Search Mailing List Archives


Limit search to: Subject & Body Subject Author
Sort by: Reverse Sort
Limit to: All This Week Last Week This Month Last Month
Select Date Range     through    

[protege-discussion] protege-discussion Digest, Vol 25, Issue 16

svenvanpoucke at woundontology.com svenvanpoucke at woundontology.com
Sun Aug 17 00:54:40 PDT 2008


M. Jack wrote: "In fact, there will be some image processing first, to find
every histological characteristics on images related to cancer, and then
the ontology will deliver a diagnosis. It means that the pre-work done by
the image processing will be used by the ontology in other words protege to
make a diagnosis."

Dear colleague, although there is a chance that I do not exactly understand
which direction you want to go, but it seems that several similarities can
be found with the project we are running for chronic wounds and its
imaging. Please take a look at www.woundontology.com and in particular at
the imaging workflow concept map
(http://cmapspublic3.ihmc.us/servlet/SBReadResourceServlet?rid=1207398351125_1872997579_3678&partName=htmltext).
The link between image interpretation and ontology is less straight forward
as I read in your text above. It is our opinion that the dataflow should be
as follows: domain experts annotate images; similarities and differences in
this annotated textual data is quantitative analyzed; definitions are
developed from these results hoping to generate a future consensus in the
annotating process; these new insights plus the knowledge available in
scientific literature, thesaures, etc is used as a base for ontology
development. The ontology can then be used as starting point for clinical
decision support.

I see you are from France, if you are interested, we could have a skype
discussion on our projects (I am working in Belgium).

Cheers
Dr. Sven Van Poucke
Woundontology Consortium Coordinator




On Fri, 15 Aug 2008 12:13:30 -0700,
protege-discussion-request at lists.stanford.edu wrote:
> Send protege-discussion mailing list submissions to
> 	protege-discussion at lists.stanford.edu
> 
> To subscribe or unsubscribe via the World Wide Web, visit
> 	https://mailman.stanford.edu/mailman/listinfo/protege-discussion
> or, via email, send a message with subject or body 'help' to
> 	protege-discussion-request at lists.stanford.edu
> 
> You can reach the person managing the list at
> 	protege-discussion-owner at lists.stanford.edu
> 
> When replying, please edit your Subject line so it is more specific
> than "Re: Contents of protege-discussion digest..."
> 
> 
> Today's Topics:
> 
>    1. Re: Protege-frames or Protege-OWL (Samson Tu)
> 
> 
> ----------------------------------------------------------------------
> 
> Message: 1
> Date: Thu, 14 Aug 2008 15:52:43 -0700
> From: Samson Tu <swt at stanford.edu>
> Subject: Re: [protege-discussion] Protege-frames or Protege-OWL
> To: protege-discussion at lists.stanford.edu
> Message-ID: <g82cvr$ptn$1 at ger.gmane.org>
> Content-Type: text/plain; charset=ISO-8859-1; format=flowed
> 
> 
> Both Protege 3.x [1] and Protege 4 [2] have APIs that you can use in
> your application.
> 
> OWL is a possible reasoner if you can formulate your diagnosis as a
> classification problem.
> 
> 
> [1] http://protege.stanford.edu/plugins/owl/api/index.html
> [2] http://protegewiki.stanford.edu/index.php/Protege4DevDocs
> 
> Safran, Tracy (NIH/NCI) [C] wrote:
>> Have you looked at the NCI Enterprise Vocabulary Services?  We provide
>> API access to the National Cancer Institute Thesaurus.  That might work
>> for you.
>>
>> http://evs.nci.nih.gov/
>>
>> Tracy M. Safran
>> SAIC Contractor
>> EVS Support
>> 301-402-1537
>>
>> -----Original Message-----
>> From: M. jack [mailto:mall_bidon at hotmail.fr]
>> Sent: Thursday, June 19, 2008 6:05 AM
>> To: protege-discussion at lists.stanford.edu
>> Subject: [protege-discussion] Protege-frames or Protege-OWL
>>
>>
>> Hello,
>>
>> I have to do a medical ontology concerning cancer. At the begining, I
>> was
>> using Protege 4.0 alpha, because I thought it was the last version, and
>> therefore the best one. But, now I am asking question to myself given
>> that
>> the ontology has to be used by an other application, and with
>> protege-owl
>> 4.0 I have the impression that it is not possible.
>> In fact, there will be some image processing first, to find every
>> histological characteristics on images related to cancer, and then the
>> ontology will deliver a diagnosis. It means that the pre-work done by
>> the
>> image processing will be used by the ontology in other words protege to
>> make
>> a diagnosis. Is it possible with protege 4.0 alpha? With any protege-OWL
>> editor? Or with a Protege-Frames editor?
>> I am not even sure that an ontology can be used like that. Maybe there
>> is
>> something that I don't understand at all with ontologies and with
>> Protege.
>>
>> Thank you very much for the help.
> 
> 
> 
> ------------------------------
> 
> _______________________________________________
> protege-discussion mailing list
> protege-discussion at lists.stanford.edu
> https://mailman.stanford.edu/mailman/listinfo/protege-discussion
> 
> 
> End of protege-discussion Digest, Vol 25, Issue 16
> **************************************************




More information about the protege-discussion mailing list