[Insight-users] Using SNAP for Knee segmentation
Luis Ibanez
luis.ibanez at kitware.com
Tue Dec 2 17:53:09 EST 2008
Hi Amir,
Your email is quite confusing.
I understand that you are trying to use SNAP for segmenting
a Knee Dataset.
Is that correct ?
If so, let's start from the beginning.
Please describe the Knee images that you have as input.
* Image Modality
* Image spacing
* Image dimensions
Thanks
Luis
------------
amir wrote:
>
> Hello Dear:
>
>
>
>
> I Downloded the ITK Software and started to study its help, I impoted
> the knee slices but I saw in a part of
>
>
>
>
> the Tutrial that I should load the segmentation label, by these
> commands: File /Load Data/Label
>
>
>
>
> Description/ , But there is not any "Load Data" During File , and I
> only found the , "Label Description" , as a
>
>
>
>
> subdirectory of the "Open " and "Save", But I tried both of them to
> load the "MRIcrop-seg.label" File, But I
>
>
>
>
> couldn't load the "MRIcorp-seg.label" and after opening the "Snap Label
> Editor" I didn't see the new loaded
>
>
>
>
> files, what's the problem?
>
>
>
>
> Dear, another question is: Why do we need to load another segmented
> file, like "MRIcrop-seg.label" ,I do
>
>
>
>
> not have any separated file for the knee Segmentation, I want to start
> the segmentation (Manually, or
>
>
>
>
> Automatically) from zero , by ITK Software, Do you Direct me, Please?
>
>
>
>
> Best Regards.
>
>
>
>
>
> insight-users-request at itk.org wrote:
>
> Send Insight-users mailing list submissions to
> insight-users at itk.org <mailto: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 <mailto:insight-users-request at itk.org>
>
> You can reach the person managing the list at
> insight-users-owner at itk.org <mailto: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. Re: More flexible assignment for itk::SmartPointer (Bill Lorensen)
> 2. Re: More flexible assignment for itk::SmartPointer (Bill Lorensen)
> 3. image display in GLSliceView (Yaoyao Zhu)
> 4. Re: How to load sequence items (chensiqi)
> 5. itk::SparseFieldLevelSetImageFilter (Brady McCary)
> 6. Re: itk::SparseFieldLevelSetImageFilter (Luca Antiga)
> 7. Re: itk::SparseFieldLevelSetImageFilter (Koen Vermeer)
> 8. NumericTraits level 3 warnings on VS 2008 (Denis Shamonin)
>
>
> ----------------------------------------------------------------------
>
> Message: 1
> Date: Tue, 25 Nov 2008 12:12:43 -0500
> From: "Bill Lorensen" <bill.lorensen at gmail.com
> <mailto:bill.lorensen at gmail.com>>
> Subject: Re: [Insight-users] More flexible assignment for
> itk::SmartPointer
> To: "Maarten Nieber" <hallomaarten at yahoo.com
> <mailto:hallomaarten at yahoo.com>>
> Cc: insight-users at itk.org <mailto: insight-users at itk.org>
> Message-ID:
> <4db4735c0811250912o548beecdr23563a93012a76ed at mail.gmail.com
> <mailto:4db4735c0811250912o548beecdr23563a93012a76ed at mail.gmail.com>>
> Content-Type: text/plain; charset=ISO-8859-1
>
> Maarten,
>
> Why not do the dynamic cast yourself? Then you can have control if the
> dynamic_cast fails. I think we do this several times in itk.
>
> Bill
>
> On Tue, Nov 25, 2008 at 11:04 AM, Maarten Nieber
> <hallomaarten at yahoo.com <mailto:hallomaarten at yahoo.com>> wrote:
> > Hi,
> >
> > I hope I am not restarting any old discussions, but I would like
> to be able
> > to assign an itk::SmartPointer to another pointer that has a
> compatible
> > type, for example:
> >
> > itk::Image<3, double>::Pointer image = itk::Image<3, double>::New();
> > itk::ImageBase<3>::Pointer p = image;
> >
> > Note that boost::shared_ptr works like this.
> > The behaviour could be achieved using a templated copy
> constructor for
> > itk::SmartPointer:
> >
> > template< class TObjectType2 >
> > SmartPointer(const SmartPointer<TObjectType2>& rhs)
> > {
> > // do a dynamic_cast here, and assign the result to rhs
> > }
> >
> > Would this be a good idea?
> >
> > Best regards,
> > Maarten
> >
> >
> >
> > _______________________________________________
> > Insight-users mailing list
> > Insight-users at itk.org <mailto: Insight-users at itk.org>
> > http://www.itk.org/mailman/listinfo/insight-users
> >
> >
>
>
> ------------------------------
>
> Message: 2
> Date: Tue, 25 Nov 2008 12:12:43 -0500
> From: "Bill Lorensen" <bill.lorensen at gmail.com
> <mailto:bill.lorensen at gmail.com>>
> Subject: Re: [Insight-users] More flexible assignment for
> itk::SmartPointer
> To: "Maarten Nieber" <hallomaarten at yahoo.com
> <mailto:hallomaarten at yahoo.com>>
> Cc: insight-users at itk.org <mailto: insight-users at itk.org>
> Message-ID:
> <4db4735c0811250912o548beecdr23563a93012a76ed at mail.gmail.com
> <mailto:4db4735c0811250912o548beecdr23563a93012a76ed at mail.gmail.com>>
> Content-Type: text/plain; charset=ISO-8859-1
>
> Maarten,
>
> Why not do the dynamic cast yourself? Then you can have control if the
> dynamic_cast fails. I think we do this several times in itk.
>
> Bill
>
> On Tue, Nov 25, 2008 at 11:04 AM, Maarten Nieber
> <hallomaarten at yahoo.com <mailto:hallomaarten at yahoo.com>> wrote:
> > Hi,
> >
> > I hope I am not restarting any old discussions, but I would like
> to be able
> > to assign an itk::SmartPointer to another pointer that has a
> compatible
> > type, for example:
> >
> > itk::Image<3, double>::Pointer image = itk::Image<3, double>::New();
> > itk::ImageBase<3>::Pointer p = image;
> >
> > Note that boost::shared_ptr works like this.
> > The behaviour could be achieved using a templated copy
> constructor for
> > itk::SmartPointer:
> >
> > template< class TObjectType2 >
> > SmartPointer(const SmartPointer<TObjectType2>& rhs)
> > {
> > // do a dynamic_cast here, and assign the result to rhs
> > }
> >
> > Would this be a good idea?
> >
> > Best regards,
> > Maarten
> >
> >
> >
> > _______________________________________________
> > Insight-users mailing list
> > Insight-users at itk.org <mailto: Insight-users at itk.org>
> > http://www.itk.org/mailman/listinfo/insight-users
> >
> >
>
>
> ------------------------------
>
> Message: 3
> Date: Tue, 25 Nov 2008 12:12:05 -0500
> From: "Yaoyao Zhu" <yaz304 at Lehigh.EDU <mailto:yaz304 at Lehigh.EDU>>
> Subject: [Insight-users] image display in GLSliceView
> To: <insight-users at itk.org <mailto:insight-users at itk.org>>
> Message-ID: <02ce01c94f20$f0ead780$d2c08680$@edu
> <mailto:02ce01c94f20$f0ead780$d2c08680$@edu>>
> Content-Type: text/plain; charset="us-ascii"
>
> Hi, all,
>
>
>
> I found out that image displayed in GLSliceView is upside down. Also the
> point I clicked is displayed upside down too.
>
>
>
> Anyone can help me to fix these?
>
>
>
> Thanks in advance.
>
> -------------- next part --------------
> An HTML attachment was scrubbed...
> URL:
> <http://www.itk.org/pipermail/insight-users/attachments/20081125/ce913815/attachment-0001.htm>
>
> ------------------------------
>
> Message: 4
> Date: Wed, 26 Nov 2008 03:15:11 +0800
> From: chensiqi <pidanchen at hotmail.com <mailto:pidanchen at hotmail.com>>
> Subject: Re: [Insight-users] How to load sequence items
> To: <mathieu.malaterre at gmail.com <mailto:mathieu.malaterre at gmail.com>>
> Cc: insight-users at itk.org <mailto: insight-users at itk.org>
> Message-ID: <BAY101-W31C2C89115D39E1EDB12D6BD0B0 at phx.gbl
> <mailto:BAY101-W31C2C89115D39E1EDB12D6BD0B0 at phx.gbl>>
> Content-Type: text/plain; charset="gb2312"
>
>
> Hi, Mathieu.
>
> The second thing you mentioned works!! I just set the
> SetMaxSizeLoadEntry to be 0xffff
>
> Thanks
> > Date: Tue, 25 Nov 2008 14:17:20 +0100> From:
> mathieu.malaterre at gmail.com <mailto: mathieu.malaterre at gmail.com>>
> To: pidanchen at hotmail.com <mailto: pidanchen at hotmail.com>> Subject:
> Re: [Insight-users] How to load sequence items> CC:
> insight-users at itk.org <mailto: insight-users at itk.org>> > On Tue, Nov
> 25, 2008 at 3:43 AM, chensiqi <pidanchen at hotmail.com
> <mailto:pidanchen at hotmail.com>> wrote:> >> >> > Thanks for the
> sharing.> >> > I managed to load most of the sequence data using
> GDCM instead of ITK.> > GDCM has several classes and member
> functions that can easily read sequence> > data.> >> > One thing I
> don't understand is some sequence data can not be loaded, GDCM> >
> complains them as "Bad Pointer". But I can definitely see them in
> Matlab> > using Dicominfo().> > E.g, for "ContourData" items, for
> some slices, I can load them using GDCM,> > for some other slices,
> GDCM will throw a "Bad Ptr".> > Two options (from the top of my
> head):> > - this particular DICOM file is missing the SQ. Did you
> check it is present ?> - this is the famous GDCM 1.x 'feature',
> where you have to explicitely> says: "yes I want to l
> oad long field". See :> >
> http://www.itk.org/Doxygen/html/classitk_1_1GDCMImageIO.html> ->
> Get/SetMaxSizeLoadEntry> > 2cts> -- > Mathieu
> _________________________________________________________________
> MSN???????????????????
> http://im.live.cn/newsexpress
> -------------- next part --------------
> An HTML attachment was scrubbed...
> URL:
> <http://www.itk.org/pipermail/insight-users/attachments/20081126/4ad1f50a/attachment-0001.htm>
>
> ------------------------------
>
> Message: 5
> Date: Tue, 25 Nov 2008 21:34:59 -0600
> From: "Brady McCary" <brady.mccary+ITK at gmail.com
> <mailto:brady.mccary+ITK at gmail.com>>
> Subject: [Insight-users] itk::SparseFieldLevelSetImageFilter
> To: insight-users at itk.org <mailto: insight-users at itk.org>
> Message-ID:
> <a773c0740811251934y3f9e9749x63048ddad5e9cd8f at mail.gmail.com
> <mailto:a773c0740811251934y3f9e9749x63048ddad5e9cd8f at mail.gmail.com>>
> Content-Type: text/plain; charset=ISO-8859-1
>
> Insight-users,
>
> The class documentation I am referring to is here:
>
> http://www.itk.org/Doxygen/html/classitk_1_1SparseFieldLevelSetImageFilter.html
>
> Concerning the documentation and function of
> itk::SparseFieldLevelSetImageFilter, in the OUTPUTS section, it says
> that values around the active list will be the signed distance
> transform to the zero level set and otherwise it will be a fixed
> positive/negative value.
>
> In the PARAMETERS section, it says that in your computation you must
> use an appropriate number of layers and that if you do not use enough
> you may pull in random/arbitrary values from the background.
>
> At every iteration I am interested in the sign of the level set
> function at every pixel, not just those close to the zero level set. I
> am not sure what the documentation is saying. It is probably saying
> one of these:
>
> 1. During all iterations, only pixels close to the zero level set have
> meaning values and meaningful signs.
> 2. During all iterations, only pixels close to the zero level set have
> meaning values, but all pixels have meaningful signs.
>
> Could someone clarify this point?
>
> I am looking through the documentation for a way to, e.g., create an
> inside/outside mask (or an itk::SpatialObject with inside/outside) of
> the current iteration in an itk::SparseFieldLevelSetImageFilter.
>
> Thanks!
>
> Brady
>
>
> ------------------------------
>
> Message: 6
> Date: Wed, 26 Nov 2008 09:35:28 +0100
> From: Luca Antiga <luca.antiga at gmail.com <mailto:luca.antiga at gmail.com>>
> Subject: Re: [Insight-users] itk::SparseFieldLevelSetImageFilter
> To: Brady McCary <brady.mccary+ITK at gmail.com
> <mailto:brady.mccary+ITK at gmail.com>>
> Cc: insight-users at itk.org <mailto: insight-users at itk.org>
> Message-ID: <1C7CB8B4-9124-49C1-9807-CF75DD36C978 at gmail.com
> <mailto:1C7CB8B4-9124-49C1-9807-CF75DD36C978 at gmail.com>>
> Content-Type: text/plain; charset=US-ASCII; delsp=yes; format=flowed
>
> Hi Brady,
> during all iterations, only pixels close to the zero level set have
> meaningful values,
> but all pixels have meaningful signs (negative inside, positive
> outside), so it should
> be easy to do what you want to do.
> Best reagards
>
> Luca
>
>
>
> On Nov 26, 2008, at 4:34 AM, Brady McCary wrote:
>
> > Insight-users,
> >
> > The class documentation I am referring to is here:
> >
> > http://www.itk.org/Doxygen/html/
> > classitk_1_1SparseFieldLevelSetImageFilter.html
> >
> > Concerning the documentation and function of
> > itk::SparseFieldLevelSetImageFilter, in the OUTPUTS section, it says
> > that values around the active list will be the signed distance
> > transform to the zero level set and otherwise it will be a fixed
> > positive/negative value.
> >
> > In the PARAMETERS section, it says that in your computation you must
> > use an appropriate number of layers and that if you do not use enough
> > you may pull in random/arbitrary values from the background.
> >
> > At every iteration I am interested in the sign of the level set
> > function at every pixel, not just those close to the zero level
> set. I
> > am not sure what the documentation is saying. It is probably saying
> > one of these:
> >
> > 1. During all iterations, only pixels close to the zero level set
> have
> > meaning values and meaningful signs.
> > 2. During all iterations, only pixels close to the zero level set
> have
> > meaning values, but all pixels have meaningful signs.
> >
> > Could someone clarify this point?
> >
> > I am looking through the documentation for a way to, e.g., create an
> > inside/outside mask (or an itk::SpatialObject with inside/outside) of
> > the current iteration in an itk::SparseFieldLevelSetImageFilter.
> >
> > Thanks!
> >
> > Brady
> > _______________________________________________
> > Insight-users mailing list
> > Insight-users at itk.org <mailto: Insight-users at itk.org>
> > http://www.itk.org/mailman/listinfo/insight-users
>
>
>
> ------------------------------
>
> Message: 7
> Date: Wed, 26 Nov 2008 09:45:08 +0100
> From: Koen Vermeer <koen at vermeer.tv <mailto:koen at vermeer.tv>>
> Subject: Re: [Insight-users] itk::SparseFieldLevelSetImageFilter
> To: insight-users at itk.org <mailto: insight-users at itk.org>
> Message-ID: <1227689108.3735.4.camel at localhost
> <mailto:1227689108.3735.4.camel at localhost>>
> Content-Type: text/plain
>
> Hi Brady,
>
> I'd reason like this: If 1 is true, then it would introduce spurious
> zero level sets (resulting from the zero-crossings due to the sign
> changes) and there would be no way to know which zero level set is the
> 'right' one. So only 2 gives meaningful results, hence, that's probably
> the one that's implemented.
>
> >From a more practical point of view: My experience with
> itk::ThresholdSegmentationLevelSetImageFilter is that the sign is
> meaningful at all locations.
>
> Best,
> Koen
>
>
> On Tue, 2008-11-25 at 21:34 -0600, Brady McCary wrote:
> > At every iteration I am interested in the sign of the level set
> > function at every pixel, not just those close to the zero level
> set. I
> > am not sure what the documentation is saying. It is probably saying
> > one of these:
> > 1. During all iterations, only pixels close to the zero level set
> have
> > meaning values and meaningful signs.
> > 2. During all iterations, only pixels close to the zero level set
> have
> > meaning values, but all pixels have meaningful signs.
> > Could someone clarify this point?
>
>
>
>
> ------------------------------
>
> Message: 8
> Date: Wed, 26 Nov 2008 12:23:48 +0100 (CET)
> From: "Denis Shamonin" <dshamoni at science.uva.nl
> <mailto:dshamoni at science.uva.nl>>
> Subject: [Insight-users] NumericTraits level 3 warnings on VS 2008
> To: insight-users at itk.org <mailto: insight-users at itk.org>
> Message-ID:
> <25779.145.88.209.33.1227698628.squirrel at webmail.science.uva.nl
> <mailto:25779.145.88.209.33.1227698628.squirrel at webmail.science.uva.nl>>
> Content-Type: text/plain;charset=iso-8859-1
>
> Dear All,
>
> I've compile warnings on VS 2008 (Itk 3.10.0) for
>
> Class:
> NumericTraits<char> : public vcl_numeric_limits<char>
>
> Function:
> static char min() { return char(255) < 0 ? -128 : 0; }
> static char max() { return char(255) < 0 ? 127 : 255; }
>
> Warnings:
> itk3\include\common\itkNumericTraits.h(165) : warning C4310: cast
> truncates constant value
> itk3\include\common\itkNumericTraits.h(166) : warning C4310: cast
> truncates constant value
>
> Should it be changed to
> static char min() { const char minValue=255; return char(minValue) < 0 ?
> -128 : 0; }
> static char max() { const char maxValue=255; return char(maxValue) < 0 ?
> 127 : 255; }
>
>
> Thanks,
> -Denis Shamonin
>
>
>
> ------------------------------
>
> _______________________________________________
> Insight-users mailing list
> Insight-users at itk.org <mailto:Insight-users at itk.org>
> http://www.itk.org/mailman/listinfo/insight-users
>
>
> End of Insight-users Digest, Vol 55, Issue 58
> *********************************************
>
> --
> This email was checked by Astaro Security Gateway anti virus and is
> clean.
>
>
> ------------------------------------------------------------------------
>
> _______________________________________________
> Insight-users mailing list
> Insight-users at itk.org
> http://www.itk.org/mailman/listinfo/insight-users
More information about the Insight-users
mailing list