMI interference will not show up as unnoticeable alterations of realistic tissue imaging but rather as artefacts all over the volume, like you normally see in clinical MRIs that weren't taken 100% optimally.
Thanks for the kind words. I am the first author of the "Neural correlates of interspecies perspective taking in the post-mortem Atlantic Salmon: An argument for multiple comparisons correction" paper. Happy to take any questions here. A link to the original poster: http://prefrontal.org/files/posters/Bennett-Salmon-2009.pdf
It would be nice if the cost of an MRI was so low you would typically get a cheap one as part of your yearly physical and if anything popped up they could do it again in an expensive, high powered one to verify.
I've scanned about 300 people as part of my research career. The director of the imaging center reviewed every anatomical scan. From that group of 300 we informed about three people that they had an anomaly which should be examined by a doctor.
Yeah, that's what I'm talking about. Sure, it was 1% that needed further validation but that 1% is so much cheaper and easier to treat when its caught early vs. later on when it's noticed by the patient.
MRI's becoming commonplace, even if it were every 3 years instead of annually would be a useful tool to improve health outcomes across the board.
Marc Abrahams, organizer of the Ig Nobels, asked us for a salmon recipe to include in a cookbook they were publishing. We sent in a single page recipe for how to cook a salmon in an MRI scanner by overriding the safety protocols. That was fun to write.
Not sure the dead salmon is relevant. That paper is focused on false discovery in FUNCTIONAL MRI. Different can of fish. Most clinical work is structural MRI.
Those false positives are because fmri runs countless statistical tests and the earlier "misconfigured software" wasn't running stringent enough multiple comparisons corrections. Basically the same issue in the classic "jelly bean causes acne" xkcd (https://xkcd.com/882/). The exact number depends on voxel size, temporal resolution, and experimental condition but is somewhere close to tens of thousands of tests.
The "images" that are presented in fMRI studies and that contain false positives are representing results of statistical tests (t-values, and f-values after correction) not the contents of voxels. So the false positive rate of an fMRI has very little to do with the accuracy of a voxel's content in a structural MRI.
the primary innovation is using deep learning to denoise the signal and the cost savings derived from being able to use a noisier signal.
whether you call it "SnR improvement" or "additive noise cancellation", it is undeniably adulteration of the signal.
looking at the supplementary information, it looks like this paper was reviewed by mr-physicists. i think it also should have been reviewed by ml experts as well.
Sure, but it's not like it has the potential for overfitting. From my layman's understanding, the process is this:
1. Measure outside interference sources
2. Measure MRI of "nothing"
3. Use ML to estimate f(interference) = noise
4. Subtract estimated noise from signal
So the noise removal process has no awareness of brains, skeletons, etc.
Exactly my thoughts too. I'm fine with a simple noise-removal pass, but if the AI is context-aware, what's to stop it saying "hmm, this brain would look more like a normal brain if I remove these tumors". Obviously, they'll test for that, but that only handles common cases they concider, it's always going to be a risk for more unusual sceanrios, and the danger with altering the data is that anyone looking at the results wont have a way to tell how dubious that data is.
Reminds me of https://en.wikipedia.org/wiki/Xerox#Character_substitution_b... which was _so much_ worse than the equivilent OCR bug because it occured at the image level, where everyone expects errors to to produce noise, not contextly sensible and sharp _but wrong_ characters.
EDIT: based on other comments below, this is thankfully not the case, the AI just understands noise, it doesn't try to "fill in the blanks" based on how brains are supposed to look.
The ML denoising is within-sample across voxels—-or so I presume from similar work in small animal MRI. And you can always have the “with” and “without”. I do not see any problem if a radiologist is in the review process.
Denoising can on average improve the result, but sometimes it will be wrong.
Spotting when it goes wrong is potentially a difficult task, but generally the difficulty scales pretty clearly with the difficulty of understanding the original image anyway. If you can't spot when a denoising filter has screwed up, chances are you wouldn't have spotted anything interesting in the original image anyway.
But once an AI is context-aware things get way more complicated - it will try very hard to produce an image that doesn't _look_ wrong. Even if it goes wrong, it can go wrong and still succeed in managing to make an image that looks correct, it just no longer matches the real brain that was scanned. Perhaps it decided a tumor was just a smudge on the lense, and invented some brain to go behind it. An operator expecting to see brain and seeing brain wont think anything of it. When the patient dies, they may look back and say "wow, that tumor didn't exist at all just 3 days before! that should be impossible!".
tldr: Having an ai that might make mistakes is one thing, having an ai that can just invent exactly the data everyone is expecting to see is dangerous.
(reposting my comment) From my layman's understanding, the process is this:
1. Measure outside interference sources
2. Measure MRI of "nothing"
3. Use ML to estimate f(interference) = noise
4. Subtract estimated noise from signal
So the noise removal process has no awareness of brains, skeletons, etc.
There are a lot of applications that are surprising. I’ve scanned for salmon farmers (is that the term?) who want to check they are breeding good fish and are looking at spine alignment.
I’ve scanned logs for forestry managers who want to look at something in their trees.
I’ve scanned old hearts that have been sitting in formalin for decades.
All are probably better at higher field strength but maybe some of that can be compensated for by scanning for longer? A log isn’t going to move, and a dead fish scan is likely only limited by the time it takes for it to rot.
I’d be scared of scanning unknown things, it might be a low field MRI, but it’s still a big magnet.
>However, MRI accessibility is low and extremely inhomogeneous around the world. According to the 2020 Organisation for Economic Co-operation and Development (OECD) statistics, there are approximately 65,000 installations of MRI scanners worldwide (~7 per million inhabitants)
Given that my little podunk hospital in the midwest seems to have roughly 5x the worldwide average number of MRI machines, totally agree.
I have seen an alarming number of talks where someone proposes to algorithmically add Gado contrast or turn a T1 into a T2 image. In a few very specific contexts, this makes sense (e.g., aligning a T1 taken in one session with a T2 taken in another). Otherwise though, it seems dangerous to mistake a "real" image with the expected image given another one.
If reducing gadolinium dose is the aim, a more prompt following of the literature, radiologist request (rather than surgeon demand) and weight based dosing would drastically reduce dosage.
A moaning radiographer, what a surprise!
I'm kind of thinking the opposite. Image analysis is where you don't want AI. Noise removal is further upstream (I'm assuming) and if it fails wouldn't it cause significant artifacts (blur for example) in the images?
It would be helpful to see results with and without this correction, or even with varying degrees of it.
Sparse observations save lives. A quicker MR. Less X-Ray exposure.
It's totally valid to worry about validation, but to the degree you can validate image processing algorithms of any kind - AI or otherwise - they absolutely save lives.
Yes, and when a quick MRI is available, it can remove the need for a CT.
Fast brain protocols are now less than 5 minutes. This makes things practical that weren't before.
This exact product is mentioned in the article as evidence for clinical/market demand. It also shows precedence for FDA approval of a pretty similar instrument for clinical diagnostics. Although, its interesting to note that the hyperfine MRI (at least ostensibly) seems to do the same thing in a smaller/more portable form factor.
What is the SNR they are getting ? Can't seem to find this info in the paper.
I am also working on a low-field MRi prototype, but at a much lower field (1mT) and using SQUID-based detection. This approach, in theory, allows to have much better T1 contrast, which is an issue raised in this paper. Also, at these levels of field you can use a low-consumption resistive magnet which permits much better field homogeneity.
Anyway the results this team is getting are very impressive and gives me hope that portable MRI is not science fiction. Would love to see some clinical diagnosis data with a bigger sample and more doctors. Will definitely try out their EMI cancellation algorithm on my experiment !
How does this fare against patents? Isn't pretty much everything to do with the actual implementation of an MRI patented and copyrighted in some way to prevent anyone else from entering the game?
The very first NMRI images were published in the early 70s, so at least some of what is required must be public domain now. The original diffusion and perfusion patents are both from the 80s, so should also be expired I think?
That being said it's very hard to make any even slightly novel machine (MRI or otherwise) that isn't so close to an existing patent that a judge would dismiss a suit out of hand.
This sort of technology offers a lot of value for understanding human health in the future.
Right now, we (physicians) discourage people from getting tested outside of guidelines because we don't know what to do with incidental findings. But you could imagine that as a society, we would like to detect and understand these things, rather than just remain ignorant to them.
Inexpensive technology like this could be perfect for performing large-scale studies with repeated sampling of volunteers over time, to gain information that can help the next generation.
And perfect for very high false discovery rates and unnecessary downstream diagnostic burden and iatrogenic errors.
Rather see a focus on new magnet technologies to reduce cost without loss if already marginal clinical MRI resolution.
> And perfect for very high false discovery rates and unnecessary downstream diagnostic burden and iatrogenic errors.
...which is exactly why the comment you're replying to says that physicians discourage them. That's missing the point; noisier devices are indeed not going to be great at improving the existing applications. But there's a whole world of other possibilities out there as long you don't try to substitute questionable data for good. Like monitoring over time, or between-patients studies where you get additional significance from large numbers, or even just fishing expeditions where you see what the cheaper and more deployable stuff is capable of. Not everything needs the best and only the best.
> Rather see a focus on new magnet technologies to reduce cost without loss if already marginal clinical MRI resolution.
Why not both? The work required is going to be pretty different.
And chaining them together is a time-honored technique: use the quick cheap thing to detect reasons to dig in with the fancy stuff. Your base rate may be low, but if the quick check is negative then the adjusted probability might drop it below some other cause that you'd be better off looking into.
Apart from the potentially massive significance to low-income countries and health costs, does someone has a good grasp on the applicability of the algorithmical advances towards classic MRI?
My current gut feeling is like: If 0.055 Tesla can create this kind of image quality, what could we possibly expect at 1.5 or more?
You can expect a lot and you get it.
It's truely impressive what a bog standard 1.5 or 3T magnet can do and how fast it can do it. A standard brain protocol will often include whole brain imaging at 0.8mm x 0.8mm x 0.8mm voxel size or thereabouts. It takes about 4-5 minutes. A leg angio done from start to finish in 20 minutes. This is without more advanced processing, and some clever processing is coming into clinical use now. Deep Resolve (Siemens) and Compressed Sense/Sensing (Philips/Siemens) are what I'm thinking of. Faster scans, or more resolution in the same time. It's a good time to be using MRI.
Towards the bottom: "Such scanner can be made low cost to manufacture, maintain and operate. For quantity production, we estimate hardware material costs under USD20K."
Siting a conventional MRI is pretty expensive (often requires a new build 6 figures for sure) and operation costs can run up to even 5 fig/month for powerful ones.
They could probably get one of these out the door for approx 100k. Clinical scanners are typically 10x+ that.
Siting cost would be next to nothing, and operating costs low too.
This is a good comment and still underplays the cost of MRI. Getting a reasonable 3T setup going will be a lot more than US$1 million. Running costs are very high, with a scanner lifetime service contract being somewhere between 50% and 100% the original cost of the MRI scanner.
Additionally, the scanner cost is only part the price. There is the Faraday cage, chilling, room setup, building strengthening, scanner install and shipping cost, peripheral equipment (compatible monitoring, injectors, compatible beds and chairs etc). It probably comes in at a doubling of the cost of the actual scanner.
While reducing the cost of the install and running will help a lot, the staffing is the larger cost in radiology, as techs and radiologists are expensive.
Costs will vary hugely depending on where you are in the world, but it isn't cheap anywhere.
I was intentionally handwaving but above is about right in orders of magnitude, i just rolled things up.
Staffing is an interesting one (which I ignored, but good point you can't really) - lots of potential deployments of a small machine like this probably don't look anything like a US standard imaging suite, and aren't going to be staffed the same way. If you run all the numbers in detail you get big variations here, depending on set up.
Why so expensive? Couldn't you just site it way out in the boonies? If you put it on a giant purpose-built concrete cube, it seems like most of this stuff becomes cheaper.
> We have experimentally estimated in our preliminary study that the apparent T1/T2 values for gray matter and white matter were approximately 330/110 ms and 260/100 ms at 0.055 T (vs. 1300/110 ms and 830/80 ms at 3 T51) while CSF maintains long T1 (>1500 ms) and T2 (>1000 ms).
That's not particularly different from normal MRIs, and the achieved resolution is not that much worse than normal MRIs. The scans have lower contrast (and repeated/longer scans is one way to improve that) and using for functional imaging will make that worse, but honestly it doesn't seem to have suffered very much at all.
> First, these scanners rely on complex superconducting electromagnet/cryogenics designs and ever increasingly powerful electronics (including gradient and radiofrequency power systems) for fast imaging and/or advanced imaging features like brain functional MRI and diffusion tractography, yet routine clinical uses only necessitate a small portion of these imaging protocols.
I believe affordable and abundant diagnostic and imaging medical devices is a prerequisite for a medical technology revolution that substantially increases lifespans.
This is cool. Don't get me wrong. You could build this in your garage maybe. But those scans are useless for what I do in my research. The resolution and contrast it provides are just too low. Edit: for neuroscience research..I hadn't considered any clinical utility.
So you're saying we have sufficient trust in the same sort of NN technology that confuses 8's and 0's in OCR text will be used to impute image data which might or might not exist? Sure, NN's are great at "filling in the gaps" and colorizing pictures based on what might be assumed, but when accuracy matters, does this approach truly work?
EDIT: I just want to point out that the original subject title of the post on HN was "A low-cost and shielding-free ultra-low-field brain MRI scanner Using AI" ... and the Using AI part of the post title was subsequently removed.
Do you have any data on the reliability of OCR systems used in production? I don’t have any such data, but given that the USPS was using OCR to sort mail over 50 years ago I would be surprised if these systems aren’t incredibly accurate.
"There are still no OCR tools that work at human level in most applications"
and also from my personal experience working with this technology every day. There are many more mistakes in OCR even with printed material than might be expected.
There is a major problem with Xerox Scanners and the 8's and 0's issue I reference.
See other comments. The nn is used to clear up electromagnetic inference as there's no shielding cage. It's not anything lik a superresolution approach on the processed voxel data.
Ok good clarification as the title of the post seems to imply much more than just fixing interference. As always, the article subject is the hook that gets you in and then you realize it's not as might have been expected.
This is fantastic. What a sentence to get to write.