Visualizing the medical data explosion | Anders Ynnerman | TEDxGöteborg
-
0:03 - 0:06I will start by posing
a little bit of a challenge: -
0:07 - 0:10the challenge of dealing with data,
-
0:10 - 0:12data that we have to deal with
-
0:12 - 0:14in medical situations.
-
0:15 - 0:17It's really a huge challenge for us.
-
0:18 - 0:20And this is our beast of burden -
-
0:21 - 0:23this is a Computer Tomography machine,
-
0:23 - 0:25a CT machine.
-
0:25 - 0:27It's a fantastic device.
-
0:27 - 0:29It uses X-rays, X-ray beams,
-
0:29 - 0:32that are rotating very fast
around the human body. -
0:33 - 0:37And in just a few seconds
it scans off the whole body. -
0:37 - 0:39It takes about 30 seconds
to go through the whole machine -
0:39 - 0:42and is generating
enormous amounts of information -
0:42 - 0:44that comes out of the machine.
-
0:44 - 0:46So this is a fantastic machine
-
0:46 - 0:47that we can use
-
0:47 - 0:49for improving health care,
-
0:49 - 0:51but as I said,
it's also a challenge for us. -
0:51 - 0:54And the challenge is really found
in this picture here. -
0:54 - 0:56It's the medical data explosion
-
0:56 - 0:58that we're having right now.
-
0:58 - 0:59We're facing this problem.
-
0:59 - 1:01And let me step back in time.
-
1:02 - 1:05Let's go back a few years in time
and see what happened back then. -
1:05 - 1:07These machines that came out -
-
1:07 - 1:09they started coming in the 1970s -
-
1:09 - 1:12they would scan human bodies,
-
1:12 - 1:14and they would generate about 100 images
-
1:14 - 1:15of the human body.
-
1:15 - 1:17And I've taken the liberty,
just for clarity, -
1:18 - 1:20to translate that to data slices.
-
1:20 - 1:23That would correspond to about
50 megabytes of data, -
1:23 - 1:25which is small
-
1:25 - 1:27when you think about the data
we can handle today -
1:27 - 1:30just on normal mobile devices.
-
1:30 - 1:32If you translate that to phone books,
-
1:32 - 1:35it's about one meter of phone books
in the pile -
1:35 - 1:37that you can see down there to the left.
-
1:37 - 1:39Looking at what we're doing today
-
1:39 - 1:41with these machines that we have,
-
1:41 - 1:43we can, just in a few seconds,
-
1:43 - 1:45get 24,000 images out of a body,
-
1:45 - 1:48and that would correspond
to about 20 gigabytes of data, -
1:48 - 1:50or 800 phone books,
-
1:50 - 1:52and the pile would then be
200 meters of phone books. -
1:52 - 1:54What's about to happen -
-
1:54 - 1:56and we're seeing this; it's beginning -
-
1:56 - 1:58a technology trend
that's happening right now -
1:58 - 2:01is that we're starting to look
at time-resolved situations as well. -
2:01 - 2:04So we're getting the dynamics
out of the body as well. -
2:04 - 2:05And just assume
-
2:05 - 2:08that we will be collecting data
during five seconds, -
2:08 - 2:11and that would correspond
to one terabyte of data - -
2:11 - 2:13that's 800,000 books
-
2:13 - 2:15and 16 kilometers of phone books.
-
2:15 - 2:17That's one patient, one data set.
-
2:17 - 2:19And this is what we have to deal with.
-
2:19 - 2:22So this is really the enormous challenge
that we have. -
2:22 - 2:25And already today - this is 25,000 images.
-
2:25 - 2:27Imagine the days
-
2:27 - 2:29when we had radiologists doing this.
-
2:29 - 2:31They would put up 25,000 images,
-
2:31 - 2:34they would go like this,
"25,0000, okay, okay. -
2:34 - 2:36There is the problem."
-
2:36 - 2:38They can't do that anymore.
That's impossible. -
2:38 - 2:39So we have to do something
-
2:39 - 2:42that's a little bit more intelligent
than doing this. -
2:42 - 2:44So what we do is that we put
all these slices together. -
2:44 - 2:47Imagine that you slice your body
in all these directions, -
2:47 - 2:50and then you try to put
the slices back together again -
2:50 - 2:52into a pile of data, into a block of data.
-
2:52 - 2:54So this is really what we're doing.
-
2:54 - 2:58So this gigabyte or terabyte of data,
we're putting it into this block. -
2:58 - 2:59But of course, the block of data
-
2:59 - 3:01just contains the amount of X-ray
-
3:01 - 3:03that's been absorbed
in each point in the human body. -
3:03 - 3:06So what we need to do
is to figure out a way -
3:06 - 3:08of looking at the things
we do want to look at -
3:08 - 3:11and make things transparent
that we don't want to look at. -
3:11 - 3:13So transforming the data set
-
3:13 - 3:15into something that looks like this.
-
3:15 - 3:16And this is a challenge.
-
3:16 - 3:19This is a huge challenge
for us to do that. -
3:19 - 3:21Using computers, even though
they're getting faster -
3:21 - 3:23and better all the time,
-
3:23 - 3:25it's a challenge to deal
with gigabytes of data, -
3:25 - 3:27terabytes of data
-
3:27 - 3:30and extracting the relevant information.
-
3:30 - 3:31I want to look at the heart.
-
3:31 - 3:34I want to look at the blood vessels.
I want to look at the liver. -
3:34 - 3:36Maybe even find a tumor,
-
3:36 - 3:37in some cases.
-
3:38 - 3:41So this is where this little dear
comes into play. -
3:41 - 3:42This is my daughter.
-
3:42 - 3:45This is as of 9 a.m. this morning.
-
3:45 - 3:47She's playing a computer game.
-
3:47 - 3:48She's only two years old,
-
3:48 - 3:50and she's having a blast.
-
3:51 - 3:54So she's really the driving force
-
3:54 - 3:57behind the development
of graphics-processing units. -
3:57 - 3:59As long as kids are playing
computer games, -
3:59 - 4:02graphics is getting better
and better and better. -
4:02 - 4:04So please go back home,
tell your kids to play more games, -
4:04 - 4:06because that's what I need.
-
4:06 - 4:07So what's inside of this machine
-
4:07 - 4:10is what enables me to do
the things that I'm doing -
4:10 - 4:11with the medical data.
-
4:11 - 4:15So really what I'm doing is using
these fantastic little devices. -
4:15 - 4:16And you know, going back
-
4:16 - 4:19maybe 10 years in time
-
4:19 - 4:20when I got the funding
-
4:20 - 4:22to buy my first graphics computer -
-
4:22 - 4:24it was a huge machine.
-
4:24 - 4:27It was cabinets of processors
and storage and everything. -
4:28 - 4:30I paid about one million dollars
for that machine. -
4:30 - 4:34That machine is, today,
about as fast as my iPhone. -
4:36 - 4:39So every month there are new
graphics cards coming out, -
4:39 - 4:42and here is a few of the latest ones
from the vendors - -
4:42 - 4:45NVIDIA, ATI, Intel is out there as well.
-
4:45 - 4:47And you know, for a few hundred bucks
-
4:47 - 4:49you can get these things
and put them into your computer, -
4:49 - 4:52and you can do fantastic things
with these graphics cards. -
4:52 - 4:54So this is really what's enabling us
-
4:54 - 4:56to deal with the explosion
of data in medicine, -
4:57 - 4:59together with some really nifty work
-
4:59 - 5:00in terms of algorithms -
-
5:00 - 5:01compressing data,
-
5:01 - 5:05extracting the relevant information
that people are doing research on. -
5:05 - 5:08So I'm going to show you
a few examples of what we can do. -
5:10 - 5:13This is a data set that was captured
using a CT scanner. -
5:13 - 5:16You can see
that this is a full data [set]. -
5:16 - 5:19It's a woman. You can see the hair.
-
5:19 - 5:22You can see the individual structures
of the woman. -
5:22 - 5:25You can see that there is
[a] scattering of X-rays -
5:25 - 5:27on the teeth, the metal in the teeth.
-
5:27 - 5:30That's where those artifacts
are coming from. -
5:30 - 5:32But fully interactively
-
5:32 - 5:35on standard graphics cards
on a normal computer, -
5:35 - 5:37I can just put in a clip plane.
-
5:37 - 5:39And of course all the data is inside,
-
5:39 - 5:42so I can start rotating,
I can look at it from different angles, -
5:42 - 5:45and I can see
that this woman had a problem. -
5:45 - 5:47She had a bleeding up in the brain,
-
5:47 - 5:49and that's been fixed with a little stent,
-
5:49 - 5:51a metal clamp that's tightening up
the vessel. -
5:51 - 5:53And just by changing the functions,
-
5:53 - 5:56then I can decide
what's going to be transparent -
5:56 - 5:58and what's going to be visible.
-
5:58 - 6:00I can look at the skull structure,
-
6:00 - 6:03and I can see that, okay, this is where
they opened up the skull on this woman, -
6:03 - 6:05and that's where they went in.
-
6:05 - 6:06So these are fantastic images.
-
6:06 - 6:08They're really high resolution,
-
6:08 - 6:10and they're really showing us
what we can do -
6:10 - 6:13with standard graphics cards today.
-
6:14 - 6:16Now we have really made use of this,
-
6:16 - 6:19and we have tried to squeeze a lot of data
-
6:19 - 6:20into the system.
-
6:20 - 6:23And one of the applications
that we've been working on - -
6:23 - 6:26and this has gotten a little bit
of traction worldwide - -
6:26 - 6:28is the application of virtual autopsies.
-
6:28 - 6:30So again, looking at very,
very large data sets, -
6:30 - 6:33and you saw those full-body scans
that we can do. -
6:33 - 6:35We're just pushing the body
through the whole CT scanner, -
6:35 - 6:38and just in a few seconds
we can get a full-body data set. -
6:39 - 6:41So this is from a virtual autopsy.
-
6:41 - 6:44And you can see how
I'm gradually peeling off. -
6:44 - 6:47First you saw the body bag
that the body came in, -
6:47 - 6:49then I'm peeling off the skin -
you can see the muscles - -
6:49 - 6:52and eventually you can see
the bone structure of this woman. -
6:53 - 6:55Now at this point,
I would also like to emphasize -
6:55 - 6:58that, with the greatest respect
-
6:59 - 7:01for the people
that I'm now going to show - -
7:01 - 7:04I'm going to show you
a few cases of virtual autopsies - -
7:04 - 7:06so it's with great respect for the people
-
7:06 - 7:08that have died under violent circumstances
-
7:08 - 7:10that I'm showing these pictures to you.
-
7:11 - 7:13In the forensic case -
-
7:13 - 7:15and this is something
-
7:15 - 7:17- there's been
approximately 400 cases so far -
7:17 - 7:19just in the part of Sweden
that I come from -
7:19 - 7:21that has been undergoing virtual autopsies
-
7:21 - 7:23in the past four years.
-
7:23 - 7:26So this will be the typical
workflow situation. -
7:26 - 7:28The police will decide -
-
7:28 - 7:30in the evening,
when there's a case coming in - -
7:30 - 7:34they will decide, okay, this is a case
where we need to do an autopsy. -
7:34 - 7:37So in the morning, in between six
and seven in the morning, -
7:37 - 7:39the body is then transported
inside of the body bag -
7:39 - 7:40to our center
-
7:40 - 7:43and is being scanned
through one of the CT scanners. -
7:43 - 7:45And then the radiologist,
together with the pathologist -
7:45 - 7:47and sometimes the forensic scientist,
-
7:47 - 7:49looks at the data that's coming out,
-
7:49 - 7:50and they have a joint session.
-
7:50 - 7:54And then they decide what to do
in the real physical autopsy after that. -
7:55 - 7:58Now looking at a few cases,
-
7:58 - 8:00here's one of the first cases that we had.
-
8:00 - 8:03You can really see the details
of the data set. -
8:03 - 8:04It's very high-resolution,
-
8:04 - 8:06and it's our algorithms that allow us
-
8:06 - 8:08to zoom in on all the details.
-
8:08 - 8:10And again, it's fully interactive,
-
8:10 - 8:13so you can rotate
and you can look at things in real time -
8:13 - 8:15on these systems here.
-
8:15 - 8:17Without saying too much about this case,
-
8:17 - 8:19this is a traffic accident,
-
8:19 - 8:21a drunk driver hit a woman.
-
8:21 - 8:24And it's very, very easy to see
the damages on the bone structure. -
8:24 - 8:27And the cause of death is the broken neck.
-
8:27 - 8:30And this woman
also ended up under the car, -
8:30 - 8:32so she's quite badly beaten up
-
8:32 - 8:33by this injury.
-
8:34 - 8:37Here's another case, a knifing.
-
8:37 - 8:39And this is also again showing us
what we can do. -
8:39 - 8:41It's very easy to look at metal artifacts
-
8:42 - 8:43that we can show inside of the body.
-
8:43 - 8:47You can also see some
of the artifacts from the teeth - -
8:47 - 8:49that's actually the filling
of the teeth - -
8:49 - 8:52but because I've set
the functions to show me metal -
8:52 - 8:54and make everything else transparent.
-
8:54 - 8:57Here's another violent case.
This really didn't kill the person. -
8:57 - 8:59The person was killed
by stabs in the heart, -
8:59 - 9:01but they just deposited the knife
-
9:01 - 9:04by putting it through one of the eyeballs.
-
9:05 - 9:07Here's another case.
-
9:07 - 9:08It's very interesting for us
-
9:08 - 9:11to be able to look
at things like knife stabbings. -
9:11 - 9:14Here you can see
that knife went through the heart. -
9:14 - 9:16It's very easy to see
how air has been leaking -
9:16 - 9:18from one part to another part,
-
9:18 - 9:21which is difficult to do in a normal,
standard, physical autopsy. -
9:21 - 9:23So it really, really helps
-
9:23 - 9:25the criminal investigation
-
9:25 - 9:26to establish the cause of death,
-
9:26 - 9:30and in some cases also directing
the investigation in the right direction -
9:30 - 9:32to find out who the killer really was.
-
9:33 - 9:35Here's another case
that I think is interesting. -
9:35 - 9:37Here you can see a bullet
-
9:37 - 9:40that has lodged
just next to the spine on this person. -
9:41 - 9:44And what we've done is that we've turned
the bullet into a light source, -
9:44 - 9:46so that bullet is actually shining,
-
9:46 - 9:49and it makes it really easy
to find these fragments. -
9:49 - 9:51During a physical autopsy,
-
9:51 - 9:54if you actually have to dig through
the body to find these fragments, -
9:54 - 9:56that's actually quite hard to do.
-
9:58 - 10:00One of the things
that I'm really, really happy -
10:00 - 10:02to be able to show you here today
-
10:02 - 10:04is our virtual autopsy table.
-
10:04 - 10:06It's a touch device that we have developed
-
10:06 - 10:10based on these algorithms,
using standard graphics GPUs. -
10:10 - 10:14We have this table and it's standing
in the corner over here, -
10:14 - 10:17so in the break, after this talk,
after the session, -
10:17 - 10:20you're most welcome to come over
and have a look at the table. -
10:20 - 10:21It actually looks like this,
-
10:21 - 10:24just to give you a feeling
for what it looks like. -
10:25 - 10:28Here's a little video
that should be going. -
10:28 - 10:30OK, so this is the table.
-
10:30 - 10:33It really just works like a huge iPhone.
-
10:34 - 10:35So we've implemented
-
10:35 - 10:38all the gestures you can do on the table,
-
10:38 - 10:42and you can think of it
as an enormous touch interface. -
10:42 - 10:44So if you were thinking of buying an iPad,
forget about it. -
10:44 - 10:47This is what you want instead.
(Laughter) -
10:48 - 10:51Steve, I hope you're listening to this,
all right. -
10:51 - 10:53So it's a very nice little device.
-
10:53 - 10:55So if you have the opportunity,
please try it out. -
10:55 - 10:58It's really a hands-on experience.
-
11:00 - 11:04So it gained some traction,
and we're trying to roll this out -
11:04 - 11:07and trying to use it
for educational purposes, -
11:07 - 11:08but also, perhaps in the future,
-
11:08 - 11:11in a more clinical situation.
-
11:11 - 11:14There's a YouTube video
that you can download and look at this, -
11:14 - 11:17if you want to convey
the information to other people -
11:17 - 11:18about virtual autopsies.
-
11:18 - 11:20Okay, now that we're talking about touch,
-
11:20 - 11:22let me move on to really "touching" data.
-
11:22 - 11:24And this is a bit of science fiction now,
-
11:24 - 11:27so we're moving into really the future.
-
11:28 - 11:31This is not really what
the medical doctors are using right now, -
11:31 - 11:32but I hope they will in the future.
-
11:32 - 11:35So what you're seeing
on the left is a touch device. -
11:35 - 11:37It's a little mechanical pen
-
11:37 - 11:40that has very, very fast
step motors inside of the pen. -
11:40 - 11:42And so I can generate a force feedback.
-
11:42 - 11:44So when I virtually touch data,
-
11:44 - 11:47it will generate forces in the pen,
so I get a feedback. -
11:48 - 11:49So in this particular situation,
-
11:50 - 11:51it's a scan of a living person.
-
11:52 - 11:54I have this pen, and I look at the data,
-
11:54 - 11:56and I move the pen towards the head,
-
11:56 - 11:58and all of a sudden I feel resistance.
-
11:58 - 12:00So I can feel the skin.
-
12:00 - 12:03If I push a little bit harder,
I'll go through the skin, -
12:03 - 12:05and I can feel the bone structure inside.
-
12:05 - 12:08If I push even harder,
I'll go through the bone structure, -
12:08 - 12:11especially close to the ear
where the bone is very soft. -
12:11 - 12:14And then I can feel the brain inside,
and this will be the slushy like this. -
12:14 - 12:16So this is really nice.
-
12:16 - 12:19And to take that even further,
this is a heart. -
12:19 - 12:22And this is also due to these
fantastic new scanners, -
12:22 - 12:24that just in 0.3 seconds,
-
12:24 - 12:26I can scan the whole heart,
-
12:26 - 12:28and I can do that with time resolution.
-
12:28 - 12:30So just looking at this heart,
-
12:30 - 12:32I can play back a video here.
-
12:32 - 12:34And this is Karljohan,
one of my graduate students -
12:34 - 12:36who's been working on this project.
-
12:36 - 12:38And he's sitting there
in front of the Haptic device, -
12:38 - 12:40the force feedback system,
-
12:40 - 12:42and he's moving his pen towards the heart,
-
12:42 - 12:44and the heart is now
beating in front of him, -
12:44 - 12:46so he can see how the heart is beating.
-
12:46 - 12:49He's taken the pen, and he's moving it
towards the heart, -
12:49 - 12:50and he's putting it on the heart,
-
12:50 - 12:53and then he feels the heartbeats
from the real living patient. -
12:53 - 12:55Then he can examine
how the heart is moving. -
12:55 - 12:57He can go inside,
push inside of the heart, -
12:57 - 13:00and really feel how the valves are moving.
-
13:00 - 13:03And this, I think, is really the future
for heart surgeons. -
13:03 - 13:06I mean it's probably the wet dream
for a heart surgeon -
13:06 - 13:09to be able to go inside
of the patient's heart -
13:09 - 13:11before you actually do surgery,
-
13:11 - 13:13and do that
with high-quality resolution data. -
13:13 - 13:15So this is really neat.
-
13:16 - 13:19Now we're going even further
into science fiction. -
13:19 - 13:22And we heard a little bit
about functional MRI. -
13:23 - 13:26Now this is really an interesting project.
-
13:26 - 13:28MRI is using magnetic fields
-
13:28 - 13:29and radio frequencies
-
13:29 - 13:32to scan the brain,
or any part of the body. -
13:32 - 13:34So what we're really getting out of this
-
13:34 - 13:37is information
of the structure of the brain, -
13:37 - 13:39but we can also measure the difference
-
13:39 - 13:42in magnetic properties of blood
that's oxygenated -
13:42 - 13:45and blood that's depleted of oxygen.
-
13:45 - 13:46That means that it's possible
-
13:46 - 13:49to map out the activity of the brain.
-
13:49 - 13:52So this is something
that we've been working on. -
13:52 - 13:54And you just saw Motts
the research engineer, there, -
13:54 - 13:56going into the MRI system,
-
13:56 - 13:58and he was wearing goggles.
-
13:58 - 14:00So he could actually see
things in the goggles. -
14:00 - 14:03So I could present things to him
while he's in the scanner. -
14:03 - 14:05And this is a little bit freaky,
-
14:05 - 14:07because what Motts is seeing
is actually this. -
14:07 - 14:09He's seeing his own brain.
-
14:10 - 14:12So Motts is doing something here,
-
14:12 - 14:15and probably he is going like this
with his right hand, -
14:15 - 14:17because the left side is activated
-
14:17 - 14:19on the motor cortex.
-
14:19 - 14:21And then he can see that at the same time.
-
14:21 - 14:23These visualizations are brand new.
-
14:23 - 14:26And this is something
we've been researching for a little while. -
14:26 - 14:29This is another sequence of Motts' brain.
-
14:29 - 14:32And here we asked Motts
to calculate backwards from 100. -
14:32 - 14:34So he's going "100, 97, 94."
-
14:34 - 14:36And then he's going backwards.
-
14:36 - 14:38And you can see how
the little math processor -
14:38 - 14:40is working up here in his brain
-
14:40 - 14:41and is lighting up the whole brain.
-
14:41 - 14:44Well this is fantastic.
We can do this in real time. -
14:44 - 14:47We can investigate things.
We can tell him to do things. -
14:47 - 14:48You can also see that his visual cortex
-
14:48 - 14:50is activated in the back of the head,
-
14:50 - 14:53because that's where he's seeing,
he's seeing his own brain. -
14:53 - 14:55And he's also hearing our instructions
-
14:55 - 14:57when we tell him to do things.
-
14:57 - 14:58This is relly nice.
-
14:58 - 15:01The signal is really deep
inside of the brain as well, -
15:01 - 15:02and it's shining through,
-
15:02 - 15:04because all of the data
is inside this volume. -
15:04 - 15:07And in just a second here you will see
- okay, here. -
15:07 - 15:09Motts, now move your left foot.
-
15:09 - 15:11So he's going like this.
-
15:11 - 15:12For 20 seconds he's going like that,
-
15:12 - 15:14and all of a sudden it lights up up here.
-
15:14 - 15:17So we've got motor cortex activation
up there. -
15:17 - 15:18So this is really, really nice,
-
15:18 - 15:20and I think this is a great tool.
-
15:20 - 15:23And connecting also
with the previous talk here, -
15:23 - 15:25this is something
that we could use as a tool -
15:25 - 15:26to really understand
-
15:26 - 15:29how the neurons are working,
how the brain is working, -
15:29 - 15:32and we can do this with very,
very high visual quality -
15:32 - 15:33and very fast resolution.
-
15:34 - 15:36Now we're also having
a bit of fun at the center. -
15:36 - 15:40So this is a CAT scan -
Computer Aided Tomography. -
15:40 - 15:44So this is a lion from the local zoo
-
15:44 - 15:47outside of Norrkoping in Kolmarden, Elsa.
-
15:47 - 15:49So she came to the center,
-
15:49 - 15:51and they sedated her
-
15:51 - 15:53and then put her straight
into the scanner. -
15:53 - 15:56And then, of course, I get
the whole data set from the lion. -
15:56 - 15:58And I can do very nice images like this.
-
15:58 - 16:01I can peel off the layer of the lion.
-
16:01 - 16:02I can look inside of it.
-
16:02 - 16:05And we've been experimenting with this.
-
16:05 - 16:07And I think this is a great application
-
16:07 - 16:09for the future of this technology,
-
16:09 - 16:13because there's very little known
about the animal anatomy. -
16:13 - 16:16What's known out there for veterinarians
is kind of basic information. -
16:16 - 16:18We can scan all sorts of things,
-
16:18 - 16:20all sorts of animals.
-
16:20 - 16:23The only problem
is to fit it into the machine. -
16:23 - 16:25So here's a bear.
-
16:25 - 16:27It was kind of hard to get it in.
-
16:27 - 16:30And the bear is a cuddly, friendly animal.
-
16:31 - 16:33And here it is.
Here is the nose of the bear. -
16:33 - 16:36And you might want to cuddle this one,
-
16:36 - 16:39until you change the functions
and look at this. -
16:39 - 16:41So be aware of the bear.
-
16:41 - 16:42So with that,
-
16:42 - 16:44I'd like to thank all the people
-
16:44 - 16:47who have helped me
to generate these images. -
16:47 - 16:49It's a huge effort
that goes into doing this, -
16:49 - 16:52gathering the data
and developing the algorithms, -
16:52 - 16:54writing all the software.
-
16:54 - 16:56So, some very talented people.
-
16:56 - 17:00My motto is always, I only hire people
that are smarter than I am -
17:00 - 17:02and most of these are smarter than I am.
-
17:02 - 17:03So thank you very much.
-
17:03 - 17:06(Applause)
- Title:
- Visualizing the medical data explosion | Anders Ynnerman | TEDxGöteborg
- Description:
-
Today medical scans produce thousands of images and terabytes of data for a single patient in mere seconds, but how do doctors parse this information and determine what's useful? Scientific visualization expert Anders Ynnerman shows us sophisticated new tools - like virtual autopsies - for analyzing this myriad data, and a glimpse at some sci-fi-sounding medical technologies in development. This talk contains some graphic medical imagery.
- Video Language:
- English
- Team:
- closed TED
- Project:
- TEDxTalks
- Duration:
- 17:23
Ivana Korom edited English subtitles for Visualizing the medical data explosion | Anders Ynnerman | TEDxGöteborg | ||
Ivana Korom edited English subtitles for Visualizing the medical data explosion | Anders Ynnerman | TEDxGöteborg | ||
Ivana Korom edited English subtitles for Visualizing the medical data explosion | Anders Ynnerman | TEDxGöteborg | ||
TED Translators admin edited English subtitles for Visualizing the medical data explosion | Anders Ynnerman | TEDxGöteborg | ||
TED Translators admin edited English subtitles for Visualizing the medical data explosion | Anders Ynnerman | TEDxGöteborg | ||
Ivana Korom approved English subtitles for Visualizing the medical data explosion | Anders Ynnerman | TEDxGöteborg | ||
Ivana Korom accepted English subtitles for Visualizing the medical data explosion | Anders Ynnerman | TEDxGöteborg | ||
TED Translators admin edited English subtitles for Visualizing the medical data explosion | Anders Ynnerman | TEDxGöteborg |