[00:00.000 --> 00:08.180]  So our next speaker is from NYU Tandon School of Engineering, from the Digital Future Lab.
[00:09.100 --> 00:16.780]  His focus for this talk will be using engineering and AI to build the next gen of smart scopes
[00:16.780 --> 00:19.340]  capable of diagnostic support.
[00:19.700 --> 00:26.660]  And fun little fact, on his spare time, he does 3D print graffiti artists in the style
[00:26.660 --> 00:28.660]  of green army men.
[00:33.260 --> 00:41.380]  So presenting their talk, microscopes are stupid, I agree, here is Lou Auguste.
[00:46.700 --> 00:51.600]  Hello everybody, good morning, good morning, thanks for coming to see this speech on microscopes
[00:51.600 --> 00:52.580]  are stupid.
[00:52.900 --> 00:58.680]  My name is Lou Auguste, I work at NYU Tandon School of Engineering in their future lab,
[00:58.680 --> 01:04.200]  so it's really, I'm an entrepreneur in residence there, they incubate my company, been running
[01:04.200 --> 01:08.020]  it there for three years now, and we work on solving this problem.
[01:08.160 --> 01:12.040]  So just a little bit before we get started, we've won some awards over the last couple
[01:12.040 --> 01:12.600]  of years.
[01:12.600 --> 01:16.120]  We won the ASME award for best hardware prototype in 2015.
[01:16.540 --> 01:20.620]  Last year we were nominated for science startup of the year by this competition out in Germany
[01:20.620 --> 01:22.280]  called Falling Walls.
[01:22.400 --> 01:28.160]  We won the Indian government's endowment for science research last year, and this year
[01:28.160 --> 01:32.100]  we're finalists for Qualcomm's prize for design in India.
[01:32.420 --> 01:39.100]  I published my methods in the British Medical Journal in 2015 on how to use smartphones
[01:39.100 --> 01:46.320]  to create whole slide images, and I did a pre-clinical validation study of that information
[01:46.880 --> 01:51.920]  in 2016, which I presented at USCAP, which is the United States and Canada Anatomical
[01:51.920 --> 01:53.480]  Pathologist Society.
[01:53.940 --> 01:57.560]  And this year we received IRB approval to do our clinical validation study, which I'm
[01:57.560 --> 01:58.960]  writing up right now.
[02:00.180 --> 02:02.720]  So yes, microscopes are stupid.
[02:02.720 --> 02:04.460]  I said it, and that's it.
[02:04.560 --> 02:09.260]  If you look at this microscope here, it's such a dinosaur that it's not even connected
[02:09.260 --> 02:10.240]  to the internet.
[02:13.360 --> 02:17.740]  So basically the problem is microscopes are dependent on the operator, and who's operating
[02:17.740 --> 02:18.840]  that microscope.
[02:19.100 --> 02:23.500]  And the problem that we're facing is as we look out at more and more of the healthcare
[02:23.500 --> 02:29.040]  landscape in the world, we find that there are things called healthcare deserts.
[02:29.040 --> 02:34.260]  These are places in America, the developing world, where options for healthcare don't
[02:34.260 --> 02:35.200]  exist.
[02:35.400 --> 02:36.860]  And it's not that they don't have microscopes.
[02:36.860 --> 02:37.940]  They have microscopes.
[02:37.940 --> 02:40.860]  They don't have anyone that could help them do diagnosis.
[02:41.680 --> 02:47.980]  So this is very true, as I said, in Kentucky, just as true as it is in Haiti, just as true
[02:47.980 --> 02:49.220]  as it is in India.
[02:50.760 --> 02:55.220]  So, before we go forward, I want to give a shout out to my boy, Anton van Leeuwenhoek.
[02:56.260 --> 02:58.980]  He's like the G of microscopes.
[02:59.020 --> 03:05.980]  So basically, he was born in the 1500s, and 40 years before he was born, they had created
[03:05.980 --> 03:07.620]  the compound microscope.
[03:08.500 --> 03:13.360]  Leeuwenhoek was a tradesman, and he was actually into glassworking.
[03:13.360 --> 03:15.180]  He didn't have any advanced degrees.
[03:15.180 --> 03:17.120]  He didn't have a PhD.
[03:17.120 --> 03:19.740]  So he was eliminated from a lot of the science community.
[03:20.120 --> 03:25.740]  But what he did was he created, with his knowledge of glassblowing or glassmaking, he created
[03:25.740 --> 03:27.260]  this microscope here.
[03:27.360 --> 03:31.880]  And this microscope had a magnification of over 200 times magnification.
[03:32.200 --> 03:36.140]  Up to that point, they had already invented the compound microscope, which is very similar
[03:36.140 --> 03:38.660]  to what we see today in any laboratory.
[03:38.760 --> 03:43.120]  But that only had a magnification of 20 to 30 times magnification.
[03:43.640 --> 03:47.400]  So van Leeuwenhoek was definitely one of the first disruptors.
[03:47.460 --> 03:52.540]  And he's also considered the father of microbiology, because of what he was able to see through
[03:52.540 --> 03:54.280]  his microscope that he created.
[03:54.440 --> 03:59.380]  And in fact, it wasn't really until the 1800s that they made any advancements past what
[03:59.380 --> 04:01.120]  he made with this microscope here.
[04:02.500 --> 04:04.640]  So also, humans are stupid.
[04:04.680 --> 04:11.560]  Because when we're given the task, humans get tired, and they miss things.
[04:11.560 --> 04:14.780]  And diagnosis itself depends on memory.
[04:15.160 --> 04:20.480]  So you probably can't see this right here, because the screen's a little bit contrasty.
[04:20.620 --> 04:25.460]  But if you were looking for cancer on this thing, there's actually a monkey in the upper
[04:25.460 --> 04:30.480]  right-hand corner of the lung that most people miss when they're looking for cancer.
[04:30.540 --> 04:34.260]  So I'm not sure if you could see that here, but that's usually a good example of how people
[04:34.260 --> 04:38.900]  miss things that are obvious when they're doing something that's repetitive.
[04:39.560 --> 04:45.180]  So a little history on telepathology, which is sort of what we do.
[04:45.420 --> 04:47.540]  So this is 1986.
[04:47.560 --> 04:51.340]  This was the first demonstration of a robotic microscope.
[04:51.600 --> 04:55.060]  And you can only imagine the satisfaction that this man felt clutching those keys and
[04:55.060 --> 04:59.760]  hearing those sweet clicking sounds as he moved the microscope around.
[04:59.980 --> 05:04.780]  And really, the history of telepathology is sort of a history of the internet in many
[05:04.780 --> 05:06.080]  ways as well.
[05:06.080 --> 05:11.320]  Because as things improved with the internet, we were able to do more and more in terms
[05:11.320 --> 05:16.900]  of sharing slides, and then virtually moving on to creating virtual slides and sharing
[05:16.900 --> 05:18.360]  those slides over the cloud.
[05:18.540 --> 05:22.360]  And now with things like TensorFlow, we're actually getting to the point where we can
[05:22.360 --> 05:26.140]  deploy AI locally on the device.
[05:26.360 --> 05:31.260]  And that's a big step, I think, that's happening right now in the telepathology industry.
[05:32.740 --> 05:39.440]  So, really, the work that I've done over the last four years has been focused on helping
[05:39.440 --> 05:43.200]  health outcomes in the developing world and solving the problems that they're facing.
[05:43.300 --> 05:46.900]  And so one of the biggest problems we look at is this really simple equation.
[05:46.900 --> 05:48.940]  Lost time equals lost lives.
[05:49.060 --> 05:54.340]  So there's a worldwide shortage of pathologists or doctors able to make diagnosis.
[05:54.660 --> 05:58.240]  And because of that, people can't get diagnosed.
[05:58.240 --> 06:01.800]  And so if people can't get diagnosed, they can't begin treatment.
[06:01.860 --> 06:06.800]  And the later you wait to begin treatment, the worse your health outcome is going to be.
[06:08.720 --> 06:15.480]  So a lot of the research we've done is creating just simple ratios when we look and see how
[06:15.480 --> 06:21.120]  many specialists there are in a country versus how many people there are.
[06:21.120 --> 06:28.360]  And so you can see that in the US, you've got a ratio of basically 1 to 17,000.
[06:29.260 --> 06:35.360]  But then if you look at a country like China, you've got 1 to 58,000.
[06:35.420 --> 06:40.860]  And then if you look at a country like Haiti, you've got 1 to 1,375,000.
[06:40.920 --> 06:47.320]  So you can see that there's just not enough doctors to make diagnosis for all these people.
[06:47.820 --> 06:51.580]  And there's also things that happen when you're in one of these countries that has a small
[06:51.580 --> 06:52.680]  number of doctors.
[06:52.920 --> 06:56.600]  You can actually fix your price as one of those doctors, and your price can be a lot
[06:56.600 --> 06:58.640]  higher than it would be in another country.
[06:58.860 --> 07:01.700]  And so not only are those people not able to get access, but they have to pay a lot
[07:01.700 --> 07:03.960]  more money for access to diagnosis.
[07:04.840 --> 07:11.200]  So the College of American Pathologists states that between 60% and 70% of all diseases need
[07:11.340 --> 07:16.360]  a diagnosis using some sort of cellular biology.
[07:16.360 --> 07:22.300]  And that includes cancer, things like malaria, a lot of diseases that we know today.
[07:23.060 --> 07:28.240]  Anyway, so another thing we've studied is this travel burden.
[07:28.540 --> 07:31.840]  And a lot of people have done studies here in America.
[07:31.840 --> 07:35.040]  And so we have three studies here, one from Kentucky, one from Illinois, and one from
[07:35.040 --> 07:35.960]  Georgia.
[07:36.240 --> 07:42.680]  And basically all these studies stated that people that lived at a far distance away from
[07:42.680 --> 07:47.120]  the primary diagnosis center, they would get staged for cancer much later.
[07:47.600 --> 07:49.540]  And so that's a big thing that we're facing.
[07:49.640 --> 07:54.400]  So like I said, if it takes you a long time to get a diagnosis, you're probably going
[07:54.400 --> 07:57.900]  to get diagnosed much later when it's going to be much more difficult to cure.
[07:59.160 --> 08:03.840]  So to give you an example of one of the patients that I saw when I was down in Haiti.
[08:04.020 --> 08:07.660]  So we had this woman come about three years ago and present herself.
[08:07.660 --> 08:09.000]  And she had a breast mask.
[08:09.560 --> 08:15.060]  And so we had a surgeon at the hospital who was able to do a biopsy for her, but there
[08:15.060 --> 08:19.400]  was no one available that could look at her specimen once we had it.
[08:20.020 --> 08:25.440]  So we gave her her specimen in a jar, and we gave her instructions on how to get to
[08:25.440 --> 08:26.660]  the nearest laboratory.
[08:26.920 --> 08:31.000]  And so that laboratory is about six, seven hours away, and she never made that visit.
[08:31.320 --> 08:35.880]  So a couple of years later, she came back in, and this time the mask had grown so large
[08:35.880 --> 08:37.960]  that it actually had ulcerated out of her breast.
[08:37.960 --> 08:43.760]  So now you see we definitely can say, okay, well, this without a doubt is going to be
[08:43.760 --> 08:45.060]  breast cancer right here.
[08:45.340 --> 08:48.940]  But when we first saw her, when she first presented herself, when she only had a small
[08:48.940 --> 08:53.560]  mask, we could have used diagnostic testing to prove that it was breast cancer at that
[08:53.560 --> 08:57.140]  point, and consequently we could have started treatment much earlier.
[08:57.500 --> 09:00.340]  And that's sort of an example of what happens.
[09:00.760 --> 09:06.760]  Also it's important to note that the cost of testing, diagnostic testing, in Haiti is
[09:06.760 --> 09:08.440]  $50 per test.
[09:08.580 --> 09:12.800]  So that's like a really important number to kind of remember.
[09:13.440 --> 09:18.660]  So the previous solutions were like to travel to Port-au-Prince, find a lab, wait a few
[09:18.660 --> 09:20.520]  months and hopefully get a diagnosis.
[09:21.220 --> 09:25.660]  What we were doing before, a long time ago, was collecting all the samples, flying them
[09:25.660 --> 09:30.100]  to America, getting a lab to process them in the United States, sending all the results
[09:30.100 --> 09:33.360]  back and praying that we could find all the people that we had tested while we were down
[09:33.360 --> 09:34.020]  there.
[09:35.060 --> 09:39.980]  Another chance is like the doctor operates based on symptoms, and then really what mostly
[09:39.980 --> 09:42.620]  ends up happening is people die of unknown diseases.
[09:43.400 --> 09:46.320]  So that's pretty heavy, so I'm going to chill out for a second.
[09:49.360 --> 09:54.100]  But we're like, we're working to solve this problem because we know we can.
[09:54.100 --> 09:57.280]  And we know we can use technology to solve this problem.
[09:57.700 --> 10:02.360]  And so what we've done is we've been focusing on building human-machine teams.
[10:02.940 --> 10:08.480]  So the vision really is, and it's something that the WHO sort of shares with us as well,
[10:08.480 --> 10:10.940]  is to create more healthcare workers.
[10:10.940 --> 10:16.660]  Because the paradigm of having a hospital, having a doctor that we know and well love
[10:16.660 --> 10:20.700]  here in America or in other developed nations, it's just not going to work in a lot of these
[10:20.700 --> 10:21.340]  countries.
[10:21.340 --> 10:26.440]  So we have to take people that are willing to go to school for maybe six months to a
[10:26.440 --> 10:31.520]  year, train them at a skill, that could be a skill like becoming a lab tech, and then
[10:31.520 --> 10:36.120]  give them the technology they need in order to share those slides so that they could make
[10:36.120 --> 10:37.360]  more diagnosis.
[10:38.120 --> 10:39.560]  And so that's something we've been working on.
[10:39.560 --> 10:44.120]  This is the team that I go down to Haiti with from time to time to do that.
[10:45.300 --> 10:50.040]  So another big thing we've been looking at is, okay, so once we can build the capacity
[10:52.000 --> 10:56.800]  for doctors or for healthcare workers to prepare specimens to upload those specimens to the
[10:56.800 --> 10:59.900]  internet, well, who are they going to share those specimens with?
[10:59.900 --> 11:03.600]  So normally what we did in the past was we shared them with doctors here in America.
[11:03.740 --> 11:05.900]  But doctors in America are really busy.
[11:06.020 --> 11:09.420]  They don't have enough time to look at cases from another hospital, especially if it's
[11:09.420 --> 11:13.100]  not helping them on the bottom line, it's not helping them make more money or do whatever.
[11:13.700 --> 11:17.680]  So what we've actually done is we're working with this team of doctors here in Tanzania.
[11:18.240 --> 11:22.660]  And so these are all doctors, these are all pathologists, the women that you're seeing
[11:22.660 --> 11:26.040]  here, and that's our friend Mumbek, he's also a doctor in Tanzania.
[11:26.040 --> 11:32.600]  And what we've been working is in this hospital, Mumbek in Dar es Salaam, we're setting them
[11:32.600 --> 11:35.000]  up with the technology that they need.
[11:35.260 --> 11:39.560]  So remember when I said it was important, remember that it costs $50 to get a slide
[11:39.560 --> 11:40.840]  diagnosed in Haiti.
[11:40.840 --> 11:43.780]  Well, in Tanzania, the cost of reading a slide is only $12.
[11:43.900 --> 11:49.060]  So already we're saving money for the people that are in Haiti by giving them this option.
[11:49.200 --> 11:53.060]  And the doctors in Tanzania are only making about $700 per month.
[11:53.060 --> 11:56.540]  So they are actually interested in supplementing their income.
[11:57.240 --> 12:01.280]  And they also have an unused capacity, because they're sitting in traffic, and most of them
[12:01.280 --> 12:02.180]  have drivers.
[12:02.180 --> 12:05.560]  So when they're sitting in traffic, there's time for them, if they're on their tablet
[12:05.560 --> 12:08.620]  or smartphone device, to actually be reviewing cases.
[12:08.900 --> 12:15.600]  So our solution is really to actually send our cases from Haiti to Tanzania to decrease
[12:15.600 --> 12:19.400]  the cost of testing, so the people in Haiti can afford to pay for testing, and they can
[12:19.400 --> 12:20.840]  get a diagnosis quickly.
[12:21.340 --> 12:24.460]  And then hopefully what we'll do is export the lab training program that we're developing
[12:24.460 --> 12:29.040]  in Haiti, export that over to Tanzania, and then create more lab techs, more health workers,
[12:29.040 --> 12:30.760]  that can work with what we're building.
[12:31.900 --> 12:34.000]  So that's sort of where we're at.
[12:34.080 --> 12:38.580]  And how we've been accomplishing this right now is we've been developing a system we call
[12:38.580 --> 12:39.440]  SmartScope.
[12:39.880 --> 12:42.740]  So this system basically has two components.
[12:43.260 --> 12:48.440]  It attaches to a regular microscope, and over the eyepiece, we have a camera that just fits
[12:48.440 --> 12:49.600]  on the eyepiece.
[12:49.600 --> 12:52.780]  And so that'll fit up to an outer diameter of 44 millimeters.
[12:52.860 --> 12:55.920]  So that'll cover most eyepieces that are out there.
[12:56.260 --> 13:01.760]  And then we built this robotic slide holder, and it just attaches with two screws to the
[13:01.760 --> 13:05.880]  side of the stage of the microscope.
[13:06.320 --> 13:12.080]  So basically with these two pretty simple pieces of technology we've developed over
[13:12.080 --> 13:16.960]  the last three years, we can take a standard microscope, and then we can turn it into an
[13:16.960 --> 13:18.040]  IoT device.
[13:18.430 --> 13:24.500]  And so what this is is something that we can deploy at a cost of about $1,000 to $2,000.
[13:24.900 --> 13:29.000]  And on the other side, the companies that were previously building whole slide imaging
[13:29.000 --> 13:34.480]  machines and dynamic microscopes, they were normally charging between $3,000 and $100,000
[13:34.480 --> 13:36.520]  for one of these standalone devices.
[13:36.880 --> 13:40.500]  And if you've worked in the developing world, you'll know that any sort of standalone device
[13:40.500 --> 13:44.840]  that they have, there's a good likelihood that it's going to be broken by the time you
[13:44.840 --> 13:46.900]  get back there the next time you come down.
[13:46.900 --> 13:49.360]  And there's no one that's going to service these devices.
[13:49.540 --> 13:55.160]  So we've actually created this technology really mimicking what we saw in 3D printers,
[13:55.160 --> 13:58.040]  and we've created technology that you can actually repair yourself.
[13:58.440 --> 14:01.180]  So I think that's a big change right now.
[14:01.340 --> 14:05.420]  And then you can share it on your... it runs on the cloud, so you can share it on your
[14:05.420 --> 14:08.500]  desktop, you can share it on your tablet, or you can even look at it on your smartphone.
[14:10.140 --> 14:13.920]  So how we built it up to this point was we used the Intel Edison.
[14:14.280 --> 14:19.480]  We thought that was a really good solution for us to start with, because it gave us a
[14:19.480 --> 14:23.060]  lot of versatility, we could run a whole bunch of programs on it.
[14:23.060 --> 14:28.220]  But the one drawback of working with the Edison was that it required us to have a computer
[14:28.220 --> 14:29.880]  to run everything with.
[14:29.880 --> 14:32.940]  So we couldn't sort of do things, everything on the device.
[14:32.940 --> 14:38.380]  And that was sort of where we're at, and we're actually deploying these units into the field,
[14:38.380 --> 14:41.720]  having sort of more and more use cases for it.
[14:41.720 --> 14:45.820]  So we have hospitals in Indiana that are using it for immunohistochemistry stains.
[14:45.880 --> 14:49.380]  They're just making sure, they're just using it for Q&A, for that kind of stuff.
[14:49.820 --> 14:51.260]  But it's been good.
[14:51.260 --> 14:54.500]  And so now we're looking at the next... what's next for us?
[14:54.500 --> 14:55.780]  What's next in the future?
[14:56.240 --> 14:59.920]  And so, I mean, I think this quote from Freeman Dyson is really good.
[15:00.200 --> 15:04.000]  New directions in science are launched by new tools more than they are by new concepts.
[15:04.140 --> 15:06.940]  The effect of concept-driven revolution is to explain old things in new ways.
[15:06.940 --> 15:11.420]  The effect of tool-driven revolution is to discover new things that have to be explained.
[15:11.420 --> 15:15.940]  So I think in a lot of ways, when Leeuwenhoek went on and developed a microscope
[15:15.940 --> 15:21.400]  that could see at 200 times magnification, then he could explain microbiology.
[15:21.420 --> 15:27.100]  For us, what we see in the vision is not only are we sort of working with this concept of people
[15:27.100 --> 15:33.340]  that are going to be providing healthcare workers, we're also giving them the tools they need.
[15:33.380 --> 15:35.720]  And we think these tools are powerful enough and cheap enough
[15:35.720 --> 15:39.540]  that they can be deployed in every single laboratory anywhere in the world.
[15:39.540 --> 15:44.940]  And we can create a whole global network, something that we like to call Skype for Microscopes.
[15:45.000 --> 15:50.620]  And this is how we're going to be able to track new diseases as new diseases emerge into the world.
[15:50.620 --> 15:53.680]  We're going to need to have these capabilities.
[15:53.680 --> 15:55.860]  We can't just send an expert there right away.
[15:55.860 --> 15:58.220]  There's time that it takes to transfer someone there.
[15:58.340 --> 16:01.180]  But having a sort of a network that's really light,
[16:01.180 --> 16:05.780]  we can create people around the world that can share this information with a centralized location.
[16:06.060 --> 16:08.240]  And so I think that's sort of where we're at.
[16:08.240 --> 16:11.580]  So I'll give you a little bit of a demo of how everything works.
[16:12.120 --> 16:14.660]  Let me see, just press the play button there.
[16:15.740 --> 16:19.200]  So this is our new website. It's launching later this month.
[16:20.020 --> 16:26.640]  Basically, once you sign in, you can access any devices that you have permissions to access.
[16:27.120 --> 16:28.920]  And so the devices are there.
[16:29.300 --> 16:36.500]  And then these are invitations, so you can receive invitations to join a session by someone else that has a device.
[16:37.060 --> 16:42.180]  And then once we have everything sort of running, we have this interface here.
[16:42.180 --> 16:44.100]  And you'll see the slide come up in a second.
[16:44.660 --> 16:48.360]  And so what we're able to do is we're able to control the movement of the slide.
[16:48.480 --> 16:51.040]  But we can also do things like add comments.
[16:51.060 --> 16:53.860]  So right now we're adding a comment to this box here.
[16:54.100 --> 16:57.040]  That could be sort of like anything you're seeing on the slide.
[16:57.600 --> 17:00.080]  You can submit that comment and that's recorded.
[17:00.340 --> 17:03.100]  We can invite people into the session, really simple.
[17:03.100 --> 17:05.180]  So we're going to invite Carlos right now.
[17:05.180 --> 17:06.600]  He's going to come in.
[17:06.780 --> 17:07.960]  We're going to invite him.
[17:08.100 --> 17:10.620]  You can see we have all the information available there.
[17:11.040 --> 17:12.420]  That's running on the local host.
[17:13.000 --> 17:14.840]  We have all the information on the slide there.
[17:14.840 --> 17:17.720]  And then we can slide that away and then you can view the whole slide.
[17:18.420 --> 17:24.540]  And so this is just a feed from a regular microscope, just from the eyepiece of the microscope.
[17:25.160 --> 17:26.900]  So obviously, I mean, there's some imperfections.
[17:26.900 --> 17:28.300]  You're seeing dirt and stuff like that.
[17:28.300 --> 17:31.620]  But this is what you would be seeing if you were looking through that eyepiece anyway.
[17:31.620 --> 17:36.060]  So it's a lot of, I mean, it's got clinical quality.
[17:36.240 --> 17:38.020]  It's getting the job done.
[17:38.020 --> 17:43.940]  And it really requires very little IT infrastructure to work in any way.
[17:44.940 --> 17:47.280]  So, yeah, I mean, now you're viewing the slide.
[17:47.280 --> 17:53.000]  And this is sort of an example of how we can look at different parts of the slide in order to determine a diagnosis.
[17:53.380 --> 17:56.860]  And then if we see something we like, we can take an image of that.
[17:57.060 --> 17:59.100]  We can add a comment to that image.
[17:59.500 --> 18:02.900]  And then once we add the comment to the image, we'll save that as well.
[18:04.040 --> 18:07.240]  And that just downloads to your computer, so you have a copy of it.
[18:07.780 --> 18:13.140]  And the idea, basically, is once you close out of the session, what you'll be able to do is create a report.
[18:13.420 --> 18:18.580]  And that report would just act as a single lab report, very similar to any sort of lab report you get from any hospital.
[18:18.920 --> 18:23.680]  It would tell you who was in the session, who started the session, what hospital the session took place at.
[18:23.940 --> 18:26.780]  And it would tell you if any sort of diagnosis was made.
[18:26.780 --> 18:28.900]  And then it would give thumbnails of any images.
[18:29.300 --> 18:31.860]  Okay, cool. So I've got about five minutes left.
[18:33.460 --> 18:35.840]  So, let's finish with this guy.
[18:36.940 --> 18:38.960]  And then we'll move on to the next slide.
[18:39.200 --> 18:45.360]  So, that's sort of where we're at in terms of how we see connecting laboratories around the world together.
[18:45.600 --> 18:50.120]  So let me talk to you a little bit about something that's called FlockMind, which I think is pretty interesting.
[18:50.240 --> 18:51.900]  So this was a study that was done.
[18:51.900 --> 18:57.080]  The doctor is like, some people don't like her, she's like sort of one of those figures.
[18:57.200 --> 19:00.000]  But she did this study basically where she took pigeons.
[19:00.140 --> 19:05.360]  And she trained the pigeons in order to make diagnosis on breast cancer using images from slides.
[19:05.740 --> 19:11.620]  So the pigeons themselves had an 85% diagnostic accuracy when determining cancer.
[19:12.420 --> 19:17.360]  But when they took the whole flock of pigeons, and then they actually took the result of the flock,
[19:17.360 --> 19:19.940]  they found that it actually raised up to 98%.
[19:21.120 --> 19:22.880]  So it was actually pretty good.
[19:22.880 --> 19:27.880]  But the thing they weren't telling you when I read the article was that they only used a training set.
[19:27.880 --> 19:31.660]  So they trained the pigeons on these images, and they just gave them the same training images again.
[19:31.660 --> 19:34.680]  They never gave them a testing set, so they sort of tried to hide that data.
[19:34.680 --> 19:35.920]  So I'm going to tell you that one.
[19:35.920 --> 19:40.280]  But it's still really interesting that with a training set, they could have the pigeons make their diagnosis.
[19:41.340 --> 19:45.020]  So that's essentially what we're trying to do right now with AI.
[19:45.020 --> 19:52.520]  So we're using TensorFlow, and we're basically creating our own methods of detecting cancer.
[19:52.520 --> 19:55.280]  So this is one in particular for cervical cancer.
[19:55.280 --> 20:00.800]  And we're doing screening programs where we can determine what level of cervical cancer that people are facing.
[20:01.180 --> 20:05.100]  And it's actually going really well. We're really happy.
[20:05.100 --> 20:10.100]  And we're able to build a lot of data because we have our own slide scanners, which is a big thing that holds a lot of people in line.
[20:10.860 --> 20:14.280]  And right now, we're working with Qualcomm, as I mentioned before.
[20:14.280 --> 20:19.760]  And the reason why we're really excited about that is because we're trying to actually create a new device altogether.
[20:20.040 --> 20:23.500]  This would be a standalone device that wouldn't need a computer or anything like that.
[20:23.500 --> 20:27.120]  And we really see this as the future of microscopy in a lot of ways.
[20:27.300 --> 20:30.580]  We can do everything that we were talking about before on this device.
[20:30.580 --> 20:32.980]  We could control our motors. We could do everything we want there.
[20:33.020 --> 20:35.860]  We could run our CV-based image stitching programs.
[20:36.040 --> 20:37.720]  And we can use TensorFlow and AI.
[20:37.720 --> 20:42.180]  And a lot of people are getting at us right now because they have been developing AI and they've been looking for platforms to run it on
[20:42.180 --> 20:45.220]  that are so cheap that they can be deployed into the developing world.
[20:46.040 --> 20:48.200]  And on the conclusion, that's what I'm going to say.
[20:48.460 --> 20:51.800]  It's all going to be good. We're all going to be alright because we're working on solving this problem.
[20:52.160 --> 20:53.980]  Thanks very much for your time today.