Player is loading...

Embed

Copy embed code

Transcriptions

Note: this content has been automatically generated.
00:00:00
a one question dangers i hope i'm not a watch that i run on a light
00:00:13
uh you
00:00:15
thinks he should that people might be called a lot of i know we can go
00:00:22
um we haven't addressed that at all but it it is definitely a problem in there and like car
00:00:30
i think there there are many dependencies that we haven't looked
00:00:33
into i think the exact complication people like in
00:00:37
in in our system definitely um optimise it on the available infrastructure
00:00:42
and clout so they knew like what infrastructure they had
00:00:46
things we were running in the document anus who if we can make
00:00:50
like we can like work flow soft taco containers so not have
00:00:53
like one big monolithic system but having like for every test that's what
00:00:56
we did like four then a quantitative imaging that work well
00:01:00
a system there's like some tasks so at all the different groups that meet docket containers
00:01:05
for the summer tossed and then we creative work flow we can combine them
00:01:09
to actually run it on a lot of times he automatically we have like some
00:01:13
care relies ability in in the system that we have there's also problem with like security
00:01:20
so if we move code inside a hospital like you you can half
00:01:25
that call in utah container so we may need to make sure
00:01:29
you cannot proceed great like a fully sandbox environment will be run it
00:01:32
and like totally disconnected from the rest of the hospital network
00:01:37
and then delete the virtual machine in the end and only like extract the results so there
00:01:41
are ways of dealing with that but it's something to to take into comes on
00:01:46
yeah well
00:01:51
no one else actually yes
00:01:53
any other question is to have a one
00:01:58
right and also yeah one action um examples of a project level
00:02:04
internal visible sorry medical research just so they'll for it
00:02:10
that computers are put the algorithms that would be evaluated on yeah they told
00:02:16
me that she was but my question with this kind of models
00:02:20
what's the price like so uh because putting the shoes that you'll cooled on so that they don't the company
00:02:29
and we can run sings what you live so doesn't mean that you
00:02:33
give them some kind of uh uh lights on the software
00:02:38
before they all you see the the you know the and it's it's it's totally true
00:02:46
like in in the case of intel they participated in in one of our workshops
00:02:50
and they were rather presenting like their vision for the medical domain of
00:02:54
easy for them hospitals apply it's potentially because with all electronic analysis
00:03:00
now for some like in the massachusetts general hospital were working boston um
00:03:04
they do systematically every cancer patient gets the whole genome sequence
00:03:10
and i'm like that they can be that therapies to it so if we do that
00:03:15
like we need massive computing infrastructure so for them to have the infrastructure
00:03:19
inside the hospital it doesn't mean that they run the infrastructure
00:03:23
they are they're not responsible they just loving heart pretty much so in that respect
00:03:27
it's not a problem because it's the hospital wanting to code but there is obviously
00:03:32
uh if if i'm a company into run the code in someone else's system
00:03:36
there could be like reverse engineering the could be like our analysis up the code even if we don't have source code to be
00:03:42
so it is like all we get is executable so people don't need to you to submit source code but we had companies
00:03:49
in general electric wanted to participate in the desert competitions and they ask us um
00:03:54
like can you guarantee us that nobody will touch a coding nobody would be able to see a coat
00:04:00
i'm not a security specials i told him i can't and in the end they didn't participate
00:04:04
because they said like oh no we need this guarantee to have that so i'm
00:04:08
i think a lot of it is about trust 'em between partners but
00:04:12
the result the seals the problem off are like what we can
00:04:15
do for the silver corpus we asked the participants whether we can use the code to run it on your data for example

Share this talk: 


Conference Program

Welcome
Sébastien Marcel, Senior Researcher, IDIAP, Director of the Swiss Center for Biometrics Research and Testing
March 24, 2017 · 9:17 a.m.
473 views
Keynote - Reproducibility and Open Science @ EPFL
Pierre Vandergheynst, EPFL VP for Education
March 24, 2017 · 9:20 a.m.
250 views
Q&A: Keynote - Reproducibility and Open Science @ EPFL
Pierre Vandergheynst, EPFL VP for Education
March 24, 2017 · 9:54 a.m.
Reproducible Research with Bob and the BEAT Platform
André Anjos
March 24, 2017 · 10:03 a.m.
230 views
VISCERAL and Evaluation-as-a-Service
Henning Müller, prof. HES-SO Valais-Wallis (unité e-health)
March 24, 2017 · 11:35 a.m.
109 views
Q&A - VISCERAL and Evaluation-as-a-Service
Henning Müller, prof. HES-SO Valais-Wallis (unité e-health)
March 24, 2017 · 12:07 p.m.
Making experiments on remote heart-rate measurement reproducible
Guillaume Heusch
March 24, 2017 · 12:30 p.m.
149 views
138 views

Recommended talks

HES-SO : Formation et création d'emplois
François Seppey, Directeur de la HES-SO Valais-Wallis
Oct. 9, 2014 · 2:22 p.m.
153 views