in 1895 a man took a picture on hand this hand picture was so mind-boggling
this hand picture was so mind-boggling
this hand picture was so mind-boggling that he won a Nobel Prize and it changed
that he won a Nobel Prize and it changed
that he won a Nobel Prize and it changed the world his name Wilhelm roentgen and
the world his name Wilhelm roentgen and
the world his name Wilhelm roentgen and I present to you the first medical image
I present to you the first medical image
I present to you the first medical image ever taken this is the world’s first
ever taken this is the world’s first
ever taken this is the world’s first x-ray this may not look very impressive
x-ray this may not look very impressive
x-ray this may not look very impressive to you today but at the time it was
to you today but at the time it was
to you today but at the time it was genius because this was the first time
genius because this was the first time
genius because this was the first time we could look inside of the human body
we could look inside of the human body
we could look inside of the human body without having to slice someone open and
without having to slice someone open and
without having to slice someone open and indeed medical imaging has changed the
indeed medical imaging has changed the
indeed medical imaging has changed the face of medicine in the last hundred
face of medicine in the last hundred
face of medicine in the last hundred years since roentgen imaging still
years since roentgen imaging still
years since roentgen imaging still represents one of the fastest growing
represents one of the fastest growing
represents one of the fastest growing sources of medical data let me ask you a
sources of medical data let me ask you a
sources of medical data let me ask you a question how many of you have gotten a
question how many of you have gotten a
question how many of you have gotten a mammogram a cat scan an MRI an x-ray can
mammogram a cat scan an MRI an x-ray can
mammogram a cat scan an MRI an x-ray can I see by a show of hands please that’s
I see by a show of hands please that’s
I see by a show of hands please that’s incredible because it seems that almost
incredible because it seems that almost
incredible because it seems that almost everyone here has benefited from medical
everyone here has benefited from medical
everyone here has benefited from medical imaging technology in some way or
imaging technology in some way or
imaging technology in some way or another
another
another you see we begin to realize that imaging
you see we begin to realize that imaging
you see we begin to realize that imaging can sometimes reveal a disease even
can sometimes reveal a disease even
can sometimes reveal a disease even before you feel it and for diseases like
before you feel it and for diseases like
before you feel it and for diseases like cancer the earlier we diagnosed the more
cancer the earlier we diagnosed the more
cancer the earlier we diagnosed the more likely you’ll survive this is why we
likely you’ll survive this is why we
likely you’ll survive this is why we started screening people who exhibit no
started screening people who exhibit no
started screening people who exhibit no signs or symptoms of disease pap smears
signs or symptoms of disease pap smears
signs or symptoms of disease pap smears mammograms colonoscopies all examples of
mammograms colonoscopies all examples of
mammograms colonoscopies all examples of screening tests that are recommended to
screening tests that are recommended to
screening tests that are recommended to everyone at certain ages we know that
everyone at certain ages we know that
everyone at certain ages we know that diagnosing a disease early saves lives
diagnosing a disease early saves lives
diagnosing a disease early saves lives it reduces treatment costs and it
it reduces treatment costs and it
it reduces treatment costs and it reduces soum
reduces soum
reduces soum much patient suffering unfortunately
much patient suffering unfortunately
much patient suffering unfortunately though most diseases are still diagnosed
though most diseases are still diagnosed
though most diseases are still diagnosed at advanced stages you see the problem
at advanced stages you see the problem
at advanced stages you see the problem with detecting these diseases early is
with detecting these diseases early is
with detecting these diseases early is that as you turn back the clock visible
that as you turn back the clock visible
that as you turn back the clock visible evidence of disease becomes smaller and
evidence of disease becomes smaller and
evidence of disease becomes smaller and smaller until it vanishes before the
smaller until it vanishes before the
smaller until it vanishes before the naked eye so realistically how early can
naked eye so realistically how early can
naked eye so realistically how early can we detect these diseases there’s hope
we detect these diseases there’s hope
we detect these diseases there’s hope because it turns out that there is an
because it turns out that there is an
because it turns out that there is an invisible side to imaging small changes
invisible side to imaging small changes
invisible side to imaging small changes that your eyes can’t see still exist and
that your eyes can’t see still exist and
that your eyes can’t see still exist and in my research I’ve shown that these
in my research I’ve shown that these
in my research I’ve shown that these hidden patterns can sometimes be decoded
hidden patterns can sometimes be decoded
hidden patterns can sometimes be decoded with the help of a computer and
with the help of a computer and
with the help of a computer and sometimes these patterns contain secrets
sometimes these patterns contain secrets
sometimes these patterns contain secrets about the imminence of disease that we
about the imminence of disease that we
about the imminence of disease that we never knew so let me give you an example
never knew so let me give you an example
never knew so let me give you an example osteoarthritis is one of those diseases
osteoarthritis is one of those diseases
osteoarthritis is one of those diseases that we can’t detect until the damage
that we can’t detect until the damage
that we can’t detect until the damage has been done in this room more than one
has been done in this room more than one
has been done in this room more than one in ten of us will develop osteoarthritis
in ten of us will develop osteoarthritis
in ten of us will develop osteoarthritis in our knee this is the disease in which
in our knee this is the disease in which
in our knee this is the disease in which the thin cushion of cartilage between
the thin cushion of cartilage between
the thin cushion of cartilage between two bones falls apart causing bone to
two bones falls apart causing bone to
two bones falls apart causing bone to grind painfully on bone oh it makes me
grind painfully on bone oh it makes me
grind painfully on bone oh it makes me cringe just thinking about it but today
cringe just thinking about it but today
cringe just thinking about it but today doctors can’t see osteoarthritis until
doctors can’t see osteoarthritis until
doctors can’t see osteoarthritis until after bone damage and pain have
after bone damage and pain have
after bone damage and pain have developed now about to show you an x-ray
developed now about to show you an x-ray
developed now about to show you an x-ray that shows some very subtle signs of
that shows some very subtle signs of
that shows some very subtle signs of bone damage so be sure to look this is
bone damage so be sure to look this is
bone damage so be sure to look this is what your x-ray might look like the
what your x-ray might look like the
what your x-ray might look like the first time you’re diagnosed with
first time you’re diagnosed with
first time you’re diagnosed with osteoarthritis but there’s evidence that
osteoarthritis but there’s evidence that
osteoarthritis but there’s evidence that the disease begins long before that
the disease begins long before that
the disease begins long before that inside the cartilage so why can’t we
inside the cartilage so why can’t we
inside the cartilage so why can’t we just look at the cartilage to diagnose
just look at the cartilage to diagnose
just look at the cartilage to diagnose the disease so let’s take a trip back in
the disease so let’s take a trip back in
the disease so let’s take a trip back in time and let’s actually take a look some
time and let’s actually take a look some
time and let’s actually take a look some images of cartilage these are magnetic
images of cartilage these are magnetic
images of cartilage these are magnetic resonance images or MRIs
resonance images or MRIs
resonance images or MRIs of knee cartilage these are all healthy
of knee cartilage these are all healthy
of knee cartilage these are all healthy people each scan belongs to a different
people each scan belongs to a different
people each scan belongs to a different subject the different colors here
subject the different colors here
subject the different colors here represent the different ingredients that
represent the different ingredients that
represent the different ingredients that make up cartilage and we know that three
make up cartilage and we know that three
make up cartilage and we know that three years down the line one of these groups
years down the line one of these groups
years down the line one of these groups will receive a diagnosis of
will receive a diagnosis of
will receive a diagnosis of osteoarthritis but the other group won’t
osteoarthritis but the other group won’t
osteoarthritis but the other group won’t and the question is which group is which
and the question is which group is which
and the question is which group is which you see the problem is that our eyes
you see the problem is that our eyes
you see the problem is that our eyes can’t seem to detect
can’t seem to detect
can’t seem to detect a difference between these groups of
a difference between these groups of
a difference between these groups of patients even experts can’t tell what’s
patients even experts can’t tell what’s
patients even experts can’t tell what’s wrong here so does that mean that three
wrong here so does that mean that three
wrong here so does that mean that three years before bone damage develops
years before bone damage develops
years before bone damage develops there’s nothing to see in the cartilage
there’s nothing to see in the cartilage
there’s nothing to see in the cartilage or could we possibly find evidence of
or could we possibly find evidence of
or could we possibly find evidence of early disease that eludes the naked eye
early disease that eludes the naked eye
early disease that eludes the naked eye with the help of a computer ten years
with the help of a computer ten years
with the help of a computer ten years ago I started studying signals signals
ago I started studying signals signals
ago I started studying signals signals are the way that computers understand
are the way that computers understand
are the way that computers understand and process the world and I wanted to
and process the world and I wanted to
and process the world and I wanted to teach a computer to recognize patterns
teach a computer to recognize patterns
teach a computer to recognize patterns and medical images the same way that
and medical images the same way that
and medical images the same way that your personal assistant Syrian Alexa can
your personal assistant Syrian Alexa can
your personal assistant Syrian Alexa can recognize your voice today by using
recognize your voice today by using
recognize your voice today by using something called machine learning the
something called machine learning the
something called machine learning the basic premise behind machine learning is
basic premise behind machine learning is
basic premise behind machine learning is to program a computer that can learn on
to program a computer that can learn on
to program a computer that can learn on its own with experience so the way that
its own with experience so the way that
its own with experience so the way that it works is that we feed in the images
it works is that we feed in the images
it works is that we feed in the images and whether that person goes on to
and whether that person goes on to
and whether that person goes on to develop osteoarthritis three years down
develop osteoarthritis three years down
develop osteoarthritis three years down the line and the computer sips through
the line and the computer sips through
the line and the computer sips through the images to try to determine whether
the images to try to determine whether
the images to try to determine whether there is a pattern that can
there is a pattern that can
there is a pattern that can differentiate osteoarthritis progresses
differentiate osteoarthritis progresses
differentiate osteoarthritis progresses from healthy people in my research I
from healthy people in my research I
from healthy people in my research I developed a technique called transport
developed a technique called transport
developed a technique called transport based morphometry which teaches the
based morphometry which teaches the
based morphometry which teaches the computer to learn interrelationships
computer to learn interrelationships
computer to learn interrelationships between pixels rather than trying to
between pixels rather than trying to
between pixels rather than trying to focus on finding one particular pixel
focus on finding one particular pixel
focus on finding one particular pixel within
within
within the image and the true elegance of this
the image and the true elegance of this
the image and the true elegance of this technique is that transport based
technique is that transport based
technique is that transport based morphometry can come back and teach us
morphometry can come back and teach us
morphometry can come back and teach us the patterns that the computer has
the patterns that the computer has
the patterns that the computer has learned okay so at this point you’re all
learned okay so at this point you’re all
learned okay so at this point you’re all probably dying to know whether the
probably dying to know whether the
probably dying to know whether the computer can teleport these images that
computer can teleport these images that
computer can teleport these images that we couldn’t teleport right so it turns
we couldn’t teleport right so it turns
we couldn’t teleport right so it turns out that on an image of knee cartilage
out that on an image of knee cartilage
out that on an image of knee cartilage that the computer has never seen before
that the computer has never seen before
that the computer has never seen before it can predict whether that person goes
it can predict whether that person goes
it can predict whether that person goes on to develop osteoarthritis three years
on to develop osteoarthritis three years
on to develop osteoarthritis three years down the line with 86 percent accuracy
and because these machines learn with
and because these machines learn with experience they’ll only get better and
experience they’ll only get better and
experience they’ll only get better and better as we feed in more scams now
better as we feed in more scams now
better as we feed in more scams now remember that doctors today have no way
remember that doctors today have no way
remember that doctors today have no way of diagnosing osteoarthritis three years
of diagnosing osteoarthritis three years
of diagnosing osteoarthritis three years prior to symptoms imagine what three
prior to symptoms imagine what three
prior to symptoms imagine what three years means in a person’s life if I knew
years means in a person’s life if I knew
years means in a person’s life if I knew that I would develop osteoarthritis
that I would develop osteoarthritis
that I would develop osteoarthritis three years from now I would take steps
three years from now I would take steps
three years from now I would take steps today to try to stave off the disease
today to try to stave off the disease
today to try to stave off the disease for as long as possible
okay now you’re probably wondering well
okay now you’re probably wondering well what is the computer seeing that we
what is the computer seeing that we
what is the computer seeing that we can’t see right well these images are
can’t see right well these images are
can’t see right well these images are computer-generated MRIs and the red here
computer-generated MRIs and the red here
computer-generated MRIs and the red here indicates the presence of water which we
indicates the presence of water which we
indicates the presence of water which we already know but what we didn’t know was
already know but what we didn’t know was
already know but what we didn’t know was that what the computer can use to
that what the computer can use to
that what the computer can use to diagnose osteoarthritis in the future
diagnose osteoarthritis in the future
diagnose osteoarthritis in the future is the diffusion of water you see to the
is the diffusion of water you see to the
is the diffusion of water you see to the far left we see an image of a person is
far left we see an image of a person is
far left we see an image of a person is completely healthy and the water here is
completely healthy and the water here is
completely healthy and the water here is evenly distributed throughout the
evenly distributed throughout the
evenly distributed throughout the cartilage on the far right we see an
cartilage on the far right we see an
cartilage on the far right we see an image of a person who goes on to develop
image of a person who goes on to develop
image of a person who goes on to develop osteoarthritis three years from now and
osteoarthritis three years from now and
osteoarthritis three years from now and the water pulls to the center of the
the water pulls to the center of the
the water pulls to the center of the cartilage just as potholes in the road
cartilage just as potholes in the road
cartilage just as potholes in the road accumulate water the pooling of water
accumulate water the pooling of water
accumulate water the pooling of water suggests that there’s a weakening of
suggests that there’s a weakening of
suggests that there’s a weakening of cartilage at that location and it’s
cartilage at that location and it’s
cartilage at that location and it’s incredible that this is the first time
incredible that this is the first time
incredible that this is the first time we can see early evidence of disease in
we can see early evidence of disease in
we can see early evidence of disease in the cartilage even though it’s been
the cartilage even though it’s been
the cartilage even though it’s been there the whole time on literally
there the whole time on literally
there the whole time on literally million
million
million of scans that physicians have seen we
of scans that physicians have seen we
of scans that physicians have seen we can finally see these changes through
can finally see these changes through
can finally see these changes through the eyes of a computer teaching us what
the eyes of a computer teaching us what
the eyes of a computer teaching us what to look for now you’re probably
to look for now you’re probably
to look for now you’re probably wondering why do we need to look through
wondering why do we need to look through
wondering why do we need to look through the eyes of a computer why couldn’t we
the eyes of a computer why couldn’t we
the eyes of a computer why couldn’t we see this on our own to which I would
see this on our own to which I would
see this on our own to which I would answer that remember that everyone’s
answer that remember that everyone’s
answer that remember that everyone’s knees a little bit different so when you
knees a little bit different so when you
knees a little bit different so when you look at a picture of knee cartilage your
look at a picture of knee cartilage your
look at a picture of knee cartilage your eyes become saturated with the normal
eyes become saturated with the normal
eyes become saturated with the normal variability that can happen from person
variability that can happen from person
variability that can happen from person to person but when the computer looks at
to person but when the computer looks at
to person but when the computer looks at the image it can really zero in on
the image it can really zero in on
the image it can really zero in on Stevan subtle differences in water
Stevan subtle differences in water
Stevan subtle differences in water content so this is why the computer can
content so this is why the computer can
content so this is why the computer can recognize early signs of disease while
recognize early signs of disease while
recognize early signs of disease while your eyes can’t cracking this puzzle was
your eyes can’t cracking this puzzle was
your eyes can’t cracking this puzzle was no easy feat science is built on
no easy feat science is built on
no easy feat science is built on accumulated knowledge and I’d like to
accumulated knowledge and I’d like to
accumulated knowledge and I’d like to thank my collaborators and colleagues I
thank my collaborators and colleagues I
thank my collaborators and colleagues I could not have done this without them
could not have done this without them
could not have done this without them early detection of osteoarthritis was a
early detection of osteoarthritis was a
early detection of osteoarthritis was a great starting place for me because for
great starting place for me because for
great starting place for me because for me it highlighted the power of machine
me it highlighted the power of machine
me it highlighted the power of machine learning to be able to push our human
learning to be able to push our human
learning to be able to push our human capabilities we could finally find
capabilities we could finally find
capabilities we could finally find things that we never knew to look for
things that we never knew to look for
things that we never knew to look for and we never even knew existed and to
and we never even knew existed and to
and we never even knew existed and to think of the myriad diseases where we
think of the myriad diseases where we
think of the myriad diseases where we can apply this technique today we don’t
can apply this technique today we don’t
can apply this technique today we don’t understand how many diseases arise and
understand how many diseases arise and
understand how many diseases arise and develop particularly in the brain
develop particularly in the brain
develop particularly in the brain Alzheimer’s autism schizophrenia are
Alzheimer’s autism schizophrenia are
Alzheimer’s autism schizophrenia are examples but in the future we may be
examples but in the future we may be
examples but in the future we may be able to understand how these diseases
able to understand how these diseases
able to understand how these diseases start and identify new targets for
start and identify new targets for
start and identify new targets for treatment today we can’t diagnose
treatment today we can’t diagnose
treatment today we can’t diagnose diseases until after symptoms develop
diseases until after symptoms develop
diseases until after symptoms develop and by then it might be too late in the
and by then it might be too late in the
and by then it might be too late in the future we might be able to diagnose
future we might be able to diagnose
future we might be able to diagnose diseases before they develop and we
diseases before they develop and we
diseases before they develop and we might have the opportunity to halt the
might have the opportunity to halt the
might have the opportunity to halt the disease before it even begins I’m
disease before it even begins I’m
disease before it even begins I’m working to get this technology in the
working to get this technology in the
working to get this technology in the hands of your doctors within the next 10
hands of your doctors within the next 10
hands of your doctors within the next 10 years but for that what needs to happen
years but for that what needs to happen
years but for that what needs to happen first because these machines learn with
first because these machines learn with
first because these machines learn with experience
experience
experience we need vast amounts of patient data to
we need vast amounts of patient data to
we need vast amounts of patient data to ensure that these computers become
ensure that these computers become
ensure that these computers become smarter and more accurate in diagnosing
smarter and more accurate in diagnosing
smarter and more accurate in diagnosing fortunately this computer lives in our
fortunately this computer lives in our
fortunately this computer lives in our hospitals today second we need to build
hospitals today second we need to build
hospitals today second we need to build a community of people who can accelerate
a community of people who can accelerate
a community of people who can accelerate this work and bring benefits to patients
this work and bring benefits to patients
this work and bring benefits to patients sooner rather than later
sooner rather than later
sooner rather than later just as in 1895 with the first rent
just as in 1895 with the first rent
just as in 1895 with the first rent Gunnar Graham the face of Medicine is
Gunnar Graham the face of Medicine is
Gunnar Graham the face of Medicine is about to change again because this is
about to change again because this is
about to change again because this is the first time we can see not the
the first time we can see not the
the first time we can see not the visible but the invisible changes in the
visible but the invisible changes in the
visible but the invisible changes in the human body that allow us to diagnose a
human body that allow us to diagnose a
human body that allow us to diagnose a disease even before it develops now all
disease even before it develops now all
disease even before it develops now all we need is curiosity and an open mind
we need is curiosity and an open mind
we need is curiosity and an open mind thank you
thank you
thank you [Applause]
[Applause]
[Applause] [Music]
”
Be First to Comment