[Insight-users] Segmentation of articular cartilage from MR
Ken Urish
ken.urish at gmail.com
Fri Apr 18 14:18:00 EDT 2008
Hello Sirisha
Articular cartilage segmentation can be very challanging. It depends
on the location and quality of images. I recently finished a similar
project and found I had to use much more sophisticated techniques -
level set, shape modeling etc. Its difficult to comment w/out images,
but......
If you have the cartilage segmented and its not connected to anything
else, I would do a connected components and threshold the output to
throw out the other objects. But I suspect that your edge boundaries
are leaky and these structures are attached. If this is the case, I
cant think of an easy fix. You can try level sets, but *guessing* on
your scans this will also be leaky as well.
For a great sampling of attempts by other people, I would look at
papers by Eckstein, Ourselin, Majumdar.
Example images of your output would help to answer the question a great deal.
You are walking down a potentially challanging but really fun path.
Thanks
--Ken--
Message: 2
Date: Thu, 17 Apr 2008 13:53:18 -0500
From: "Tadimalla, Sirisha" <sirisha-tadimalla at uiowa.edu>
Subject: [Insight-users] Segmentation of articular cartilage from MR
images
To: <insight-users at itk.org>
Message-ID:
<305EB2466DAA4346994565B8EE14AC400248726B at HC-MAIL11.healthcare.uiowa.edu>
Content-Type: text/plain; charset="iso-8859-1"
Hi all,
I need to develop an automatic method to segment articular cartilage
in 2D MR scans. I am using the following steps currently:
Curvature anisotropic diffusion
Gradient magnitude image filter
Threshold image filter
fast marching image filter
binary morphological closing
But the output that I get is very crude segmentation. I am obtaining
all other parts of the image having similar intensity ranges as
cartilage like ligaments and meniscus and so on. How do I use a robust
method to obtain just the cartilage?
-sirisha
On 4/18/08, insight-users-request at itk.org <insight-users-request at itk.org> wrote:
> Send Insight-users mailing list submissions to
> insight-users at itk.org
>
> To subscribe or unsubscribe via the World Wide Web, visit
> http://www.itk.org/mailman/listinfo/insight-users
> or, via email, send a message with subject or body 'help' to
> insight-users-request at itk.org
>
> You can reach the person managing the list at
> insight-users-owner at itk.org
>
> When replying, please edit your Subject line so it is more specific
> than "Re: Contents of Insight-users digest..."
>
>
> Today's Topics:
>
> 1. .dll generation (Emin KUGU)
> 2. Segmentation of articular cartilage from MR images
> (Tadimalla, Sirisha)
> 3. VIRGIL : Dashboard Submission. (Luis Ibanez)
> 4. Load a large image (Olivier Tournaire)
> 5. Read a part of an image (Olivier Tournaire)
> 6. Re: Read a part of an image (Julien Jomier)
> 7. Re: itkFlatStructuringElement (Richard Beare)
> 8. Poor Tree Trace Interface (Kevin H. Hobbs)
> 9. registration of multimodal images and optimisation surface
> (Severino)
>
>
> ----------------------------------------------------------------------
>
> Message: 1
> Date: Thu, 17 Apr 2008 10:04:29 -0700 (PDT)
> From: Emin KUGU <eminkugu at yahoo.com>
> Subject: [Insight-users] .dll generation
> To: insight-users at itk.org
> Message-ID: <385106.80296.qm at web35205.mail.mud.yahoo.com>
> Content-Type: text/plain; charset="iso-8859-1"
>
> Hi,
>
> I am a new user.
>
> I want to generate .dll files from some of the filtering examples.
> Do you now how to do that?
>
> Thanks.
>
> Emin.
>
>
> ---------------------------------
> Be a better friend, newshound, and know-it-all with Yahoo! Mobile. Try it now.
> -------------- next part --------------
> An HTML attachment was scrubbed...
> URL: <http://www.itk.org/pipermail/insight-users/attachments/20080417/b2ecbfeb/attachment-0001.htm>
>
> ------------------------------
>
> Message: 2
> Date: Thu, 17 Apr 2008 13:53:18 -0500
> From: "Tadimalla, Sirisha" <sirisha-tadimalla at uiowa.edu>
> Subject: [Insight-users] Segmentation of articular cartilage from MR
> images
> To: <insight-users at itk.org>
> Message-ID:
> <305EB2466DAA4346994565B8EE14AC400248726B at HC-MAIL11.healthcare.uiowa.edu>
>
> Content-Type: text/plain; charset="iso-8859-1"
>
>
> Hi all,
>
> I need to develop an automatic method to segment articular cartilage in 2D MR scans. I am using the following steps currently:
>
> Curvature anisotropic diffusion
> Gradient magnitude image filter
> Threshold image filter
> fast marching image filter
> binary morphological closing
>
> But the output that I get is very crude segmentation. I am obtaining all other parts of the image having similar intensity ranges as cartilage like ligaments and meniscus and so on. How do I use a robust method to obtain just the cartilage?
>
> -sirisha
>
>
> ------------------------------
>
> Message: 3
> Date: Thu, 17 Apr 2008 15:20:56 -0400
> From: Luis Ibanez <luis.ibanez at kitware.com>
> Subject: [Insight-users] VIRGIL : Dashboard Submission.
> To: Insight Users <insight-users at itk.org>, ITK
> <insight-developers at itk.org>
> Message-ID: <4807A318.4040501 at kitware.com>
> Content-Type: text/plain; charset=ISO-8859-1; format=flowed
>
>
> The Dasbhboard submission from "VIRGIL" has been
> posting compilation errors for quite a while:
>
> http://www.cdash.org/CDash/viewBuildError.php?buildid=55606
>
>
>
> Some of the problems seems to be related to the API
> change of ConvertPointToContinousIndex:
>
>
>
> /.../Build_SunOS/Wrapping/WrapITK/Modules/Base/wrap_itkImageFunctionJava.cxx:168:
> error: `ConvertPointToContinousIndex'
>
> ConvertPointToContinousIndex' undeclared (first use this function)
>
>
> It seems that a new version of ITK has been mixed with
> an old version of WrapITK.
>
>
> Could the maintainer of this build please contact us,
> so we can track down this problem ?
>
>
>
> Thanks
>
>
> Luis
>
>
>
>
>
> ------------------------------
>
> Message: 4
> Date: Thu, 17 Apr 2008 23:04:10 +0200
> From: "Olivier Tournaire" <olitour at gmail.com>
> Subject: [Insight-users] Load a large image
> To: "Insight User" <insight-users at itk.org>
> Message-ID:
> <4cbd7b750804171404t76449ad5hd88a049340564ce5 at mail.gmail.com>
> Content-Type: text/plain; charset="iso-8859-1"
>
> Hi all,
>
> I am currently using itk, and, I tried a few days ago to read a large image
> (15000x10000, unsigned char, 3 components). The image size is about 400Mo,
> if fully loaded in memory. However, I always get a "Failed to allocate
> memory" exception on windows platforms (2Go RAM, 1.2Go enable). Under Linux
> or OSX (2Go RAM), I do not have this exception.
> Could you please provide some help ?
>
> Regards
>
> Olivier
> -------------- next part --------------
> An HTML attachment was scrubbed...
> URL: <http://www.itk.org/pipermail/insight-users/attachments/20080417/5c06b274/attachment-0001.htm>
>
> ------------------------------
>
> Message: 5
> Date: Thu, 17 Apr 2008 23:06:09 +0200
> From: "Olivier Tournaire" <olitour at gmail.com>
> Subject: [Insight-users] Read a part of an image
> To: "Insight User" <insight-users at itk.org>
> Message-ID:
> <4cbd7b750804171406x620fb417l558b817e70a81c23 at mail.gmail.com>
> Content-Type: text/plain; charset="iso-8859-1"
>
> Hi all,
>
> I would like to know if it is possible to read just a region of an image, in
> order to not load le full image in memory. I saw a SetBufferedRegion method
> for itk::Image, but, I do not know how to use it with itk::ImageFileReader.
> Any tips ?
>
> Best regards,
>
> Olivier
> -------------- next part --------------
> An HTML attachment was scrubbed...
> URL: <http://www.itk.org/pipermail/insight-users/attachments/20080417/118ad3b0/attachment-0001.htm>
>
> ------------------------------
>
> Message: 6
> Date: Thu, 17 Apr 2008 17:14:40 -0400
> From: Julien Jomier <julien.jomier at kitware.com>
> Subject: Re: [Insight-users] Read a part of an image
> To: Olivier Tournaire <olitour at gmail.com>
> Cc: Insight User <insight-users at itk.org>
> Message-ID: <4807BDC0.9080700 at kitware.com>
> Content-Type: text/plain; charset=ISO-8859-1; format=flowed
>
> Hi Olivier,
>
> ITK has support for streamed reading/writing for uncompressed MetaImage
> files. (AFAIK this is the only format that supports full streaming for now).
>
> You can look at some test examples in
> Insight/Testing/Code/IO/itkMetaImageStreamingIOTest.cxx
> Insight/Testing/Code/IO/itkMetaImageStreamingWriterIOTest.cxx
>
> Hope that helps,
>
> Julien
>
> Olivier Tournaire wrote:
> > Hi all,
> >
> > I would like to know if it is possible to read just a region of an
> > image, in order to not load le full image in memory. I saw a
> > SetBufferedRegion method for itk::Image, but, I do not know how to use
> > it with itk::ImageFileReader. Any tips ?
> >
> > Best regards,
> >
> > Olivier
> >
> >
> > ------------------------------------------------------------------------
> >
> > _______________________________________________
> > Insight-users mailing list
> > Insight-users at itk.org
> > http://www.itk.org/mailman/listinfo/insight-users
>
>
> ------------------------------
>
> Message: 7
> Date: Fri, 18 Apr 2008 09:48:42 +1000
> From: "Richard Beare" <richard.beare at gmail.com>
> Subject: Re: [Insight-users] itkFlatStructuringElement
> To: "Albert M" <albermnz at gmail.com>
> Cc: insight-users at itk.org
> Message-ID:
> <779dabeb0804171648w5501bc3bu1a4adb5acc6d81cf at mail.gmail.com>
> Content-Type: text/plain; charset=ISO-8859-1
>
> Sure, just set the elments of Rad individually.
>
> Rad[0]=5;
> Rad[1]=3;
>
> etc
>
> On 4/18/08, Albert M <albermnz at gmail.com> wrote:
> > Dear all,
> > I would like to know if it's possible to set differet values for the radio
> > in the different dimensions. Is there available any example?
> >
> > typedef itk::FlatStructuringElement<Dimension>
> > StructuringElementType;
> >
> > StructuringElementType::RadiusType Rad;
> > Rad.Fill(5);
> >
> >
> > Regards
> > Al
> >
> > _______________________________________________
> > Insight-users mailing list
> > Insight-users at itk.org
> > http://www.itk.org/mailman/listinfo/insight-users
> >
> >
>
>
> ------------------------------
>
> Message: 8
> Date: Fri, 18 Apr 2008 08:56:20 -0400
> From: "Kevin H. Hobbs" <hobbsk at ohiou.edu>
> Subject: [Insight-users] Poor Tree Trace Interface
> To: Insight Users List <insight-users at itk.org>
> Message-ID: <1208523380.21105.16.camel at gargon.hooperlab>
> Content-Type: text/plain; charset="us-ascii"
>
> I've been working on an program for tracing out the center-lines of
> dendrites in confocal images.
>
> I have a working first version at :
> http://crab-lab.zool.ohiou.edu/kevin/Interactive_Trace-0.0.1/
>
> This is a *very* early version it segfaults, it throws exceptions, it's
> written in a very C like way, it's clunky... but it works.
>
> One of the core requirements was that the original image could be huge,
> and that work could be done on small pieces.
>
> It uses vesselness -> fast marching -> gradient -> stream tracing to
> produce the center-lines.
>
> Please give me your comments.
> -------------- next part --------------
> A non-text attachment was scrubbed...
> Name: not available
> Type: application/pgp-signature
> Size: 189 bytes
> Desc: This is a digitally signed message part
> URL: <http://www.itk.org/pipermail/insight-users/attachments/20080418/dac9eeaa/attachment-0001.pgp>
>
> ------------------------------
>
> Message: 9
> Date: Fri, 18 Apr 2008 17:08:15 +0200
> From: "Severino" <fdezas at gmail.com>
> Subject: [Insight-users] registration of multimodal images and
> optimisation surface
> To: <insight-users at itk.org>
> Message-ID: <000a01c8a166$0b8dfd10$2201a8c0 at severino>
> Content-Type: text/plain; charset="iso-8859-1"
>
> I am having trouble to register two small images coming from the remote sensing area, one a radar image and the other one from an optical sensor. Mutual information hould work for this case as it does in medicine, to test it I used an application written by the ORFEO project from CNES. But trying with a large set of different parameters for the optimization (gradient descent) and for the measure (Viola and Wells or Mattes).
> I have therefore used the small program of Lydia Ng to observe the behaviour of the function to be optimized. But the results are quite astonishing, as I can not see a global maximum but a plateau like maximum. If this is the real shape, it is no wonder that I can not register the function, as there are a compact set of maxima. I suppose this strange shape comes froom the perameter settings, but I just used the default values that Lydia put in her code, and any variation showed the same shape.
> Is anybody aware of settings I could try to see if this shape changes and produces a smooth surface with a well identified maximum?
> regards
> -------------- next part --------------
> An HTML attachment was scrubbed...
> URL: <http://www.itk.org/pipermail/insight-users/attachments/20080418/03e4968d/attachment-0001.htm>
>
> ------------------------------
>
> _______________________________________________
> Insight-users mailing list
> Insight-users at itk.org
> http://www.itk.org/mailman/listinfo/insight-users
>
>
> End of Insight-users Digest, Vol 48, Issue 53
> *********************************************
>
More information about the Insight-users
mailing list