h a l f b a k e r y
add, search, annotate, link, view, overview, recent, by name, random
news, help, about, links, report a problem
or get an account
Every so often, people need to undergo one of the many
medical imaging procedures. There are numerous
techniques, from the common X-ray for bone fractures,
magnetic resonance imaging for abnormalities of soft
In the past, X-rays for example, relied upon large sheets
film which were looked at by a busy junior
doctor at the end of a 30hr shift, They looked at the
suspected area before declaring the metacarpal broken
the person a fool for hitting a wall. Nowadays, X-rays
be electronically displayed. Whereupon the suspected
is looked at, the metacarpal declared broken, and the
person declared a fool for hitting a wall. More advanced
imaging is handled in a similar way, although there is
often an imaging technician available to help
What links diverse medical imaging techniques, is that
they're often looking for something specific, like a
metacarpal or evidence of congenital abnormalities.
the tired junior doctor has confirmed a broken bone,
they're likely to carry on along their original plan in the
absence of any fragments or other related complications.
The electronic image is then filed away on a hard drive
somewhere until it is no longer needed, accidentally
deleted or distributed to the world as part of a colossal
data breach during the latest big budget IT failure.
As someone who spends a tremendous amount of time
analyzing imaging data, I'm acutely aware of how much
guided by what I am looking for. Often, quite glaringly
obvious phenomena are missed because you're simply not
looking for it. Alternatively, you may have learned that
spending half a day looking at B is somewhat detrimental
to your detailed analysis of A, so its consciously or
unconsciously ignored. A third way, is that you display
images in such a way as to maximize your chances of
noticing phenomenon A, while B disappears into the
I suspect similar things happen with medical imaging all
the time. Its easy to miss a grape seed sized tumour in
pancreas when you're a hepatologist looking for gall
If Amazon's Mechanical Turk is anything to go by, it's
surprisingly easy to get large numbers of people to
computer based tasks for little money. This is the model
that could be used.
Once electronic imaging data is collected, the data
be carefully stripped* of identifying data and uploaded
server. From here the imaging data may be analyzed by
freelance people from around the world. Any oddities
within the imaging data are then referred up to people
with some actual training. Initially, much dreadful dross
will be flagged up. Eventually however, individuals will
emerge with real talent, either generally or in specific
types of imaging. These people can gradually be
with progressive financial incentives. Soon they'll be
spotting real medical issues within the images and these
can be referred all the way along to the managing
physician. Often, these will simply confirm the problem
that the imaging was performed for. But every now and
then, they'll spot something the medical staff missed,
especially if several people flag the same thing in the
The best people to set this up would be the companies
make the equipment. The financial incentives would
be easily covered by the hospital who will be happy to
the extra business**. The companies can boast about
enhanced detection rates. Strangely, people will also do
out of curiosity, like with the planet-finding, or out of
some macabre fascination with broken metacarpals.
Perhaps people will try and cheat, using automated
analysis, but still, good luck to them.
*carefully, not like normal.
** assuming the US system of hospitals and insurance
companies looking for extra justification to screw each
||Reminds me of Eyewire, which is not at all this, but is
somewhat related. (Crowdsourced analysis of how nerves
are routed in the retina for connectome purposes)
||Stick it on the pile of future jobs for laid off accountants.
||//future jobs for laid off accountants// Accountancy - n., an inability to count.
||This is actually not such a bad idea.
||Genomic data might also benefit from this. Automation is much easier for genomic analysis, but enthusiastic amateurs might still make interesting findings, or develop excellent software.
||As another thought, anatomy's thought to be a bit of a dead
science, but every now and then there's a new nerve or
whatnot found. Shirley a great big sample size is the way to
go for better measurements/modest discoveries?
||I thought about using something similar to find petroleum from acoustic maps as well as computed image representations of oil fields. I thought perhaps even a handyphone app could have a training set where people could learn to recognize valuable squiggles (so to speak) at images then look through unprocessed images to find further valuable squiggles. While deep AI has outperformed humans at Go, crowdsourced petroleum finding might find lots of petroleum anyway.
||Also a 1/10% of 1% royalty from finding new petroleum could get hundreds of thousands of people doing this.
||If I understand that correctly, 10% is 0.1 of 1. So, 1/10% =
1/0.1. 1/0.1 is 10%. That's a hell of a finders royalty.
||[bs0u0155] noted. also, i liked it better before i changed it. talk about optimism!
||What I like most about this idea is that you've found two new ways to spell metacarpal.
||//found two new ways to spell metacarpal//
||ugh, well, the opportunities for novel research in the field
of anatomy are pretty slim. Fortunately, a quick change of
name and you have a whole new thing to study. If you'll
excuse me, I have to tend to my side business of re-labeling
tubes. Supplying antibodies to those unaware of protein
synonyms is a necessary service I provide to enable the re-
distribution of grant money away from the rich, feeble
minded or partially educated.
||I'd always assumed that alternative splicing only existed to fill all the synonyms.
||Interesting idea for the hobbyist, but I think I hear the malpractice lawyers sharpening their talons, or is that the metacarpal? Darn, where did I put that copy of Gray's Anatomy...
||Bunned halfway through for the prose alone.
||The danger or this "outsource medical imaging"
scheme is that there are very smart and very
skilled physicians who, by virtue of not being in
the US, are pain very little. If this crew gets the
power to read medical images it will be no time at
all before they are reading all the images, possibly
with one US radiologist to then gesture
approvingly. The other , non gesturing highly paid
US radiologists will be high and dry. They are a
savvy bunch themselves, these highly paid US
radiologists, and so watch carefully for any sign of
this outsourcing scheme and quash it accordingly.
||"Well, Mr. Steunkrantz, the bad news is that none of our crowdsourcers have found any abnormality to explain your symptoms or offer a therapeutic opportunity. The good news is that they've found Wally."