[Insight-users] Hello world program and other questions
Radhika Sivaramakrishna
rsiva02 at hotmail . com
Tue, 09 Sep 2003 13:11:59 -0700
Hello there!
I have just started with ITK and installed it on my computer with VC6. I
have the following questions:
1. I followed the directions for installation as given in the software guid.
I then tried to run the Hello World example discussed in 2.2 of the software
guide. However, it gave an error at the Linking stage namely that it couldnt
find the file ITKCommon.lib. Can you tell me what the problem is?
2. I need to use ITK to do segmentation and registration for images which
are in Analyze format. Can you tell me if there is a facility to do this?
3. Also to be able to display input and output images, is the best way to
save the images in VTK format and invoke VTK or are there any other ways to
do this?
4. I have some Java code from a different source which I would like to
incorporate into my final program. Can I just include it as one of the files
in my project?
Thanks
Radhika
----Original Message Follows----
From: insight-users-request at itk . org
Reply-To: insight-users at itk . org
To: insight-users at itk . org
Subject: Insight-users digest, Vol 1 #880 - 16 msgs
Date: Tue, 09 Sep 2003 14:16:01 -0400
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-admin 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: Segmentation Question : Breast MRI (Luis Ibanez)
2. ITK and STLPort (Aaron Boxer)
3. Stand alone project (Thimmaiah, Sandhya)
4. Distance between two 3d meshes (Aaron Boxer)
5. Re: [Insight-developers] Deadline for Special issue of MedIA on ITK
Seotember 15. (Luis Ibanez)
6. Landmarks with FEM-Registration (Ralf o Floca)
7. Re: Distance between two 3d meshes (Mark Foskey)
8. Can metrics handle nodata/void data values ? (Carolyn Johnston)
9. Re: Distance between two 3d meshes (Mathieu Malaterre)
10. Re: Can metrics handle nodata/void data values ? (Luis Ibanez)
11. Re: ITK and STLPort (Mathieu Malaterre)
12. Re: Can metrics handle nodata/void data values ? (Carolyn Johnston)
13. Re: Can metrics handle nodata/void data values ? (Luis Ibanez)
14. Data images (Thimmaiah, Sandhya)
15. Re: Can metrics handle nodata/void data values ? (Carolyn Johnston)
--__--__--
Message: 1
Date: Tue, 09 Sep 2003 09:56:04 -0400
From: Luis Ibanez <luis . ibanez at kitware . com>
To: Neha D <itkneha at yahoo . com>, insight-users at public . kitware . com
Subject: Re: [Insight-users] Segmentation Question : Breast MRI
Hi Neha,
It is not wise to process a medical image before getting familiar
with the acquisition process that was used for generating it. You
may have to do some research with whoever provided the images to
you.
The first fundamental thing to figure out is whether the image was
acquired with a contrast agent or not.
You will understand better what I meant by 'images acquired in well
controlled conditions' if you look into the acquisition process for
breast MRI. Please look at:
http://imaginis . com/breasthealth/mri . asp#how
Region growing is not probably what you need for this application.
Breast abnormalities may be very small and with non-convex shapes.
You may want to figure out first the acquisition conditions of the
images, and get together with an clinical expert that would be in
the position of showing you examples of commonly found abnormalities.
Please look at the following link for some illustrative examples
http://imaginis . com/breasthealth/mri_casestudy . asp
Regards,
Luis
-----------------
Neha D wrote:
> Hi Luis,
>
> Thanks for a very detailed reply. Currently, with the MRIs that i have,
> I am not sure if they are the images of normal breast or breast with
> abnormalities.Also, I have no absolutely no idea about if those images
> are before or after injection of gadolinium contrast agent.
> Currently, I am doing a research if i can use ITK for making this clear
> if there is any abnormaility in the breast MRI.
>
> So, without knowing this can I say, ITK facilitate the
> delineation/quantification of abnormailities? How? Can I proceed with
> any of the Region Growing Segmentatikn Algo. in ITK?
>
> Also, I did not understand what you meant by "images acquired in well
> controled conditions". Can you please explain that to me.
>
> Thanking you in advance,
> Neha
>
>
--__--__--
Message: 2
Date: Tue, 9 Sep 2003 07:32:51 -0700 (PDT)
From: Aaron Boxer <boxerab at yahoo . com>
To: "ITK Users (E-Mail)" <insight-users at itk . org>
Subject: [Insight-users] ITK and STLPort
Hello ITK Users,
I am compiling ITK with VC6.
In my other VC6 projects, I use the STLPort standard
library implementation, as it is superior to the MS
standard lib.
Are there any plans for ITK to support STLPort?
Thanks.
Aaron Boxer
__________________________________
Do you Yahoo!?
Yahoo! SiteBuilder - Free, easy-to-use web site design software
http://sitebuilder . yahoo . com
--__--__--
Message: 3
From: "Thimmaiah, Sandhya" <sthimmaiah at neurosurgery . wayne . edu>
To: "'insight-users at itk . org'" <insight-users at itk . org>
Date: Tue, 9 Sep 2003 10:50:26 -0400
Subject: [Insight-users] Stand alone project
Hi,
Can anybody let me know how to make DicomImageViewer in insight application
as a stand alone project. Can you let me know what all steps I should take
and also should I use cmake and how??. Thank you
Regards,
Sandhya Thimmaiah
--__--__--
Message: 4
Date: Tue, 9 Sep 2003 08:54:52 -0700 (PDT)
From: Aaron Boxer <boxerab at yahoo . com>
To: "'insight-users at itk . org'" <insight-users at itk . org>
Subject: [Insight-users] Distance between two 3d meshes
Hello,
I am segmenting a bell-shaped region (the retina)
inside of a 3D data set of the eye, using the 3d
deformable contour filter.
The result will be two meshes: top nd bottom surfaces.
I would like to compute the distance between these two
meshes. Is there a filter to do this?
Thanks!
Aaron Boxer
__________________________________
Do you Yahoo!?
Yahoo! SiteBuilder - Free, easy-to-use web site design software
http://sitebuilder . yahoo . com
--__--__--
Message: 5
Date: Tue, 09 Sep 2003 11:56:57 -0400
From: Luis Ibanez <luis . ibanez at kitware . com>
To: Dimitris Metaxas <dnm at cs . rutgers . edu>
Cc: Insight-developers at public . kitware . com,
Insight-users at public . kitware . com
Subject: [Insight-users] Re: [Insight-developers] Deadline for Special issue
of MedIA on ITK
Seotember 15.
Dimitris,
Just to double-check,
In order to submit papers for the special issue, is it
enough to send the PDF files by email to you or Terry ?
or is this in addition to the normal hardcopy submission.
The instructions in the MedIA web page seem to require
us to send 5 hardcopies by mail.
Submitting PDF's by email would certainly be more convenient.
Could you please comment on this,
Thanks
Luis
-----------------------
Dimitris Metaxas wrote:
> This is a final reminder that the deadline for the special issue of
> MedIA on ITK
> is September 15. (see also: http://cbim . rutgers . edu/MedIA_cfp . htm)
>
> Please send us your papers via email and in pdf format.
>
> If you have any questions please email me or Terry.
>
>
> Thanks
>
> Dimitris Metaxas
>
>
> _______________________________________________
> Insight-developers mailing list
> Insight-developers at itk . org
> http://www . itk . org/mailman/listinfo/insight-developers
>
--__--__--
Message: 6
From: "Ralf o Floca" <rfloca at stud . fh-heilbronn . de>
To: <insight-users at itk . org>
Date: Tue, 9 Sep 2003 18:08:39 +0200
Subject: [Insight-users] Landmarks with FEM-Registration
Hello
I have questions regarding the use of landmark files with the
itkFEMRegistration filter.
1. What type is the landmark file of? And how can a generate one?
2. The public function ReadConfigFile sets a landmark parameter
"Landmark variance", but there seems to be no public function to set the
parameter, if you don't use a parameter file for the setup. Is this
correct, or is there a setting function, which I missed, when reading
through the documentation?
Thank you for any help,
Ralf o Floca
--__--__--
Message: 7
Date: Tue, 09 Sep 2003 12:20:29 -0400
From: Mark Foskey <mark_foskey at unc . edu>
Organization: CADDLab, Department of Radiology, UNC Chapel Hill
To: insight-users at itk . org
Subject: Re: [Insight-users] Distance between two 3d meshes
I believe you have come up against a gap in ITK. One good approach
would be to convert one mesh to a binary image, run
itk::DanielssonDistanceMapImageFilter, and then compare the other mesh
against the resulting distance image. But there isn't a mesh-to-image
filter like that.
If the meshes are finely tessellated, you may get satisfactory results
by only working with distances between vertices. It is easy to create
a binary image from a list of points, and then you could use the
Danielsson filter. The FastMarching filter may be faster if you know
the two meshes aren't far apart, since you can set a stopping value so
it won't keep propagating the distances. Note that, for FastMarching,
you start with a list of nodes, not a binary image. This could easily
be created from the vertices of the mesh.
Aaron Boxer wrote:
> Hello,
>
> I am segmenting a bell-shaped region (the retina)
> inside of a 3D data set of the eye, using the 3d
> deformable contour filter.
>
> The result will be two meshes: top nd bottom surfaces.
> I would like to compute the distance between these two
> meshes. Is there a filter to do this?
>
> Thanks!
>
> Aaron Boxer
>
>
>
> __________________________________
> Do you Yahoo!?
> Yahoo! SiteBuilder - Free, easy-to-use web site design software
> http://sitebuilder . yahoo . com
> _______________________________________________
> Insight-users mailing list
> Insight-users at itk . org
> http://www . itk . org/mailman/listinfo/insight-users
--
Mark Foskey (919) 843-5436 Computer-Aided Diagnosis and Display Lab
mark_foskey at unc . edu Department of Radiology, CB 7515, UNC
http://www . cs . unc . edu/~foskey Chapel Hill, NC 27599-7515
--__--__--
Message: 8
Date: Tue, 09 Sep 2003 10:49:45 -0700
From: Carolyn Johnston <Carolyn . Johnston at vexcel . com>
Organization: Vexcel
To: Insight Toolkit listserv distribution <insight-users at itk . org>
Subject: [Insight-users] Can metrics handle nodata/void data values ?
I haven't found anything about this yet, either online or in the
software guide...
I have data that contains void (no data available) pixels. I am
wondering whether it is possible to identify their values to a metric,
and have it handle them appropriately. For example, if the mean squares
metric sees a nodata value in either the fixed or moving image, it might
just skip over that point. (I realize this would create normalization
problems for the metric, but this is just an example). Or nodata values
could be replaced by white noise in the metric calculation, if
normalized correlation were the metric in use.
Is anything like this already in place in Insight?
thanks,
Carolyn
--__--__--
Message: 9
Date: Tue, 09 Sep 2003 18:46:00 +0200
From: Mathieu Malaterre <Mathieu . Malaterre at creatis . insa-lyon . fr>
To: Aaron Boxer <boxerab at yahoo . com>
Cc: "'insight-users at itk . org'" <insight-users at itk . org>
Subject: Re: [Insight-users] Distance between two 3d meshes
You can use this stand alone software:
http://mesh . epfl . ch/
Maybe you can try to embbed it into ITK...
HTH
mathieu
Aaron Boxer wrote:
> Hello,
>
> I am segmenting a bell-shaped region (the retina)
> inside of a 3D data set of the eye, using the 3d
> deformable contour filter.
>
> The result will be two meshes: top nd bottom surfaces.
> I would like to compute the distance between these two
> meshes. Is there a filter to do this?
>
> Thanks!
>
> Aaron Boxer
>
>
>
> __________________________________
> Do you Yahoo!?
> Yahoo! SiteBuilder - Free, easy-to-use web site design software
> http://sitebuilder . yahoo . com
> _______________________________________________
> Insight-users mailing list
> Insight-users at itk . org
> http://www . itk . org/mailman/listinfo/insight-users
>
--
Mathieu Malaterre
CREATIS
28 Avenue du Doyen LEPINE
B.P. Lyon-Montchat
69394 Lyon Cedex 03
http://www . creatis . insa-lyon . fr/~malaterre/
--__--__--
Message: 10
Date: Tue, 09 Sep 2003 13:11:14 -0400
From: Luis Ibanez <luis . ibanez at kitware . com>
To: Carolyn Johnston <Carolyn . Johnston at vexcel . com>
Cc: Insight Toolkit listserv distribution <insight-users at itk . org>
Subject: Re: [Insight-users] Can metrics handle nodata/void data values ?
Hi Carolyn,
There has been some talk among developers for adding masking capabilities
to the ImageMetrics. In that context the metrics will accept an extra
parameter
in the form of an itkSpatialObjet that will indicate whether a point in
space
is 'inside' or 'outside' the mask. Only pixels inside the mask will be
considered
during the metric computation.
This has not been implemented yet. It is an entry on the list of 'useful
things' to
add to the toolkit.
If you are in a hurry for using such functionality you may want to try the
set of modifications below:
1) in the itkImageToImageMetric add
- a member variab le of type itk::Image<char,N> m_ImageMask
- itkSetObjectMacro( ImageMask )
2) in the specific metric : e.g. itkNormalized Correlation,
go to the GetValue() method and in the image iteratorloop
add an "if()" that will test if the pixel of the fixed image is
enabled on the mask image. If it not, the pixels is discarded
and the iterator incremented.
Masking will certainly be very useful for medical applications since
it will allow the metric to concentrate on the regions that are
relevant for the clinical application at hand.
Please let us know if you would like to have more details on
how to implement this.
Regards,
Luis
----------------------------
Carolyn Johnston wrote:
> I haven't found anything about this yet, either online or in the
> software guide...
>
> I have data that contains void (no data available) pixels. I am
> wondering whether it is possible to identify their values to a metric,
> and have it handle them appropriately. For example, if the mean
> squares metric sees a nodata value in either the fixed or moving
> image, it might just skip over that point. (I realize this would
> create normalization problems for the metric, but this is just an
> example). Or nodata values could be replaced by white noise in the
> metric calculation, if normalized correlation were the metric in use.
>
> Is anything like this already in place in Insight?
>
> thanks,
> Carolyn
>
> _______________________________________________
> Insight-users mailing list
> Insight-users at itk . org
> http://www . itk . org/mailman/listinfo/insight-users
>
--__--__--
Message: 11
Date: Tue, 09 Sep 2003 18:58:23 +0200
From: Mathieu Malaterre <Mathieu . Malaterre at creatis . insa-lyon . fr>
To: Aaron Boxer <boxerab at yahoo . com>
Cc: "ITK Users (E-Mail)" <insight-users at itk . org>
Subject: Re: [Insight-users] ITK and STLPort
Aaron,
You may want to search in the ML for previous post about BCB6 and ITK:
http://www . google . com/search?hl=fr&ie=ISO-8859-1&q=+site%3Awww . itk . org+borland+BCB6+insight-users&btnG=Recherche+Google&lr=
I know that Borland 6 is shipped with STLPort, but there seems to be
some compilation problems for now.
HTH
mathieu
Aaron Boxer wrote:
> Hello ITK Users,
>
> I am compiling ITK with VC6.
>
> In my other VC6 projects, I use the STLPort standard
> library implementation, as it is superior to the MS
> standard lib.
>
> Are there any plans for ITK to support STLPort?
>
> Thanks.
>
> Aaron Boxer
>
> __________________________________
> Do you Yahoo!?
> Yahoo! SiteBuilder - Free, easy-to-use web site design software
> http://sitebuilder . yahoo . com
> _______________________________________________
> Insight-users mailing list
> Insight-users at itk . org
> http://www . itk . org/mailman/listinfo/insight-users
>
--
Mathieu Malaterre
CREATIS
28 Avenue du Doyen LEPINE
B.P. Lyon-Montchat
69394 Lyon Cedex 03
http://www . creatis . insa-lyon . fr/~malaterre/
--__--__--
Message: 12
Date: Tue, 09 Sep 2003 11:45:32 -0700
From: Carolyn Johnston <Carolyn . Johnston at vexcel . com>
Organization: Vexcel
To: Luis Ibanez <luis . ibanez at kitware . com>
Cc: Insight Toolkit listserv distribution <insight-users at itk . org>
Subject: Re: [Insight-users] Can metrics handle nodata/void data values ?
Hi Luis,
I think that the itkSpatialObject solution would solve only half of the
problem. A mask object could be constructed using the void data points
of the fixed image, but the metric would also need to be aware of the
void points of the moving image, the location in space of which would be
changing all the time. Of course, it is the void points in the moving
image which cause problems with mean squares metric normalization
anyway, since as the moving image moves, the number of void points in
the fixed image region (at least in the case of the mean squares metric
-- we could probably make it work for the normalized correlation metric).
So I will keep thinking about this. I hope your busy week isn't too crazy.
:) Carolyn
--__--__--
Message: 13
Date: Tue, 09 Sep 2003 14:01:15 -0400
From: Luis Ibanez <luis . ibanez at kitware . com>
To: Carolyn Johnston <Carolyn . Johnston at vexcel . com>
Cc: Insight Toolkit listserv distribution <insight-users at itk . org>
Subject: Re: [Insight-users] Can metrics handle nodata/void data values ?
Hi Carolyn,
I probably missunderstood what you meant by "void" points,
or "void" pixels. I assumed that those were pixels where the
data is not valid. For example is the image is the result of resampling
another image, and some areas didn't got any pixel data. That's common
with ultrasound images.
Could you explain why the "void" pixels will keep changing ?
Shouldn't they be the same during the entire registration process ?
Thanks
Luis
-----------------------------
Carolyn Johnston wrote:
> Hi Luis,
>
> I think that the itkSpatialObject solution would solve only half of
> the problem. A mask object could be constructed using the void data
> points of the fixed image, but the metric would also need to be aware
> of the void points of the moving image, the location in space of which
> would be changing all the time. Of course, it is the void points in
> the moving image which cause problems with mean squares metric
> normalization anyway, since as the moving image moves, the number of
> void points in the fixed image region (at least in the case of the
> mean squares metric -- we could probably make it work for the
> normalized correlation metric).
>
> So I will keep thinking about this. I hope your busy week isn't too
> crazy.
>
> :) Carolyn
>
> _______________________________________________
> Insight-users mailing list
> Insight-users at itk . org
> http://www . itk . org/mailman/listinfo/insight-users
>
--__--__--
Message: 14
From: "Thimmaiah, Sandhya" <sthimmaiah at neurosurgery . wayne . edu>
To: "'insight-users at itk . org'" <insight-users at itk . org>
Date: Tue, 9 Sep 2003 14:05:29 -0400
Subject: [Insight-users] Data images
Hi,
I have not been able to find brainweb89.png or
brainweb89_train.png images for GibbsPriorFilter1. Could
someone guide me how to acquire these files or provide me
with these images.
Thanks
--__--__--
Message: 15
Date: Tue, 09 Sep 2003 12:10:48 -0700
From: Carolyn Johnston <Carolyn . Johnston at vexcel . com>
Organization: Vexcel
To: Luis Ibanez <luis . ibanez at kitware . com>
Cc: Insight Toolkit listserv distribution <insight-users at itk . org>
Subject: Re: [Insight-users] Can metrics handle nodata/void data values ?
> Hi Carolyn,
>
> I probably missunderstood what you meant by "void" points,
> or "void" pixels. I assumed that those were pixels where the
> data is not valid. For example is the image is the result of resampling
> another image, and some areas didn't got any pixel data. That's common
> with ultrasound images.
>
> Could you explain why the "void" pixels will keep changing ?
> Shouldn't they be the same during the entire registration process ?
>
> Thanks
>
> Luis
No, you have the right idea, although my images tend to be shot through
with little clumps of void data here and there.
I am not saying that the locations of the void pixels in *image* space
will change, (they won't) but as different transforms from the parameter
space are applied, the locations of the moving image's voids in the
fixed image's frame of reference will change. As I understood it, in
your previous post you were talking about using a spatial object --
referenced to coordinate space, not image space -- to define the void
mask. But both the fixed and moving images are likely to have voids.
Carolyn
--__--__--
_______________________________________________
Insight-users mailing list
Insight-users at itk . org
http://www . itk . org/mailman/listinfo/insight-users
End of Insight-users Digest
_________________________________________________________________
Need more e-mail storage? Get 10MB with Hotmail Extra Storage.
http://join . msn . com/?PAGE=features/es