Algorithm Brings Speedier, Safer CT Scans 58
kenekaplan writes "Standard CT scanners can generate images of patient's body in less than five minutes today, but the radiation dose can be equal to about 70 chest X-rays. Lower-powered CT scans can be used in non-emergency situations, but it can take more than four days to produce those images. Intel and GE created an algorithm that speeds up a computer's ability to process the low radiation dose scans by 100x, from 100 hours per image to one hour."
God damned stupid article (Score:5, Informative)
1. I hate 'news articles' that are chock full of hyperbole and mis information. TFA implies that most CT scanning is done in the ER for life or death reasons which is hardly true. It oversells the current radiation dose of modern 16+ slice scanners and attempts to lower the radiation doses for all CTs.
2. Current gen CT scanners cut the dose of most tests by at least half from the second and third gen scanners. Of course, TFA doesn't mention how good the new dose regimens are in terms of decreasing dose.
3. It appears that this new tech has a significant price tag. TFA quoted 1.5 million for a 128 slice scanner with the "new algorithm". More slices = faster and more resolution, but mostly faster. The current 'top of the line' is 64 slice. "Standard" CTs are 16 slice and cost anywhere from $150 - 250K.
4. At least the GE scanners run Linux!
Re: (Score:2)
And if this linked article [royalgazette.com] doesn't remind you of a certain Monty Python sketch, then you've ceased to be, kicked the bucket and shuffled off this mortal coil.
I don't see how they did that blurb with a straight face.
Re: (Score:1)
It was so cool back in the days to see DEC/OSF booting on an MRI tech console. Diversity of both software and hardware. SGI workstations (Indigo, perhaps, I don't remember) in another room, with funky 4Dwm windows & icons. Now almost every medical equipment I run is either Windows or Linux (like that new GE CareStation we got last week). Linux, Linux, Linux. Or Windows. Or VxWorks. This starts to get boring.
Re:God damned stupid article (Score:4, Funny)
Better get used to it. The GE tech rep said it was going to be Linux all the way down as far as GE is concerned....
Re: (Score:2)
The GE tech rep said it was going to be Linux all the way down as far as GE is concerned
Maybe we should replace Tux with a new mascot, maybe this guy? [wikimedia.org]
Nah, Linux is too fast. hey, Windows doesn't have a mascot and this would fit them better. Maybe GE will reconsider their OS choice?
Re: (Score:3)
Did you read another article than the one I read? This is an honest question.
1. The article in fact mention that the new technique is not applicable for life or death situation where a high radiation dose is acceptable. But rather for routine tests where it is important to limit the dose.
2. Article doesn't mention different generations of CT
3. No price is mentioned that I can see. I've search for "1.5", "million", neither words are used anyway
4. No mention of linux
Maybe the link have changed from an earlier
Re:God damned stupid article (Score:5, Informative)
No, I added a few things -
1. The article makes breathless claims about "emergency' CT scans and gives a decidedly FUD picture to the issue of radiation exposure via medical devices. It's there, just not as dramatically as mentioned.
2. I added the different generations of CT scanners to point out that manufacturers have been cutting down dosage systematically and significantly over the past couple of decades. Again, it's really just progress.....
3. The cost of the 128 slice "new algorithm" scanner is almost an order of magnitude more than a base gen 3 CT scan. It does things that the cheaper scanner doesn't but that's a pretty high price to pay. The info comes from a linked article in TFA (see my post below the first one).
4. This is Slashdot. I thought somebody would appreciate this bit of technical trivia. Of course, if it ran OS X or if Google developed it, the thread would get 10 times the comments this one will get.
Mostly I'm just grumping about stupid press releases. If they toned down the rhetoric and added some technical detail, it might be an interesting Slashdot post. As it is, it's just fluffy techno pony drivel.
Now, if you don't mind, it's time for my nap....
Re: (Score:1)
4. No mention of linux
My guess is (s)he works in the medical imaging field where it's pretty common knowledge. It doesn't need to be mentioned in the article. GE scanners run Linux and ran Solaris before that.
Maybe the link have changed from an earlier version. The article is intel.com so I assume that it's main purpose was PR, but still I thought it was pretty ok and it was clear on the improvement that was made (computation time was reduced by a factor of 100).
I have a friend who works for Sapheneia [alpha-imaging.com] They have been doing this for several years now. Not only have they been able to do this for some time, but they also work with almost any vendors scanner.
Re: (Score:2)
Re: (Score:3, Interesting)
Re:God damned stupid article (Score:4, Funny)
Hopefully it will stop soon. 640 slices ought to be enough for anyone....
Re: (Score:2)
Technology is well... Just great... (Score:1)
OpenCL || Intel add (Score:4, Interesting)
Sounds like a job for OpenCL. A GPU cluster would be much more scalable than using expensive Xeons. Which also makes this article sound like an add for Intel CPUs.
Re: (Score:1)
Minor nit: "ad" = advertisement, "add" = addition.
Re: (Score:2)
Not every problem leads itself to GPGPU solutions. I'm no expert, but looking at a paper on a similar idea for optical reconstruction, I'd bet that the creation and update of the model via analysis (comparsion between predicted and actual results) is really hard to make parallel, and that process has a lot of non-localized memory access.
I'm sure you could use GPU acceleration for the CG calculations in the reconstruction phases, but I'm not sure that's the limiting factor here.
In short, there are really goo
Re:OpenCL || Intel add (Score:4, Informative)
I think this very much is an Intel ad. I was curious, because this sounded familiar, so I looked it up. From the press release and GE's white paper [gehealthcare.com], it looks like their system:
Uses 25 mAs dose (75% less than standard, they say)
Is ready in an hour, 100 times faster than when they started in 2006 (so 6-10x of that speedup is Moore's Law, the other 10-16x is algorithm improvement)
Uses 28 quad-core Xeons
On the other hand, a GPU solution [physorg.com] from 2 years ago:
Gives a 2-4 mAs dose (97-99% less than standard, they say)
Is ready in 1-2 minutes, 100 times faster than contemporary CPU algorithms
Uses a single GPU
Better, faster, cheaper... Pick three.
Re: (Score:2)
You're right. In fact, it has already been done [acceleware.com].
Throwing resources at the problem (Score:1)
How to obtain a 100x speedup: consider an architecture with 112 cores, wait for 2 CPU generations to pass, and put 3 engineers on the task for several years to parallelize the algorithm by hand. Of course, giving it to the research community would have been impossible because, you know, it may have worked faster with more general solutions.
Inquiring minds (Score:4, Funny)
Inquiring minds want to know, since this will substantially reduce the needed resources for a scan, how much cheaper will they be?
You can stop laughing now!
Re: (Score:3)
Yes, but that machine now has a higher throughput. More scans to amortize across. Time is a resource.
Looking forward to improvements (Score:3)
Re: (Score:1)
From what I have read, you basically get a 1/400 chance of cancer over 10 years.
Sounds like a lot/little depending on your view. My mother had 6 CTs.
Re:Looking forward to improvements (Score:5, Informative)
The heat you felt is really because the iodine gets to the thyroid provoking a thermal regulation change.
Re: (Score:2)
So that's why I never noticed that side effect after my thyroid was removed.
Re: (Score:1)
They don't inject radiation into you.
Yes, I am a biologist.
Re: (Score:1)
Perhaps the procedure described was a PET/CT scan. In that case, they do indeed "inject radiation into you":
PET images features CT doesn't, but CT provides much better spatial resolution, which is why it's diagnostically advantageous to have simultaneous and coregistered subject imaging. The obvious way to achieve this is to build the two scanning apparatuses into the same device to provide both spatial and temporal locality. Whereas CT imaging provides its own signal (the emitter as well as the detector),
Re: (Score:2)
Re: (Score:2)
You seriously have no idea what the fuck you're talking about, do you. "My arm where the IV was injected with radiation..." ?! Your arm was not injected with radiation. Your arm was injected with Contrast. Were you listening to the Rad Techs at all? It went something like this "OK, I'm going to inject you with contrast now. You'll feel it spreading warmly through you. Take a deep breath...and hold it... (as the scan goes), OK, breathe."
Oh, my qualification? I work on GE Lightspeed and Toshiba Aquil
Re: (Score:1)
A number of misunderstandings in this post and the comments:
1. The IV injection is an iodine containing contrast, it does not contain radioisotopes / radiation. Iodine is a heavy, and thus radiopaque element and is used to show blood flow in the CT scan.
2. The warmth you felt is due to a histamine and vasodilatory reaction to the IV contrast, it's got nothing to do with the thyroid. It's similar to the warming sensation you get when you have a couple of shots of alcohol and actually causes you to cool down.
danger of "model-in, model-out" (Score:2)
Anatomy (Score:2)
On the other hand, there's quite a lot of difference betwen a hand, a head, a foot, a chest..
If the initial model used for the reconstruction is just some generic approximative shape, it will still provide some speed up, but won't be affected that much by the actual pathology which is being imaged.
Worthwhile Goal (Score:2)
A while back I had several full-body CT scans on an emergency basis. They found what they were looking for in my liver and it was treated. But I was forbidden to have any X-Rays of any kind for two years after that. So when I came down with bronchitis and pneumonia, the doctor had to play it by ear (literally, he just listened to my chest). All is well, now. But lowering the X-Ray dosage of CT scans is very worthwhile.
New algorithm or hand-tuned code? (Score:2)
Is it really a new algorithm, or is it just that they hand-tuned the code to run iterative reconstruction quickly? There's a world of difference. There are some great algorithms out there to speed up calculation of large images where you expect them to be compressible in some basis, but from this article it looks like they didn't invent a new fancy algorithm, they just heavily optimized an existing one. Anybody have a link to a technical paper so we can find out for sure?
Not news.... (Score:1)
So what, exactly, have they done? (Score:2)