Friday, December 18, 2015

Frasier

Hey, Dad!


What, Frasier?


There isn't a lot of time, Dad, and there's a lot to say. The vet will be here pretty soon, you know.


Vet?


Yeah, Dad. I'm almost 17 years old, damn old for a Jack Russell Terrier, and I'm not doing so hot. I know you see it when you look at me.


Yeah, Fras. I know. I had hoped you didn't understand.


I put on that dumb face so you won't worry about me. But it's OK, Dad. Really. I'm ready. I can barely breathe, I can't eat, I can't stand up anymore. I'm not having a very good day, and I'm tired. Really, really tired. It's time. We all know it.


I'm sorry, Frasier. We don't want to let go of you. You aren't hurting, are you?


Nah. Just uncomfortable. But this whole  dying thing is darn undignified, you know? Why you humans keep yourselves going when you've reached this state is beyond me. If you really loved your loved ones like you love me, you would let them go in peace. Personally, I'm looking forward to it.


Frasier...


Cut it out, Dad. No tears, please. OK, maybe a few if you must. I know you and Mom and the kids (and even that little devil dog Sophie) love me. It's been a damn good life. I don't have any regrets and you shouldn't either. Really. Loved our walks, loved sleeping in the bed with you, licking your pillow (even when you yelled at me for it). I really liked the frozen yogurt on my birthday, and the occasional McDonald's cheeseburger and fries. It's all good. It really was.


You are a very good boy Frasier...


Yeah, I tried my best. At least you never played that stupid human game of "Who's a Good Boy?" I can rest knowing that I was.


Will we see you again?


Ha. That's the Big Question, isn't it? Wish I could tell you. Jewish law is kinda vague on that. Supposedly, there are 5 kinds of souls. Animals have the most basic version, the life-force. That goes back to G-d. Humans have all 5, and they say go to a different part of Heaven.


I hate to disagree with you and the Rabbis, Frasier, but I'm pretty convinced you have a human soul, too.


Hope you're right, Dad. I've always thought so, but I'm just a dog. If so, we will meet again. But even if not, I'll be back with G-d which is a fair trade-off, don't you think?


We love you Fras... Godspeed.


Love you too, Dad. Don't forget me, but don't grieve too much. I'll be fine. I promise. And you will too.

Sunday, December 06, 2015

Exhibits At An Exhibition: PACS, HYPOTHETICALLY-Speaking

Having little time at this year's RSNA, I was able to only briefly stop in to see friends at the Visage and lifeIMAGE booths. Both products show nice incremental improvements. Visage offers deconstructed PACS, with better collation of prior studies in this incarnation. It is a viable alternative to a full-fledged PACS, IF your IT folks can handle the concept. Big IF for some. Again, there is no worklist option included; "That would make us a PACS company!" So what's wrong with that?

lifeIMAGE continues to progress, now with even better connectivity. See this nice summary from Imaging Technology News for details. Many PACS vendors offer some form of image sharing in competition with lI, but the latter does it better. I've said it before and I'll say it again:  NOT using an image-sharing system is MALPRACTICE. Period. If you never believe anything else I write, believe that.

I have stated elsewhere that if I were to need a new PACS, my list would be short, based on experience, discussion, research, gestalt, instinct, hubris, and maybe a little luck: Merge, McKesson, Intelerad, and Sectra. Unfortunately, I only had time to visit the first two.

In addition to the Code Name: Avicenna project, Merge offers the latest version of PACS, Merge 7.1, to be released in the Spring of 2016. This latest descendant of the venerable AMICAS PACS (Version 3.7 is still in use at Mass General!) includes a number of tidbits gleaned from Emageon and DR, the systems Merge has assimilated over the years. The major improvement concerns the worklist, which can be used in composite mode, with up to 10 separate worklists operating on-screen at once. And unlike a certain system we know and love, this has no IMPAXT upon the speed of the client. Rules for the next study to be read can be specified so the most appropriate (and urgent) study is the next one to be read. (The next iteration, still a Work In Progress, will further assign studies based on RVU, subspecialty, etc, and should truly be Universal across the enterprise.)

My Merge-based IT people will be pleased to know that user-management is now templated, allowing quicker assignments of permissions and so forth. And the slippery menu-driven preferences is now on a single pop-up window. There is user-level XML integration which could, for example, be used to keep windows open or closed after completing dictation.

There is a new Macro Manager that will combine multiple repetitive actions. There is advanced breast-tomosynthesis with slab-viewing and position markers, as well as PET/CT fusion.

From DR comes embedded dictation with Speech Recognition (which I won't use!), and further improvements on an already excellent hanging protocol functionality. I'm excited to say that there will no longer be the same degree of dependence on series labels (which I cannot get the techs to standardize for love, money, or prolonged tantrums); one can specify, for example, what T2 means on an MRI from Scanner Vendors X, Y, and Z, and then key a hanging protocol to show all the T2 images. You get the idea.

I proposed the HYPOTHETICAL scenario of a failing Big-Iron PACS and asked what Merge could do in such a HYPOTHETICAL situation. HYPOTHETICALLY speaking, Merge could either provide an overlay to the database of the HYPOTHETICALLY failing PACS, assuming that component retained its integrity. Alternatively, Merge could move in as the primary PACS in such a HYPOTHETICAL situation, using DICOM Q/R to retrieve priors in the near term while migrating the entire database in the background. Fairly standard, although the ability to front for a failing system might not be as facile with the other vendors. Should the users of the HYPOTHETICALLY impaired PACS have a Merge PACS somewhere, that existing system could perhaps be used as a secondary server. Also, it would be easier to create a unified worklist for all the PACS in an enterprise if they happened to be from Merge. Food for thought.

McKesson is one of those rare PACS for which we hear minimal if any complaints, even fewer than for Merge and the others. No doubt there are some cranky rads out there who could find something wrong with it, but they are a minority indeed. McKesson PACS is now known as McKesson Radiology, a regression from the old Horizon moniker. The company has a much greater presence in my home state than I knew; they might actually have the majority of PACS here, or at least a significant pleurality.

McKesson is also proud of its hanging protocols, although the emphasis in the demonstration seemed to be on the fact that once they are set up, one wouldn't need to change them. But drag-and-drop and scripting is available for those who want to tweak things. As with Merge, they are not based on series descriptors. If your mouse wheel can tilt to either side, this motion can shift sequential hanging protocols.

There is a nice embedded advanced imaging module that does "~80%" of what one gets with an external TeraRecon, most everything but vessel fly-through. It even has lesion tracking. Tomosynthesis and PET/CT viewers are fully integrated.

Add-on modules include "Imaging Fellow" which can open RIS/EMR data, and is supposed to be able to open "any other exam from any accessible database." This would allow for data mining if you were so inclined.

PeerVue was purchased by McKesson years ago and is now called Conserus. (I would have gone a different direction...sounds too much like Cons 'R Us.) This critical-result software sends texts and emails and other reminders about things that need to be seen NOW.

The "Intelligent Worklist" allows prioritization by rules as we saw with Merge PACS (although the AMICAS/Merge worklist continues to have by far the best visual clues.) This module will monitor foreign PACS, allowing a sort of unified worklist, but still launches the foreign PACS client. I think it is capable of opening the study in your McKesson PACS if you have one, but I wasn't completely clear on that one.

A collaborative tool allows instant pinging of a colleague, referrer, etc, to get them to view a study. Right now, this spawns a second viewer program, not the main PACS viewer itself. This is to be incorporated into the main viewer eventually.

For those who work from or view from home, the main client can be used, although a VPN is required. It was unknown as to whether SSL would suffice.

When asked the HYPOTHETICAL question about the HYPOTHETICAL scenario in which a HYPOTHETICAL PACS needed replacing, the McKesson folks offered up similar solutions. The Intelligent Worklist could probably access the HYPOTHETICALLY failing PACS, as long as one had McKesson for the actual reads. Of course, they would be willing to migrate the old database in such a HYPOTHETICAL situation, and McKesson has in-house capability to do so.

With the observations now documented, I shall now stray into opinion territory. Emphasis on opinion.  Or really just me babbling on.

I have no clue at this point in time if I might be involved in any HYPOTHETICAL PACS replacements. I suppose I would suggest sending RFP's to the four companies mentioned above if that HYPOTHETICAL ever occurred. My good friend Mike Cannavo, the One and Only PACSman, has some very wise and mildly cynical ideas about RFP's. Adding in my own sarcasm, basically the IT folks don't know the questions to ask on an RFP but think they do. I have just one very easy question:  "Does the damn thing WORK?" Vendors will of course respond in the affirmative, but this really requires a far more complex answer with quite a few nuances and shades of gray. Perhaps the better question would be: "Does the damn thing work the way I want/need it to work?" I would love to hear the response to that one.

Mike noted an uptick in the number of vendors offering PACS and PACS-related wares at this RSNA:
So what was new? There are more PACS vendors for sure. I would venture to say that at least 70% of the vendors at RSNA 2015 had something PACS or PACS-related. It's just a matter of time before former PACSman award winner Ernie's Welding and Fabricating becomes Ernie's Pipes and PACS.

Even though we have had some market consolidation with high-profile mergers and acquisitions, for every one vendor that gets gobbled up, it seems like four new vendors appear. How many of the newbies will be here next year is anyone's guess, but if history repeats itself and 10% remain, it's a lot.
The problem is, even though some might have an innovative feature here and there, these tiny vendors probably won't be around in a few years, and many that are maintain their viability because their products are cheap (in price, but probably quality as well) and they appeal to small operations being run by those who don't understand what it is they are buying.

Ironically, the Powers That Be at one of our places blackballed AMICAS years ago because a consulting company (someone you hire and pay $50,000 to tell you what you already think you know) told them it was "too small" and would likely be acquired. Well, they were half-right. IBM now owns Merge, which owns AMICAS, but instead of quashing it, ala GE, the acquisition has strengthened the company and the product. GE assimilated DynamicImaging, among others, cannibalizing its PACS components into the Universal Disappointment. DI no longer exists in any form. Merge, however, is still alive, being billed as "an IBM company". AMICAS PACS lives on, and continues to grow. My friends from Emageon and DR Systems might roll their eyes a bit, but at least the best of their PACS components live on within Merge PACS, and credit is given to the predecessors as is due. I'm good with that.

McKesson Radiology is in many ways at the other end of the spectrum, being one of the last Big-Iron companies. Their product list contains hundreds of entries, and PACS is far from the largest offering. Still, there is a lot to be said for having a HUGE presence in the health-care marketplace, and to have a product with relatively few complaints. (However, I probably don't even have to say that simply buying from a huGE company doesn't guarantee a quality product.) Supposedly the rule at McK is that a call to the support center MUST be answered within 3 rings. I can't vouch for what happens after that. Many have said McKesson's architecture is a generation behind, and that there are too many different clients for different purposes, but I didn't discuss that with them at this point.

I have had very nice chats with Sectra and Intelerad folks over the years. In fact, Sectra invited me to come to their headquarters in Sweden, but I could only go in July, and Sweden apparently closes for vacation that month. My contact at Sectra has since left for a different company, as folks in this business are wont to do. I do keep in touch with some good friends at Intelerad as well. It is of note that both companies demurred somewhat as to what could be accomplished when given bits and pieces of the HYPOTHETICAL failing-PACS situation.

I'm in my eleventh year of blogging about PACS, and the more things change, the more they stay the same. What worked before still works and works better, and what didn't work still doesn't work, and may even be worse. (And the attitude of IT doesn't seem to be much different at all.) Some companies listen better than others, and some even listen to the right people, the end-users of their wares, and not just the people with the checkbook.

Remember Dalai's First Law of PACS: PACS IS the radiology department. It has to work. And not just HYPOTHETICALLY.

Saturday, December 05, 2015

Exhibits At An Exhibition: Siemens Press Conference



"Pictures at an Exhibition" Courtesy TzviErez

I'm back from a rather brief trip to Chicago and RSNA. I had two days to see stuff and get some edumacation, as we say down here in the South, and I tried to make the most of it.

Educationally, I used my limited time to concentrate on PET and thyroid/parathyroid imaging. I come out reassured that we are doing things correctly. I'm still a little confused as to the best application of SPECT/CT to parathyroid imaging, so I'll probably be doing some experimentation when we finally get the darn thing sometime early next year. One presentation claimed better accuracy with good old pin-hole/planar imaging than with SPECT/CT. We'll see.

I began my 48-hour RSNA marathon early Monday at the Siemens Press Conference. Somehow, Siemens still thinks I'm some sort of journalist, which speaks more toward my friendship with people who decide such things than their better judgement. Not to worry, though, the room was filled with real reporters from real publications, who will properly convey the things correspondents are supposed to write. But you might want to question their judgement: some of them said they were readers of this blog, or at least familiar with me, and if I were them I probably wouldn't admit it. One VERY wise lady from a VERY respected publication did note the iconoclastic tone I generally manifest, proving that she really does read this. Thanks, Ms. C.P.!! I'm going to tattle, though. Some of the reporters were on their laptops doing things other than paying attention to the presentations, and one reporter who used to work for Siemens asked some very long and barely comprehensible questions at the end. Which were answered quite throughly.

Having been a regular attendee at the Siemens event, I was surprised this year to see new faces. In years past, Dr. Hermann Requardt, (PhD in Physics!) CEO of Siemens Healthcare, presided over the meeting, with Dr. Gregory Sorensen, (Neuroradiologist) CEO of Siemens Healthcare North America, in the supporting role. They are no longer with us, at least no longer visible, having been replaced respectively by Dr. Bernd Montag, also a physicist, and David Pacitti, recently of Abbott Labs. Requardt is now on the board of Bruker, Inc., and is the new Chairman of the Board of SuperSonic Imagine; Sorenson was removed just in October.  HMMMMMM.... Perhaps their vision didn't match the current trends, but I can't say I heard anything much different than last year in that regard. Back in February, Siemens announced the change of CEO's. Joe Kaeser, President and CEO of Siemens AG, said: “Mr. Requardt and the managers and employees of Healthcare can be quite proud of their highly successful work together over the past years. I have the greatest respect for Mr. Requardt’s decision to make way for a generation change. We are now setting up Healthcare as a separately managed business within Siemens in order to pave the way for an equally successful future in a highly dynamic market and innovation- driven environment. This is now the task of Bernd Montag, Michael Reitermann and Michael Sen. They will have the full support of the Managing Board and their direct partner, Board member Siegfried Russwurm, who worked in the company’s former Medical Engineering and Medical Solutions units for ten years.”

I could report chapter and verse of what was said, but I'll leave that to the real reporters. What I will convey is my impression as the only physician in the room. (At last year's event, I was one of two along with Dr. Sorensen.)

Technologically, there was a smattering of this new or upgraded scanner or that, the standard stuff. Dr. Montag announced 510K approval of Siemens CT scanners for lung screening programs, and the new "teamplay" software for data transparency and availability (acknowledging the ubiquity of tablets in the healthcare environment). The new HELX touch-control ultrasound scanners should reduce operator variance thorough streamlined user interface. It's supposed to be easy for inter operative use by surgeons. Thanks, Siemens. We also note the advanced robotic and even 3D capability of the new MultiTom Rax X-ray room. Good incremental improvements, all. No mention of PACS, advanced visualization, etc.

The main message I got from the hour-long session is that Siemens understands the changes in healthcare, both here and pending, and wants to help physicians navigate them successfully, "Enabling Healthcare Providers Worldwide" in their words. The flip-side is that Siemens is invested in these changes, assumes they will come, and is resigned to the fact that they ARE coming. The transformation process to the new reality has three components:

  1. Consolidation of Providers 
  2. Industrialization--Dr. Montag: "Medicine is not an art anymore. It must be managed like a company in a controlled fashion." How sad.
  3. Managing Health--i.e., the transition from fee-for-service to value models
The process supposedly is inexorable, like the Law of Gravity. 

Diagnostics, particularly imaging are pillars of healthcare, and have been almost from the beginning. In fact, Roentgen himself was an early Siemens customer, and the company archives contain a letter of complaint from the man himself, noting the rather high equipment costs. Some things never change. Indeed, Siemens has been in on quite a few innovations in medical imaging, PET, PET/CT, PET/MRI, dual-source CT, etc.

Dr. Montag tells us that "90% of medical decisions are based on technologies in the Siemens portfolio." This, I think, is a little misleading. We could say that 95% of the world is lit by technology in the GE portfolio, the remaining 5% still using fire, but that really doesn't get us anywhere. I might have phrased it differently, but we get it.

Further examples were given of how Siemens can and will holistically improve health care, radiation therapy guidance, laboratory productivity, and triaging patients. Siemens will help us with standardization, consulting, and a world-wide network geared to mastering the digital transformation, leading to better outcomes at lower costs. 

In the end, 10% of the costs of healthcare relate to diagnosis, and our value thus depends on early diagnosis which could reduce the price of the remaining 90%. That's a better definition of value than I've heard to this point.

Still, I'm personally not as convinced as the good folks at Siemens that this value thing is permanent. Much will depend on the upcoming elections among other things. But I do understand the need to conform to the environment in which they wish to sell their wares. No doubt if fee-for-service comes back, Siemens will exercise its flexibility once again, and pivot back to whatever worked in the old days. Like selling scanners to doctors' offices. Just like GE. Still, if your going to scan, you might as well have the best scanner. 

Thursday, December 03, 2015

Code Name: Avicenna
The Future In Progress

One of my Radiology professors back in residency, a very wise man, had a saying: "The more dogmatic you get, the more likely you will be wrong."

In the medical business, there is a tie for the three most important little words: "I was wrong," competes nicely with "I don't know." (If you were wondering, the four scariest words in the radiological lexicon are: "You read a scan...")

The Future has a way of sneaking up on us, and occasionally biting us on the behind. In my youth, I thought for example, that age 50 was a long way off. Now I'm well into that decade of life, and the 60's are looming. As Steve Miller put it, "Time keeps on slippin', slippin', slipping', into the Future..."

All this leads us to the fact that I was dead wrong about something futuristic, something I thought we wouldn't see until many years from now. Something I saw this week at RSNA at the Merge booth. I was quite adamant that it would not be possible for a computer to read scans and such for at least 5-10 years. What I saw proves me wrong, or at least indicates that being dogmatic led me down the wrong path yet again. I was blindsided by a Work In Progress titled "Code Name: Avicenna", a peek into the future at some very disruptive technology (I use that term with all due respect and awe) brought about by the new consortium between Merge, now a wholly-owned subsidiary of IBM, and IBM Watson Health.

Let us speak a moment about Avicenna, whom I'm assuming is the inspiration behind the Code Name: Avicenna project. Since you are reading my blog, you are of course quite intelligent and well-educated, and thus you have probably heard of Avicenna. I, however, had not, so I turned to the Wiki:
Avicenna (c. 980 – June 1037) was a Persian polymath who is regarded as one of the most significant thinkers and writers of the Islamic Golden Age. Of the 450 works he is known to have written, around 240 have survived, including 150 on philosophy and 40 on medicine.

His most famous works are The Book of Healing – a philosophical and scientific encyclopedia, and The Canon of Medicine – a medical encyclopedia, which became a standard medical text at many medieval universities and remained in use as late as 1650.

Besides philosophy and medicine, Avicenna's corpus includes writings on astronomy, alchemy, geography and geology, psychology, Islamic theology, logic, mathematics, physics and poetry.

Image courtesy StatusMind.com
Pretty amazing guy. Now personally, I would have gone with "Code Name: Maimonides",  after Moses Maimonides, an equally famous physician of the middle ages, or at least with his acronymed nickname Rambam (for "Rabbeinu Moshe Ben Maimon"). But then this isn't my project, is it?

The choice of the code name for this Watson-based process clearly tells us where we are going; Watson is learning medicine, and doing so at a very young age, as did Avicenna who became a physician in his teens.

IBM Watson, image courtesy IBM.com

Everyone has heard of IBM's Watson. Watson thinks, or at least simulates it nicely:
We produce over 25 quintillion bytes of data everyday and 80% of it is unstructured. Therefore, it’s invisible to current technology. IBM Watson is a cognitive system that can understand that data, learn from it and reason through it. That’s how industries as diverse as healthcare, retail, banking and travel are using Watson to reshape their industries. Watson is designed to take data in all its forms—including unstructured—and understand it, reason through it and learn from it. In a sense, Watson can think. When Watson thinks with you, you can outthink.



I cannot proceed without mentioning the old joke about the movie 2001: A Space Odyssey. The rogue self-aware computer, "HAL 9000" was supposedly a joke on IBM, the acronym being one letter off, yes? Arthur C. Clarke (or was it Stanley Kubrick?) denied this, claiming that HAL stood for Heuristic ALgorithm, and in fact IBM did help considerably with the movie details.

And this brings us to IBM's acquisition of Merge, which I blogged about when it was announced. It has since been finalized:


IBM itself whet our appetite for what was and is to come on the Watson Health website:
IBM today announced that Watson will gain the ability to “see” by bringing together Watson’s advanced image analytics and cognitive capabilities with data and images obtained from Merge Healthcare Incorporated’s medical imaging management platform. IBM plans to acquire Merge, a leading provider of medical image handling and processing, interoperability and clinical systems designed to advance healthcare quality and efficiency, in an effort to unlock the value of medical images to help physicians make better patient care decisions.

Merge’s technology platforms are used at more than 7,500 U.S. healthcare sites, as well as most of the world’s leading clinical research institutes and pharmaceutical firms to manage a growing body of medical images. The vision is that these organizations could use the Watson Health Cloud to surface new insights from a consolidated, patient-centric view of current and historical images, electronic health records, data from wearable devices and other related medical data, in a HIPAA-enabled environment.
I can't quite shake the thought of HAL, I mean Watson, watching us, but in a good way:


While it is just a Work In Progress, Code Name: Avicenna presents the first steps in realizing the unified goals of teaching Watson to see radiologic images (among others) and putting that, ummm, knowledge to good use for our patients. And you can see it in action today. Here is Merge's description of the demonstration, i.e., Code Name: Avicenna...

Merge PACS™ workstation viewer and IBM Watson Health – a vision for how to help radiologists with clinical decision making

Radiologists and cardiologists today have to view large amounts of imaging data relatively quickly leading to eye fatigue. Further, they may have limited access to clinical information relying mostly on their visual interpretation of imaging studies for their diagnostic decisions.  In this demo, we present a futuristic workstation for radiologists where their normal viewing of imaging studies is augmented with clinical and imaging summaries to help their clinical decision-making. This technology could assist by running in the background to collect relevant clinical, textual and imaging patient data from electronic health records systems. It could then analyze multimodal content to detect anomalies and summarize the patient record, collecting relevant information pertinent to a chief complaint. The results of anomaly detection would then be fed into a reasoning engine which uses evidence from both patient-independent clinical knowledge and large-scale patient-driven similar patient statistics to arrive at potential differential diagnosis to help radiologists’ clinical decision making. Compact clinical summaries, along with the findings from imaging studies, would be available both for simultaneous viewing and export as a DICOM SR report.

The demo will show our vision of this futuristic technology using the Merge PACS™ workstation. The radiologist will open an exam from the Universal Worklist (UWL).  When the exam is opened, both the PACS viewer and the IBM Watson Health work in progress will be launched in separate monitors to show respective content. The ultimate output from the tool in the form of a pre-populated radiology report will then be presented to the radiologist to review and consider in making his or her decisions.

DISCLAIMER: The capability demonstrated here is for DEMONSTRATION PURPOSES ONLY. The capability is in the research and development phase and is not available for any use, commercial or non-commercial. Any statements and claims related to the capability are aspirational only. The case study in this demonstration is a hypothetical case study using fictitious medical information and do not represent an actual medical case. The results contained in this demonstration were obtained in a controlled environment and represent a vision of possible future technology. The demo will show our vision of this futuristic technology using the Merge PACS™ workstation.
The punch-line to Code Name: Avicenna is quite simple. IT WORKS (something typical of Merge products, but sadly not for others in the same industry). A case was presented to Watson consisting of history, physical findings, lab values, and a CT. Well, it was a CT-pulmonary arteriogram, so Watson had a little clue there. The demonstration progressed to show Watson's integration of the data into a cloud-display of likely diagnoses. He, OK, it, proceeded to analyze the CT, showing outlines of his its regions of interest. And Watson found the majority of the emboli on the very positive sample scan. Watson's ROI's matched those of the training radiologist quite well. And it then displayed dozens of priors from its memory with similar findings. The most likely differential became "pulmonary embolism", which was of course correct.

As an aside, many have wondered just how Watson acquires the images upon which he it trained. I had asked this question of the Merge execs early on, but they weren't ready to answer until now. Basically, the scans are collected with secondary use rights, to which the institutions providing them must agree. The images and reports and other data are anonymized, so there is no privacy problem. To date, several Big Name operations have signed on to this effort, including many you might have heard of. (I'm not supposed to name names as yet, but I, for one, was quite impressed with the players so far.) I'll be glad to sign mine over, too. There simply is no downside to doing so. There are 30 BILLION images in Merge's iConnect cloud service already. That should keep Watson busy for a millisecond or two, once they are allowed to be, shall we say, assimilated?

Now you might say that Computer Aided Diagnosis is already here. You would be missing the point. CAD doesn't learn. Watson, being a cognitive computer, learns. It learns the way I learned to read CT's. Hopefully it will read them better than I do. Think of it this way... I went to college to learn the chemistry and physics (and for me, engineering and computer science) needed to understand higher concepts. I went on to medical school to learn how the body is put together with all that chemistry and physiology and stuff. I learned where the pulmonary arteries were, and what happens if a clot gets lodged in one. In radiology residency, I learned how it looks on a scan if that happens. (Well, to be fair, the scanners weren't fast enough for CTPA grams back then, and so we learned the concept with conventional arteriography, but you get the idea.)

One physician was overheard saying something like, "Bah. My first-year residents could get that one." Yes...A COMPUTER can match the achievement of a human that has gone through college and medical school. Let this sink in.  Code Word: Avicenna shows us THAT A COMPUTER IN THE EARLIEST STAGES OF LEARNING HOW TO READ COMPLEX IMAGING STUDIES CAN MATCH A FIRST-YEAR RADIOLOGY RESIDENT.

This, people, is the epitome of disruptive technology. This is a sea-change in how radiology will manifest in the future. The implications here are staggering. To me, this is MUCH more important and noteworthy than an extra Tesla on a magnet (although a Tesla in my garage would be most appreciated) or an extra hundred slices on a CT. Code Name: Avicenna represents the most important development in our field in a very, very long time. This is a fundamental change in the way we do things. It assists the radiologist, allowing him/her to perform at the highest possible level, but does not replace us. Not for the foreseeable future, anyway.

I was right on that one, at least.

I have seen the future, and its Code Name is Avicenna. Seriously. Trust me, I'm a doctor! But if you don't believe me, just ask Watson.