Wednesday, November 30, 2011

Vital: Denoising Is NOT Dose Reduction

After my visit to Kang and HealthFortis, which, by the way is associated with lifeIMAGE, I had the chance to wander over to Vital Images, and discuss our upcoming Shoot Out for Advanced Imaging. I must have been in the company of the right people (hear that, John?) as before I knew it, I was introduced to the CEO and to the EVP of Sales. After the pleasantries, I had the chance to really look hard at some of the things I needed to see, and had a really informative chat with our intrepid (and beleaguered, mostly by me) salesman and technical folks. I left knowing much more that I started with, but I'm going to leave the feature-list for the report of the Shoot Out itself.

One thing I do want to publish right now, though, is some information about denoising. Vital has a really nice denoising subroutine, which will take a noisy scan and smooth it out. Vital made it clear to me, however, and said that absolutely I have their permission to broadcast to the world, that this is NOT dose-reduction software. All it does is make an image that is degraded for whatever reason (NOT to include deliberately degraded) look prettier. No guarantees on whether data is lost, although almost certainly there won't be much lost at all, but users are urged to toggle back and forth between the pretty and the not-so-pretty pictures.

Where the idea of using denoising for dose-reduction came from, I'm not sure. I don't believe Vital ever promised this at all. I think in retrospect we must have found it perusing information from Clarity which DOES promise that one can lower the parameters to levels that produce crappy dose-reduced scans and then "rescue" them with their box, which performs digital filtering on the images:
Clarity is server-based and seamlessly integrates into your existing DICOM network. During installation of the Clarity solution, dose-optimized protocols are established on the CT scanner(s) to deliver desired image quality at reduced dose levels. Low dose images are transferred from the CT scanner to a Clarity server that resides on your DICOM network. Based on desired results that have been pre-determined by your Radiology staff, Clarity algorithms enhance image quality and automatically route the final images to their intended destinations.
I'm not buying it. In either sense of the term.

Much obliged to the good folks at Vital.

CPOE So Easy A Caveman Surgeon Could Use It!

Whilst cavorting with old friends at lifeIMAGE (see the previous post), I had the chance to connect with another old friend, Kang, formerly one of the technical gurus of AMICAS, now CEO of his own little company, HealthFortis. (He's working with another AMICAS alum, Dmitry, whom I sadly didn't get to see this trip.)

Kang, having created some wonderful stuff AMICAS over the years, needed a new challenge, and he picked a big one: CPOE, aka Computerized Physician Order Entry. (Some say "Provider" instead of Physician, which clearly tells us physicians that we are no longer held in particularly high regard, but whatever.) CPOE is clearly a tough nut to crack, as one must create software that physicians (even surgeons and, yes, even orthopedic surgeons) will have to use to order stuff for their patients. Keep in mind, these are guys (and gals) who are used to scribbling something illegible on a piece of paper over the course of three seconds, and then faxing or maybe throwing it (literally) at someone with the full expectation that their intentions will be telegraphed magically. Of course, sometimes they will lower themselves to simply barking said orders at someone, in person or by phone, with the same somewhat unrealistic expectations of completion.

Now that EMR's and such have taken over, computerizing this process in the form of CPOE is felt desirable, and even necessary. But no one asked the physicians about this, and therein lies the path to big trouble.

Our largest hospital system instituted Cerner Millenium CPOE over the past few years, and the physicians to a man (and woman) seem to hate it with a passion. I'm on the CPOE committee for one of our other hospital systems, and we are struggling with the joys of trying to crowbar a entry process into the ancient legacy MediTech Magic program, you know, the one that ports a 1980's green Data General window to Windows. I'd rather be the bagel delivery-boy for the Gaza district.

Kang nicely outlines what is wrong with pretty much every CPOE product out there: it tries to make docs do things differently, and, trust me, docs do not want to do things differently. Why are we forcing them to take 5-20 minutes and 59 mouse-clicks to accomplish what they once did with a piece of paper and a pencil in 3 seconds? The intelligent approach is to first make it easy for the physician to use CPOE, and then leverage all the nice things that an electronic approach can deliver. This, of course, includes "Decision Support at the Point of Decision." Brilliant!

HealthFortis takes a very simple approach. There are just a few points of entry, but they spawn everything appropriate to taking the order, and all of the entry boxes allow for free-text, much like Google, with a list of possible entries building and then narrowing as you type. To find your patient, you might simply type Do Da, which would bring up Doctor Dalai, among other less interesting people. Select the patient and then a simple window appears, wherein you enter the diagnosis and, if you wish at that point, the exam to be done. Here's where the magic starts.  Suppose you enter "AA".  The program gives a few possibilities, such as "AAA", which we then select. You are then given a list of possible exams, ranked by ACR recommendation codes from 9 (good choice) to 1 (you have to be kidding!). Clicking the exam you want spawns an order in HL-7 to be delivered back to your HIS/EMR.  If the condition/symptom isn't quite so specific, the program brings up more data and options to help you decide. Of course, you can still override this and forge on ahead with an arteriogram for little toe pain, but you will definately get a "1" for that choice, and you will be told just why that is inappropriate.

There is included some nice stuff like searches for recent orders of the same type (did you really want to repeat the CT for the 10th time this month?)

Right now, the system is in its infancy, having been online for only a few months, but it is growing, and I'll predict there will be rather wide-spread acceptance. The order-sets for the moment include more radiology exams than anything else, at least as I understand it. Kang did outline a heuristic learning function, which will help grow the database; as more and more entry-pairs are collected, the system will learn which are being used most frequently, and make them more easily available.

This is one of those offerings that is elegant in its simplicity and usability. I'm not sure it will be ready for full hospital use in time to derail MediTech, but it possibly could be deployed at least to physicians ordering stuff from outside the hospital. I'll take that for now.

Make it easy and they will come. Guaranteed.

Disruptive Technology

I'm sitting at one of the RSNA Bistro venues, having just spent $20 on a mediocre buffet meal which did at least consist of some mildly healthy alternatives. I've got a couple of things to tell you about, some from the meeting, of course, but one gleaned from FoxNews while perusing the net over lunch.

Let's start with the fun stuff. I think I've stumbled across the next revolution in photography, and truly this is a disruptive technology. I'm referring to the new Lytro camera, which uses "light field" imaging instead of regular old, well, light.  Here are the three models, the middle version having 16 GB of storage for 750 images, and the others coming in at 8GB for 350 images.

I'll refer you to Lytro's site for an explanation of what goes on in this little box.

Capture living pictures with the press of a single button. By instantly capturing complete light field data, the Lytro gives you capabilities you've never had in a regular camera...

Since you'll capture the color, intensity, and direction of all the light, you can experience the first major light field capability - focusing after the fact. Focus and re-focus, anywhere in the picture. You can refocus your pictures at anytime, after the fact.
And focusing after the fact, means no auto-focus motor. No auto-focus motor means no shutter delay. So, capture the moment you meant to capture not the one a shutter-delayed camera captured for you.
And here is what you can create. Click anywhere on the image to refocus, double-click to zoom.

This is the start of something big, I think, although it will probably take quite a while for this to migrate into mainstream photography. Of course, it took quite a while for digital to overtake film. You saw it here on first.

On to things Radiologic.

I attended a seminar on the lifeIMAGE LINCS, the lifeImage Network Cloud Service, narrated by CEO Hamid Tabatabaie, former CEO of AMICAS if you didn't know. LINCS is now fully operational, and it is being used at multiple centers. Hamid showed us a live view of user stats, and the system is quite impressively active. For the full explanation, check the lifeIMAGE website. In brief, the system facilitates easy, HIPAA-compliant sharing of studies between institutions, with the idea of empowering physicians themselves to "be the network". Most every permutation is considered, as long as someone in the equation has a LINCS account. The study can be sent or received with a few clicks among LINCS members, and if a "foreign" study is to be imported to LINCS, appropriate electronic paperwork is presented. A study can then be nominated to be uploaded to PACS, pending approval by whichever human you designate.

Two partnerships offering viewer options and more were announced:

  • lifeIMAGE is demonstrating a technology intergration with Vital Images, an advanced visualization and analysis software company, which shows Vital’s FDA-cleared universal viewer launching from LINCS. The two companies are also exploring a collaboration to provide on-demand access through LINCS to advanced visualization tools and comprehensive clinical solutions for cardiovascular, neurovascular and oncology imaging.
  • lifeIMAGE also has partnered with ClearCanvas, a leading provider of innovative diagnostic imaging applications, including Picture Archival and Communication Systems (PACS) and workstations. ClearCanvas offers a free version of its diagnostic workstations in an open-source format, as well as an FDA-approved clinical version, that will connect the 15,000 members of the ClearCanvas community to lifeIMAGE.
In my own humble opinion, this places lifeIMAGE on the road to creating a Cloud-based PACS, although when I suggested this to Hamid he just smiled and shook his head. Maybe someday.

lifeIMAGE literally offers us a life-saving (and disruptive) technology, and that is NOT an exaggeration. At our trauma hospital, it is more likely than not that a patient will arrive with a CD from St. Elsewhere that has not even been reported, and probably not even reviewed. And sometimes, that CD won't even load. In the best possible circumstance, we the rads spend 10 minutes loading the CD and reviewing it with the house staff. In other cases, the patient is rescanned, the new scan interpreted, and then reviewed with the residents, adding 30-40 minutes to the process (and doubling the radiation dose if anyone cares about that.) Of course, in the worst possible scenario, the patient could well be dead 20 minutes after arrival in the ED if he is the victim of severe trauma. What would we give to have the images in hand and reviewed before the patient hits the door? A few dollars goes a long way, and that's what lifeIMAGE costs when distilled down to the basics.

Not to sound histrionic, but isn't the patient's life worth that? (And no, I don't get a kickback from Hamid.) This is damn good technology, and you should, you MUST look at it.

My second disruptive technology is one you can't buy, directly, that is. Fovia sells their 3D technology not to end-users like me, but rather to PACS and Advanced Visualization companies, including Merge (where I use a limited thick-client version on my PACS), as well as GE, and Vital, among several others. The full version of their engine operates as a thin-client with server-side processing, and it works very, very well. Fovia has taken a very logical approach. "Which would you bet on as the best investment," asked Ken, Fovia's CEO, "a system that uses proprietary graphics cards, one that uses off-the-shelf gaming video cards, or one that uses the CPU of your computer and leverages Moore's Law?" Ken's answer, of course, is number three.

Fovia has bucked the system, going against the prevailing paradigm of proprietary graphics cards (viz TeraRecon) or gaming cards (nVidia, etc.) and does the graphic processing with a server's CPUs. This may seem counterintuitive at first, but stop and peek inside your computer. Even the little MacBook Airs now have a dual-core processor, and what you can buy for $1K on the street (well, don't buy it on the street, but you get the idea) outstrips anything you could have purchased for $10K 5 years ago. Add multithreading to the mix, and you can see that leveraging your investment based on the assumption that CPU's will become more powerful makes considerably more sense than assuming any other factor will accelerate to the same degree. Fovia notes a 30-50 fold increase in the speed of their product over the last 5 years, based in part on the rapid growth of CPU processing power. Fovia's system is highly scalable and flexible...the more CPU's, the faster it runs. Given Intel's recent announcement of a 50-core chip, the speed of processing might be as close to instantaneous as possible.

You will agree that Fovia's High Definition Volume Rendering (HDVR) can produce some powerful images as you will see in this gallery page iframed from Fovia (if it doesn't load, go to this LINK):

Fovia's claim to fame is the use of a frequency domain-based algorithm, for the techies among us. This involves "deep supersampling," rendering each voxel 32,768 times.  Sounds pretty involved to me.

While you can't buy Fovia directly, you can buy some products which use its technology. As an aside, I discussed with the execs the possibility of Fovia creating its own GUI, its own wrapper for the incredible viewing software. The answer? "Others have suggested that..." I guess we'll have to wait and see. But for the moment, they do a darn good job in the background.


Dr. Robert Taylor, CEO of TeraRecon, sent me this comment on the dedicated-card vs. GPU vs. CPU debate:

I read your blog this AM and noticed the barb from Fovia about proprietary cards. To set the record straight, I just wanted to point out, TeraRecon also has a full SW option and we only use the VolumePro (VP) because it happens to be dramatically better than using software and scalable. We can now render over 70,000 slices in real time (the combination of many users working at once) from a single 2U server thanks to this technology. Today, and for the foreseeable future, that's impossible with SW (Fovia, GE, Philips) or GPU (Vital, Siemens).

When the sledgehammer (VP) is not required, we also have the nutcracker (SW), and this is why we have sold hundreds of laptop-based systems that work without a graphics board in sight. We also hope and expect that one day CPU technology will be able to do what is needed, and we're fine with that. It's the application that matters in the long run.

Tuesday, November 29, 2011

RSNA 2011: Siemens Hints At The Future

I mentioned something in the last post about attending the Siemens Media Breakfast, and I promised to elaborate.

As a quasi member of the press, perhaps we should say vanity press, I was once again invited to the annual media event. Being on my new eating program, I didn't take much advantage of the proffered breakfast, but I did listen intently to the talks given by Hermann Requardt, President and Chief Executive Officer of Siemens Healthcare, and Gregory Sorensen, MD, Chief Executive Officer, Siemens Healthcare North America.

There were the usual announcements and scanner refreshes/updates.  The Siemens Biograph mCT gets some new software to allow better quantitation and reproducibility. We are told that this is the best selling PET/CT on the market today.  Wish I had one. The Biograph mMR, the PET/MR scanner, has been installed at 10 sites with 20 pending orders. Wish I had one of those, too, but a $5M expenditure is not in my future. While it was said that the mMR has no competition, Philips apparently has one about to be approved, and GE did announce one in the works.

Two new CT scanners were announced, the Somatom Definition Edge, a single-source scanner utilizing the new Stellar Detector, with 0.3mm routine spatial resolution, and the "business class" Somatom Perspective, a 128-slice state-of-the-art machine with low dose imaging and a lower price point.

There will be two new Acuson units, the cheaper S1000 and the top of the line S3000, the latter having built in automatic fusion to other modalities.

There is a new association with Eli Lilly to distribute the latter's amyloid tracer via Siemens' PET NET network.

The syngo family is mobilized, in other words, it can be accessed remotely, via computer or iPad or whatever. Supposedly mobile apps will allow manipulation, although on the exhibit floor, there was a some hemming and hawing as to how much one can or cannot do on an iPad.

More important than the machinery are the rather candid observations offered by the Siemens execs.

Dr. Requardt opened with a statement that we all know is true: Healthcare spending at current levels is not sustainable. In developed countries, there is the desire to decrease costs, but in emerging countries  there is need to increase access to health care. Siemens sees a "sweet spot" wherein the two curves meet, and they plan to position themselves to take full advantage of this. Turning the conventional paradigms around, Siemens now views therapy as the driver of imaging, and using industrial terminology, healthcare becomes a "project" business, wherein innovation is the solution and not the problem. The disconnect between diagnosis and treatment lead to increased nonconformance costs, and a shift to emphasize therapy my better satisfy patients' needs and wants.

Dr. R rather humbly (or not) noted that Siemens had "misdirected" some investments because they didn't realize the healthcare sector was "not fast enough to respond to technology". Hate to say it, but this implies the sector wasn't smart enough to grasp some of what Siemens offered. Or perhaps what Siemens gave us here and there wasn't what we needed at the time. Particle therapy was cited as a case in point. Siemens developed/created/improved the technology, but it hasn't sold well. Apparently, this was NOT one of the "non-regret" moves Siemens wants to see in the future.

I've already alluded to the statement about PACS. "We will focus on core secgments," said Dr. Requardt. "RIS/PACS today is a commodity these days, with dramatic changes in network environments. Our future investments will reflect this." Is Siemens dropping out of the RIS/PACS market? It seems that with every vendor now offering a Vulture Vendor Neutral Archive (VNA), Siemens no longer wants to compete (much?) in this space.  Sad, given the fact that the new syngo.plaza might actually be their first workable interface.

Dr. Sorenson took over, describing the demographic "wave" of aging Baby-Boomers (hey, I'm one of them!!) 80% of healthcare costs are for older patients, and Medicare is decreasing spending. Imaging expenditures are being cut back in particular, with still some increases for primary care. Dr. Sorenson describes imaging reimbursement as a bubble: reimbursement was so high that it created its own demand. (To be fair, the equipment companies, including Siemens, need to stand up and acknowledge the role they played in dangling those reimbursements in front of clinicians as incentives to purchase their scanners.)

In what I find to be a rather ominous, but still realistic, approach, Siemens plans to address the increased scrutiny we docs are now experiencing, mainly from governmental sources. This drive masquerades as a drive toward minimizing "practice variability". IT tools will move us toward evidence-based, rational care. Reading deeply between the lines, our systems will tattle on us physicians if we stray from the government (or third-party payer norm, whatever that is. Big Brother will be watching us. Now, I don't blame Siemens for this, and being a good Capitalist, I will even applaud them for blazing a path to profit through this mess. But I'm still not happy about it at all. It's probably time to retire.

Siemens will spend 1.4 Billion Euro on R&D this year, and it certainly shows. That's actually just about the same number as their reported profit.

Finally, Siemens, the German company, now manufactures half of its CT's in China. "We make it wherever it's adequate to make it." The factories in China are 100% staffed by Chinese nationals, and the facilities are identical to their German counterparts. Far better to invest in China than to be the main investment, I would say.

I wonder what Siemens will bring us next year?

Monday, November 28, 2011

View From The Balcony..

I'm back at RSNA for what must be the 13th or 15th time since my first time way back in 1990.  Or was it 1989? Back then, the meeting spanned the entire Lakeside building, which was all there was of McCormick Place at the time.

Today, many of the BIG vendors have reoccupied Hall D of the Lakeside building, although I'm seeing a lot of empty space in the periphery of the North and South exhibit halls.

I'm sitting up on the Balcony Cafe in exhibit hall.  It's quieter up here, the wifi is strong, and there are numerous power outlets. My iPhone 4 is gobbling up battery power, thanks to iOS 5.0.1, and I've stolen Mrs. Dalai's Macbook Air to facilitate reporting from the floor.

The atmosphere here is pretty vibrant, and there seems to be a lot of interest at the booths, although I have no idea of how much money is actually changing hands.

I've been to several educational sessions already, and I've spent some time on the floor.  There isn't a LOT thats new, but there are a few interesting things here and there. I'll have a separate report on the Siemens Media Breakfast later, but their big news involves the introduction of two new CT scanners.  And, there was a remark made in passing almost concerning the act that RIS/PACS is now a commodity, and as such it may not justify quite the same level of investment it once did. That's unfortunate, as syngo.plaza might actually be Siemens' first functional PACS.

I've had a look at one of the two SPECT/CT candidates, and while its bone SPECT images haven't improved much, there are some other minor improvements.  I'll have a peak at the other one tomorrow or Wednesday.

A friend of mine who works at McKesson had me take a look at their latest PACS GUI. While it's busy and has maybe too much customization, I'm coming to appreciate what it can do; it's a very powerful interface, and if I needed to replace a PACS, it would be on my short-list of competitors. McK has finally decided to converge the various clients, so the view is more or less the same no matter if you access the PACS from home or office. So far, no iPad client, but there is something pretty revolutionary in the works, although apparently not yet enough of a work-in-progress per se that it can be seen by the likes of me.

Probably my greatest accomplishment today was to connect the folks of Blackford Analysis to a major PACS vendor. The rest is up to you, mates!

What has surprised me most of all is the number of folks who remember me from earlier interactions, and continue to read the blog. I continue to be humbled by the fact that anyone actually looks at this thing, but you all have my deepest gratitude for doing so.

Tonight, dinner with some old friends, and then meeting up with some other old friends. My daughter might even be able to break away for a moment and join us!

I'm tired already, and it's only Monday at RSNA...

Sunday, November 27, 2011

Your Village Called
Their Radiologists Went To RSNA

I'm on my now-annual trek to Chicago for RSNA. I go every year now that my daughter is in school up there in the frigid North.

(As an aside, I think I've come up with a wonderful idea viz-a-viz the horrendous weather in places like Chicago and Buffalo. We need to swap cities with Mexico. Chicago could trade places with, say, Cancun, and New York City and Mexico city could easily flip-flop. No? Well, darn..)

I've been bombarded with advertisements from a sampling of the zillions of vendors out there in the imaging space, and you might hear about some of these when I submit The Dalai's to Aunt Minnie. More on that later.

There is one marketing communication that is just so far off the wall, I have to let you know about it even while I'm still in the air.  I won't name the name, but the ad comes from one of the publishing houses specializing in things radiologic. Where they came up with this idea, I haven't a clue, but here's what you could see if you happen to be in the right place tomorrow at the right time:
RSNA Tribute Flash Mob – Monday November 28 at 9:45 AM
Haven't you all wanted to participate in a flash mob? Here is your chance! We have created an RSNA Tribute song (and dance) to be performed on Monday morning at 9:45am right before the exhibits open. If you have never heard of a flash mob, here's the story:

The music ("R-S-N-A" to the tune of "Y-M-C-A" – EVERYONE knows this song!) starts and just a couple of people start dancing and singing along…gradually more and more people join in and before you know it there are a whole bunch of folks rockin' out. So you are wondering what you have to do? Just click on the link below. We've posted the very basic dance steps (don't worry, they are quite simple) with music. You don't have to be a singer – the music has been professionally recorded and will be broadcast at full volume! We will have the expert support of some Chicago college dance students, so you won't be alone and you can just "follow the leader" as they dance! We plan to have a short rehearsal in Chicago. Our goal is to record this to relive the celebration, and laugh (a lot). We are quite sure that this will be a first for RSNA and we feel that it is the duty of all (the) family members to bring a bit of liveliness to this staid and somber meeting.
Here are the new lyrics, butchered sung on YouTube:

And for those far more coordinated than I, here are the dance instructions:

I'm probably going to be in an educational (OK, I'm trainable if not educable) session when this goes down, so I'll expect reports and links to videos of the actual event.

Frankly, I think I need to pervert rewrite YMCA myself...

Hey Doc, My Ass Hurts, Oy Vey!
I need me a CT TODAY!
Ummm...never mind...

Addendum...It actually went down!

Hat tip to Ken from Fovia.

Saturday, November 26, 2011

iPads From Our Futures Past

Apple loves to sue people and companies that even hint at coming close to imitating their stuff. The latest prolonged battle targets Samsung, whose Galaxy Tab is said to be a "slavish copy" of the iPad. In response to several legal defeats, Samsung is slightly modifying the Galaxy to prevent anyone from possibly confusing it with an iPad. Not that anyone would have.

If you are at all interested in the legal machinations, check out THIS article from

Samsung, to their corporate credit, has come up with a novel defense that might just work in the courts. Samsung claims that the "look and feel" of an iPad has been around quite a while, as we see in this clip from Stanley Kubrick's SciFi masterpiece, "2001, A Space Odyssey":

And that's not all.  Consider Star Trek's various "Padd's":


And even from the Original Series!

Yup...there's nothing new under the various suns in the Star Trek universe.

Oh, by the way, there's a tablet out there that doesn't get much mention, but I think was truly the original, forming the basis of a lot of things we deal with today:

Top that, Apple!

Wednesday, November 23, 2011

Another Shoot-Out,
Or, A Requiem For Advanced Imaging

Shoot-Out at the OK Corral
The word has gotten out to some of our potential vendors, so I might as well go public. We're having another shoot-out, and it should be quite interesting.

Our larger hospital system seems to have found some funding for an advanced imaging product of some sort, and somehow your friend Doctor Dalai has become the point-man in the decision. Initially, we were going to go with a bundled solution, as we need a few CT scanners, not to mention my beloved SPECT/CT scanner. Sadly (for the vendor in question), some of the initial prices ("good only for the next 10 days!") were way out of line, and so we are unbundling the purchase. I am thus free to pursue the best-in-breed of Advanced Imaging and SPECT/CT.  Someone else gets to worry about CT.

There are only a few choices when it comes to SPECT/CT, and I've reviewed them before. But advanced imaging is another story.

To create the atmosphere for a fair and balanced decision with respect to advanced imaging software, we will arrange a "shoot out" between some of the major vendors and their products.  I say "some" because we don't have enough room or time to showcase every possibility, so we are limiting the scope to a few programs that seem to have potential to accomplish what we need to do. A side-by-side comparison seems much more efficacious than the series of 20-minute demos we've been enduring. Plus, some of the vendors have been, shall we say, a teeny bit aggressive about placing their product for a prolonged demo, to the point that we were to accommodate about a half-a-dozen servers and 5 IP addresses. That might be the next step, but we need to be absolutely certain that our needs will be met before we start opening up rack-space in the data center.

The format will be similar to the Stanford PET/CT competition I wrote about a while back, with the vendors processing data we provide on a real-time basis. We will give them a script to follow, so we can see the same things done on the different machines, and then of course there will be some time for the vendors to do their own thing.

The script is still in flux, but I have a number of things that we need to see, and a few that we would like to see. In no particular order, here's what's on the list so far:
  • One-button processing, or as near to this ideal as possible. Of course, there must be a way to go back and manually alter anything that needs altering.
  • To the greatest degree possible, the system must be operable/viewable from anywhere, and any platform (PACS station, laptop, iPhone, iPad, Android phone or tablet, and whatever else comes up in the near future.)
  • There must be complete and total integration with IMPAX 6.5 and beyond, our illustrious PACS.
  • Procedures will include (but certainly not be limited to):
    • Brain perfusion
    • PET/CT viewing
    • Full cardiac/coronary work-up
    • Virtual colonography
    • Bone subtraction/transparent/translucent rendering
    • AVI creation
Suggestions for other items are welcome, although vendors need to be circumspect on this.

In addition, we have been tempted by "dose reduction" or "denoising"software, which is included in some of the advanced packages. I've discussed the concept earlier, and frankly, I still don't like the idea of dropping the quality of a scan in hopes of rescuing it later. So, to me anyway, this will not be a critical component. If it comes with, fine, if it doesn't, also fine.

The tentative schedule for the shoot-out is set for early January. Ambulances will be at the ready for the fallen.

Tuesday, November 15, 2011

The Match Game

Once in a great while, something comes across my virtual e-mail desk that gets me excited, and when you reach my age, getting excited is rare and possibly dangerous. Nonetheless, when I saw what the folks from Blackford Analysis ( had to offer, I definitely got a thrill.

Blackford comes from outer space, almost literally. Their origins are in the astrophysics world, and their break-through technology is called MOPED:

Blackford Analysis’s core technology is MOPED, an algorithm developed in astrophysics to tackle analysis of immense datasets. The patented approach involves compressing the huge datasets while retaining all information needed to solve a problem – allowing speedups of many orders of magnitude over traditional techniques.

The technology comes from astronomical surveys, where instruments capture gigabytes of images per hour. This information is generally interpreted by comparison with models, essentially complex formulae driven by a set of parameters, which reproduce the observations.

Parameters might be the mass of a galaxy, or the distance it is from Earth, and there will be some combination of parameters that produces a modelled image that is very close to that actually seen through the telescope. Situations like this are called ‘parametric modelling problems’.

MOPED’s particular ability when solving such problems is that it speeds up the step that determines how well a given combination of parameters recreates the image.

After the initial compression, the time taken for each combination changes from being set by the number of pixels to being set by the number of parameters. If 10 parameters were to be determined by an image taken by a modern digital camera with 12 million pixels, the calculation would be more than one million times faster.

This means that problems that were too slow become possible, often solvable in real-time. As datasets become larger, and the cost of the hardware resources required to tackle them rocket, the case for MOPED is even more compelling: the powerful algorithm vastly reduces that hardware cost.
So what does this have to do with imaging?  It seems that we can apply the algorithm to matching volumes, such as two CT scans!
Developed by Blackford Analysis, the medical imaging technology makes it possible for radiologists to anatomically link small features such as lung nodules between studies for the first time within the PACS.

While the radiology imaging software will also align CT and MR from any part of the body, instant anatomical alignment in the chest is a major breakthrough, given respiratory movement and the requirement for a deformable registration.

Blackford Analysis’ technology greatly reduces the time it takes to compare current and prior studies, a drain of radiologist’s time as volumetric datasets increase in size and complexity and become ever more commonplace.

A key advantage of the software is that it designed for integration in the existing PACS environment so radiologists can use it without having to interrupt their natural review processes by moving to another workstation.

Crucially, the alignment is achieved without any alteration of the raw slice data so radiologists don't need to worry about the authenticity of what they are reviewing.
A video is worth at least 10,000 words:

Blackford is thinking outside the box.  In all of the other registration programs I've seen, an attempt is made to match the entire volume of the old study to the new. Because patients are not rigid (their bodies aren't, anyway) this doesn't work so well. Some software will attempt to distort the data-set to achieve a fit, which could conceivably distort the findings as well.  Blackford takes the novel and proper approach of an instantaneous point-to-point mapping, finding the exact spot on the old study that I'm seeing in the new exam.  Brilliant! That's really all we need in the end, isn't it? And it does appear to work quite well. And to have it actually integrated into the PACS viewer would be incredible.

I hope to meet with the folks from Blackwell at RSNA and see the thing live and in action.

PACS vendors: you WANT this in your product. You really do. Jump on it now.

Contact r