From isshaa7 at gmail.com  Thu Jun  1 22:09:55 2017
From: isshaa7 at gmail.com (slvnk151)
Date: Thu, 1 Jun 2017 19:09:55 -0700 (MST)
Subject: [ITK-users] quickview header not found with recent itk4.11.1
Message-ID: <1496369395820-7589996.post@n2.nabble.com>

Hi Everyone,

I was interested in integrating vtk and itk for my laptop.

I am using latest cmake 3.8.1, VTK 7.1.1 and ITK4.11.1

I am on windows 7 and using visual studio 2017 community edition.

I managed to build and test vtk 7.1.1 on my laptop.

I was also able to configure and generate ITK 4.11.1 with cmake 3.8.1

I turned on the module Module_ITKVtkGlue and pointed VTK_DIR towards vtk/bin
(obtained with cmake generation) on my computer.

I was also interested in Module_ITKMINC and Module_ITKIOMINC and
Module_ITKIOTRansformMINC

When I am building the ITK.sln(243 projects) in debug x64 mode using
ALL_BUILD->build

I am getting build errors for MINC module, which I am ignoring at the
moment.

Then I build INSTALL->build; which obviously fails for minc but is
successful for the rest.

But when I try to locate  "QuickView.h" in the include folder I am unable to
find it. This causes linker errors when trying to implement vtk-itk
examples.

I would like to know, how can I resolve the quickview.h header issue and
also how can I make ITK.sln build successfully for MINC modules.

Could someone please tell me what step am I missing.




--
View this message in context: http://itk-insight-users.2283740.n2.nabble.com/quickview-header-not-found-with-recent-itk4-11-1-tp7589996.html
Sent from the ITK Insight Users mailing list archive at Nabble.com.

From matt.mccormick at kitware.com  Fri Jun  2 10:20:40 2017
From: matt.mccormick at kitware.com (Matt McCormick)
Date: Fri, 2 Jun 2017 10:20:40 -0400
Subject: [ITK-users] quickview header not found with recent itk4.11.1
In-Reply-To: <1496369395820-7589996.post@n2.nabble.com>
References: <1496369395820-7589996.post@n2.nabble.com>
Message-ID: <CALzTN-Ry=jeWrN_s2xAYy9mj48NMS2xzWg8f5WKNDOpZp1-Q4A@mail.gmail.com>

Hi,

The MINC build issue has been addressed in ITK 4.12.0, which will be
released within the next week. Please try your build again with this
version and see if the missing QuickView.h issue persists.

Thanks,
Matt

On Thu, Jun 1, 2017 at 10:09 PM, slvnk151 <isshaa7 at gmail.com> wrote:

> Hi Everyone,
>
> I was interested in integrating vtk and itk for my laptop.
>
> I am using latest cmake 3.8.1, VTK 7.1.1 and ITK4.11.1
>
> I am on windows 7 and using visual studio 2017 community edition.
>
> I managed to build and test vtk 7.1.1 on my laptop.
>
> I was also able to configure and generate ITK 4.11.1 with cmake 3.8.1
>
> I turned on the module Module_ITKVtkGlue and pointed VTK_DIR towards
> vtk/bin
> (obtained with cmake generation) on my computer.
>
> I was also interested in Module_ITKMINC and Module_ITKIOMINC and
> Module_ITKIOTRansformMINC
>
> When I am building the ITK.sln(243 projects) in debug x64 mode using
> ALL_BUILD->build
>
> I am getting build errors for MINC module, which I am ignoring at the
> moment.
>
> Then I build INSTALL->build; which obviously fails for minc but is
> successful for the rest.
>
> But when I try to locate  "QuickView.h" in the include folder I am unable
> to
> find it. This causes linker errors when trying to implement vtk-itk
> examples.
>
> I would like to know, how can I resolve the quickview.h header issue and
> also how can I make ITK.sln build successfully for MINC modules.
>
> Could someone please tell me what step am I missing.
>
>
>
>
> --
> View this message in context: http://itk-insight-users.
> 2283740.n2.nabble.com/quickview-header-not-found-with-recent-itk4-11-1-
> tp7589996.html
> Sent from the ITK Insight Users mailing list archive at Nabble.com.
> _____________________________________
> Powered by www.kitware.com
>
> Visit other Kitware open-source projects at
> http://www.kitware.com/opensource/opensource.html
>
> Kitware offers ITK Training Courses, for more information visit:
> http://www.kitware.com/products/protraining.php
>
> Please keep messages on-topic and check the ITK FAQ at:
> http://www.itk.org/Wiki/ITK_FAQ
>
> Follow this link to subscribe/unsubscribe:
> http://public.kitware.com/mailman/listinfo/insight-users
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://public.kitware.com/pipermail/insight-users/attachments/20170602/4f1d7ac2/attachment.html>

From dzenanz at gmail.com  Fri Jun  2 10:28:28 2017
From: dzenanz at gmail.com (=?UTF-8?B?RMW+ZW5hbiBadWtpxIc=?=)
Date: Fri, 2 Jun 2017 10:28:28 -0400
Subject: [ITK-users] quickview header not found with recent itk4.11.1
In-Reply-To: <1496369395820-7589996.post@n2.nabble.com>
References: <1496369395820-7589996.post@n2.nabble.com>
Message-ID: <CAPf2UMSuPFd+Ls24Qh_ow+y=ghUkSBA2GwvNUCymP083NB5T4A@mail.gmail.com>

Hi Isshaa,

thanks for a clear report on what is happening. I just tried installing
recent ITK master in debug mode with VTK_Glue on, and I do get QuickView.h
in C:\Program Files\ITK\Include folder. If you don't want to wait for 4.12
release, you could try one of the recent release candidates or the current
git master.

Regards,
D?enan Zuki?, PhD, Senior R&D Engineer, Kitware (Carrboro, N.C.)

On Thu, Jun 1, 2017 at 10:09 PM, slvnk151 <isshaa7 at gmail.com> wrote:

> Hi Everyone,
>
> I was interested in integrating vtk and itk for my laptop.
>
> I am using latest cmake 3.8.1, VTK 7.1.1 and ITK4.11.1
>
> I am on windows 7 and using visual studio 2017 community edition.
>
> I managed to build and test vtk 7.1.1 on my laptop.
>
> I was also able to configure and generate ITK 4.11.1 with cmake 3.8.1
>
> I turned on the module Module_ITKVtkGlue and pointed VTK_DIR towards
> vtk/bin
> (obtained with cmake generation) on my computer.
>
> I was also interested in Module_ITKMINC and Module_ITKIOMINC and
> Module_ITKIOTRansformMINC
>
> When I am building the ITK.sln(243 projects) in debug x64 mode using
> ALL_BUILD->build
>
> I am getting build errors for MINC module, which I am ignoring at the
> moment.
>
> Then I build INSTALL->build; which obviously fails for minc but is
> successful for the rest.
>
> But when I try to locate  "QuickView.h" in the include folder I am unable
> to
> find it. This causes linker errors when trying to implement vtk-itk
> examples.
>
> I would like to know, how can I resolve the quickview.h header issue and
> also how can I make ITK.sln build successfully for MINC modules.
>
> Could someone please tell me what step am I missing.
>
>
>
>
> --
> View this message in context: http://itk-insight-users.
> 2283740.n2.nabble.com/quickview-header-not-found-with-recent-itk4-11-1-
> tp7589996.html
> Sent from the ITK Insight Users mailing list archive at Nabble.com.
> _____________________________________
> Powered by www.kitware.com
>
> Visit other Kitware open-source projects at
> http://www.kitware.com/opensource/opensource.html
>
> Kitware offers ITK Training Courses, for more information visit:
> http://www.kitware.com/products/protraining.php
>
> Please keep messages on-topic and check the ITK FAQ at:
> http://www.itk.org/Wiki/ITK_FAQ
>
> Follow this link to subscribe/unsubscribe:
> http://public.kitware.com/mailman/listinfo/insight-users
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://public.kitware.com/pipermail/insight-users/attachments/20170602/c8db1389/attachment.html>

From noreply at insightsoftwareconsortium.org  Fri Jun  2 10:58:10 2017
From: noreply at insightsoftwareconsortium.org (Insight Journal)
Date: Fri,  2 Jun 2017 10:58:10 -0400 (EDT)
Subject: [ITK-users] New Submission: Isotropic and Steerable Wavelets in N
	Dimensions. A multiresolution analysis framework.
Message-ID: <20170602145811.515E43D620D2@insight-journal.org>

Hello,

A new submission has been added to the Insight Journal.

Title: Isotropic and Steerable Wavelets in N Dimensions. A multiresolution analysis framework.
Authors: Hernandez-Cerdan P.
Abstract: This document describes the implementation of the external module ITKIsotropicWavelets, a multiresolution (MRA) analysis framework using isotropic and steerable wavelets in the frequency domain. This framework provides the backbone for state of the art filters for denoising, feature detection or phase analysis in N-dimensions. It focus on reusability, and highly decoupled modules for easy extension and implementation of new filters, and it contains a filter for multiresolution phase analysis,

The backbone of the multi-scale analysis is provided by an isotropic band-limited wavelet pyramid, and the detection of directional features is provided by coupling the pyramid with a generalized Riesz transform.
The generalized Riesz transform of order N behaves like a smoothed version of the Nth order derivatives of the signal. Also, it is steerable: its components impulse responses can be rotated to any spatial orientation, reducing computation time when detecting directional features.

This paper is accompanied with the source code, input data, parameters and
output data that the author used for validating the algorithm described in
this paper. This adheres to the fundamental principle that scientific
publications must facilitate reproducibility of the reported results.


Download and review this publication at: http://hdl.handle.net/10380/3558

Generated by the Insight Journal

You are receiving this email because you asked to be informed by the Insight Journal for new submissions. To change your email preference visit http://www.insight-journal.org/ .

From dr.tim.allman at gmail.com  Mon Jun  5 10:06:40 2017
From: dr.tim.allman at gmail.com (Tim Allman)
Date: Mon, 5 Jun 2017 10:06:40 -0400
Subject: [ITK-users] itkDICOMSeriesFileNames
Message-ID: <644a5a5f-7d51-b9c5-0c06-3ef66c74ecca@gmail.com>

I have been looking at reading and writing DICOM images and it didn't 
take long to stumble upon the class itkDICOMSeriesFileNames. It is 
however, almost undocumented in the Guide and is completely without 
Doxygen documentation 
(https://itk.org/Doxygen/html/itkDICOMSeriesFileNames_8h.html) but is 
used in the examples. I see as well that the file 
itkDICOMSeriesFileNames.h is located in 
/Modules/Compatibility/Deprecated// suggesting that I should be using 
something else.

Is DCMTK the preferred package now?

Thanks,
Tim

-- 
Tim Allman Ph.D.,
35 Margaret St.,
Guelph, Ont.,
N1E 5R6
Canada
519-837-0276

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://public.kitware.com/pipermail/insight-users/attachments/20170605/b6a2f576/attachment.html>

From keepdash at hotmail.com  Tue Jun  6 03:57:41 2017
From: keepdash at hotmail.com (keepdash)
Date: Tue, 6 Jun 2017 00:57:41 -0700 (MST)
Subject: [ITK-users]  ComputeMeanCurvature() in itkLevelSetFunction.hxx
Message-ID: <1496735861540-7590001.post@n2.nabble.com>

>From level set papers, we can find the curvature (2D) is: 

 K = (fxx*fy*fy + fyy*fx*fx - 2*fx*fy*fxy) / (fx*fx+fy*fy)^(3/2)

I compared the equation with the code in "itkLevelSetFunction.hxx", all same
except the normalization, seems in ITK, the curvature (2D) is computed as: 

K = (fxx*fy*fy + fyy*fx*fx - 2*fx*fy*fxy) / (fx*fx+fy*fy)

which can be found in function ComputeMeanCurvature(), line.179:
 
  return ( curvature_term / gd->m_GradMagSqr );

where the "m_GradMagSqr" is the fx*fx+fy*fy from line.332.

Then, why ITK use this way, is it better?

Thank you.



--
View this message in context: http://itk-insight-users.2283740.n2.nabble.com/ITK-users-ComputeMeanCurvature-in-itkLevelSetFunction-hxx-tp7590001.html
Sent from the ITK Insight Users mailing list archive at Nabble.com.

From gavinb+itk at antonym.org  Tue Jun  6 04:00:16 2017
From: gavinb+itk at antonym.org (Gavin Baker)
Date: Tue, 06 Jun 2017 18:00:16 +1000
Subject: [ITK-users] Super-resolution resampling
Message-ID: <1496736016.3944632.1000082120.177CCA64@webmail.messagingengine.com>

Hello!

I have a time series of 3D data (relatively low resolution), captured in
sequence, with small positional changes (eg. translation). I would like
to perform a super-resolution resampling by first co-registering each
volumetric dataset (using rigid registration) in order to reduce noise
and improve detail.

Is there a registration process that is 1:N (fixed:moving)?

Or is the recommended method to pick a fixed image (ie. #0) and register
each 1..N individually to it?

Given a set of transforms that map each of the 1..N moving images back
to the fixed image for registration, is it possible to then resample the
volume at a higher spatial resolution, combining all image data? IOW
super-resolution resampling?

I tried searching for the above and didn't have much luck finding
relevant info.

Thanks -

  :: Gavin

From dzenanz at gmail.com  Tue Jun  6 09:16:27 2017
From: dzenanz at gmail.com (=?UTF-8?B?RMW+ZW5hbiBadWtpxIc=?=)
Date: Tue, 6 Jun 2017 09:16:27 -0400
Subject: [ITK-users] Super-resolution resampling
In-Reply-To: <1496736016.3944632.1000082120.177CCA64@webmail.messagingengine.com>
References: <1496736016.3944632.1000082120.177CCA64@webmail.messagingengine.com>
Message-ID: <CAPf2UMQE0HvcfqQvfgXCJXY3WEf7-4OHFfH1Se_SwzsO01CL+w@mail.gmail.com>

Hi Gavin,

your plan sounds good! There is no 1:N registration, so you should proceed
with N 1:1 registrations. Pick one as a reference (#0 is good), register
all the other time points to it. You can initialize the k+1-st iteration by
the resulting transform of k-th registration to speed things up.

And yes, you can do super-resolution by resampling all these images onto a
higher resolution grid, e.g. same origin and direction, 2x higher size and
2x smaller spacing.

ITK has all the required classes for this process. Will you let us know how
satisfactory the result was? Ideally with some images :)

Regards,
D?enan Zuki?, PhD, Senior R&D Engineer, Kitware (Carrboro, N.C.)

On Tue, Jun 6, 2017 at 4:00 AM, Gavin Baker <gavinb+itk at antonym.org> wrote:

> Hello!
>
> I have a time series of 3D data (relatively low resolution), captured in
> sequence, with small positional changes (eg. translation). I would like
> to perform a super-resolution resampling by first co-registering each
> volumetric dataset (using rigid registration) in order to reduce noise
> and improve detail.
>
> Is there a registration process that is 1:N (fixed:moving)?
>
> Or is the recommended method to pick a fixed image (ie. #0) and register
> each 1..N individually to it?
>
> Given a set of transforms that map each of the 1..N moving images back
> to the fixed image for registration, is it possible to then resample the
> volume at a higher spatial resolution, combining all image data? IOW
> super-resolution resampling?
>
> I tried searching for the above and didn't have much luck finding
> relevant info.
>
> Thanks -
>
>   :: Gavin
> _____________________________________
> Powered by www.kitware.com
>
> Visit other Kitware open-source projects at
> http://www.kitware.com/opensource/opensource.html
>
> Kitware offers ITK Training Courses, for more information visit:
> http://www.kitware.com/products/protraining.php
>
> Please keep messages on-topic and check the ITK FAQ at:
> http://www.itk.org/Wiki/ITK_FAQ
>
> Follow this link to subscribe/unsubscribe:
> http://public.kitware.com/mailman/listinfo/insight-users
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://public.kitware.com/pipermail/insight-users/attachments/20170606/d7aa1654/attachment.html>

From gavinb+itk at antonym.org  Tue Jun  6 20:39:49 2017
From: gavinb+itk at antonym.org (Gavin Baker)
Date: Wed, 07 Jun 2017 10:39:49 +1000
Subject: [ITK-users] Super-resolution resampling
In-Reply-To: <CAPf2UMQE0HvcfqQvfgXCJXY3WEf7-4OHFfH1Se_SwzsO01CL+w@mail.gmail.com>
References: <1496736016.3944632.1000082120.177CCA64@webmail.messagingengine.com>
 <CAPf2UMQE0HvcfqQvfgXCJXY3WEf7-4OHFfH1Se_SwzsO01CL+w@mail.gmail.com>
Message-ID: <1496795989.695579.1001111152.7610AC76@webmail.messagingengine.com>


Thanks, D?enan -

I'll start with the N x 1:1 registration then.

I can see how to resample the moving image, with the transform applied,
as per the examples. However it is not clear how to _combine_ the N
images together for the super-resolution resampling. Or would it be a
two-step process, where each moving image is first resampled, and after
that they are averaged together?
Thanks -

  :: Gavin


On Tue, 6 Jun 2017, at 11:16 PM, D?enan Zuki? wrote:
> Hi Gavin,
> 
> your plan sounds good! There is no 1:N registration, so you should
> proceed with N 1:1 registrations. Pick one as a reference (#0 is
> good), register all the other time points to it. You can initialize
> the k+1-st iteration by the resulting transform of k-th registration
> to speed things up.> 
> And yes, you can do super-resolution by resampling all these images
> onto a higher resolution grid, e.g. same origin and direction, 2x
> higher size and 2x smaller spacing.> 
> ITK has all the required classes for this process. Will you let us
> know how satisfactory the result was? Ideally with some images :)> 
> Regards,
> D?enan Zuki?, PhD, Senior R&D Engineer, Kitware (Carrboro, N.C.)
> 
> On Tue, Jun 6, 2017 at 4:00 AM, Gavin Baker
> <gavinb+itk at antonym.org> wrote:>> Hello!
>> 
>>  I have a time series of 3D data (relatively low resolution),
>>  captured in>>  sequence, with small positional changes (eg. translation). I
>>  would like>>  to perform a super-resolution resampling by first co-
>>  registering each>>  volumetric dataset (using rigid registration) in order to
>>  reduce noise>>  and improve detail.
>> 
>>  Is there a registration process that is 1:N (fixed:moving)?
>> 
>>  Or is the recommended method to pick a fixed image (ie. #0) and
>>  register>>  each 1..N individually to it?
>> 
>>  Given a set of transforms that map each of the 1..N moving
>>  images back>>  to the fixed image for registration, is it possible to then
>>  resample the>>  volume at a higher spatial resolution, combining all image data? IOW>>  super-resolution resampling?
>> 
>>  I tried searching for the above and didn't have much luck finding
>>  relevant info.
>> 
>>  Thanks -
>> 
>>    :: Gavin
>>  _____________________________________
>>  Powered by www.kitware.com
>> 
>>  Visit other Kitware open-source projects at
>> http://www.kitware.com/opensource/opensource.html
>> 
>>  Kitware offers ITK Training Courses, for more information visit:
>> http://www.kitware.com/products/protraining.php
>> 
>>  Please keep messages on-topic and check the ITK FAQ at:
>> http://www.itk.org/Wiki/ITK_FAQ
>> 
>>  Follow this link to subscribe/unsubscribe:
>> http://public.kitware.com/mailman/listinfo/insight-users

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://public.kitware.com/pipermail/insight-users/attachments/20170607/73434945/attachment.html>

From gavinb+itk at antonym.org  Tue Jun  6 20:41:35 2017
From: gavinb+itk at antonym.org (Gavin Baker)
Date: Wed, 07 Jun 2017 10:41:35 +1000
Subject: [ITK-users] [ITK]  Super-resolution resampling
In-Reply-To: <CAJjw+_Zi95xD7vLXBMTENMJnE7qT_iHRAqez_53Z2uP2=J5PyA@mail.gmail.com>
References: <1496736016.3944632.1000082120.177CCA64@webmail.messagingengine.com>
 <CAPf2UMQE0HvcfqQvfgXCJXY3WEf7-4OHFfH1Se_SwzsO01CL+w@mail.gmail.com>
 <CAJjw+_Zi95xD7vLXBMTENMJnE7qT_iHRAqez_53Z2uP2=J5PyA@mail.gmail.com>
Message-ID: <1496796095.695716.1001112368.68B6224E@webmail.messagingengine.com>


Thanks, Samuel,

Great point - using the N/2 sample makes a lot of sense.  I'll start
with that example and see how I go. Any thoughts on my followup question
about the super-resolution resampling the N images together would be
most appreciated.
Regards -

  :: Gavin

On Tue, 6 Jun 2017, at 11:33 PM, Samuel Gerber wrote:
> Hi Gavin,
> 
> One small addition, I would probably take the N/2 image to register
> everybody else to, in order to minimize the maximal transformation
> (might not matter in your case since it is only small transformations
> but it could minimize errors due to resampling).> 
> This example has all the required classes you should need:
> https://itk.org/Wiki/ITK/Examples/Registration/ImageRegistrationMethod> 
> You will most likely want to use a different optimizer and you can see
> in the code how to set the size etc of the output image in the
> resampler.> 
> 
> On Tue, Jun 6, 2017 at 9:16 AM, D?enan Zuki?
> <dzenanz at gmail.com> wrote:>> Hi Gavin,
>> 
>> your plan sounds good! There is no 1:N registration, so you should
>> proceed with N 1:1 registrations. Pick one as a reference (#0 is
>> good), register all the other time points to it. You can initialize
>> the k+1-st iteration by the resulting transform of k-th registration
>> to speed things up.>> 
>> And yes, you can do super-resolution by resampling all these images
>> onto a higher resolution grid, e.g. same origin and direction, 2x
>> higher size and 2x smaller spacing.>> 
>> ITK has all the required classes for this process. Will you let us
>> know how satisfactory the result was? Ideally with some images :)>> 
>> Regards,
>> D?enan Zuki?, PhD, Senior R&D Engineer, Kitware (Carrboro, N.C.)
>> 
>> On Tue, Jun 6, 2017 at 4:00 AM, Gavin Baker
>> <gavinb+itk at antonym.org> wrote:>>> Hello!
>>> 
>>>  I have a time series of 3D data (relatively low resolution),
>>>  captured in>>>  sequence, with small positional changes (eg. translation). I
>>>  would like>>>  to perform a super-resolution resampling by first co-
>>>  registering each>>>  volumetric dataset (using rigid registration) in order to reduce
>>>  noise>>>  and improve detail.
>>> 
>>>  Is there a registration process that is 1:N (fixed:moving)?
>>> 
>>>  Or is the recommended method to pick a fixed image (ie. #0) and
>>>  register>>>  each 1..N individually to it?
>>> 
>>>  Given a set of transforms that map each of the 1..N moving
>>>  images back>>>  to the fixed image for registration, is it possible to then
>>>  resample the>>>  volume at a higher spatial resolution, combining all image
>>>  data? IOW>>>  super-resolution resampling?
>>> 
>>>  I tried searching for the above and didn't have much luck finding
>>>  relevant info.
>>> 
>>>  Thanks -
>>> 
>>>    :: Gavin
>>>  _____________________________________
>>>  Powered by www.kitware.com
>>> 
>>>  Visit other Kitware open-source projects at
>>> http://www.kitware.com/opensource/opensource.html
>>> 
>>>  Kitware offers ITK Training Courses, for more information visit:
>>> http://www.kitware.com/products/protraining.php
>>> 
>>>  Please keep messages on-topic and check the ITK FAQ at:
>>> http://www.itk.org/Wiki/ITK_FAQ
>>> 
>>>  Follow this link to subscribe/unsubscribe:
>>> http://public.kitware.com/mailman/listinfo/insight-users
>> 
>> 
>> _____________________________________
>>  Powered by www.kitware.com
>> 
>>  Visit other Kitware open-source projects at
>> http://www.kitware.com/opensource/opensource.html
>> 
>>  Kitware offers ITK Training Courses, for more information visit:
>> http://www.kitware.com/products/protraining.php
>> 
>>  Please keep messages on-topic and check the ITK FAQ at:
>> http://www.itk.org/Wiki/ITK_FAQ
>> 
>>  Follow this link to subscribe/unsubscribe:
>> http://public.kitware.com/mailman/listinfo/insight-users
>> 
>> _______________________________________________
>>  Community mailing list
>> Community at itk.org
>> http://public.kitware.com/mailman/listinfo/community
>> 
> 
> 
> 
> -- 
> Samuel Gerber
> R&D Engineer
> Kitware, Inc.

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://public.kitware.com/pipermail/insight-users/attachments/20170607/07ce3fe4/attachment.html>

From dzenanz at gmail.com  Tue Jun  6 21:32:12 2017
From: dzenanz at gmail.com (=?UTF-8?B?RMW+ZW5hbiBadWtpxIc=?=)
Date: Tue, 6 Jun 2017 21:32:12 -0400
Subject: [ITK-users] Super-resolution resampling
In-Reply-To: <1496795989.695579.1001111152.7610AC76@webmail.messagingengine.com>
References: <1496736016.3944632.1000082120.177CCA64@webmail.messagingengine.com>
 <CAPf2UMQE0HvcfqQvfgXCJXY3WEf7-4OHFfH1Se_SwzsO01CL+w@mail.gmail.com>
 <1496795989.695579.1001111152.7610AC76@webmail.messagingengine.com>
Message-ID: <CAPf2UMQJNQTKAFk80fQum-KkKXYxd73LOu8rkG0hUSnxHz_zMg@mail.gmail.com>

Hi Gavin,

if you want to avoid keeping N resampled images, you could have a sum of
resampled images which you divide by N at the end to get the average.

Regards,
D?enan Zuki?, PhD, Senior R&D Engineer, Kitware (Carrboro, N.C.)

On Tue, Jun 6, 2017 at 8:39 PM, Gavin Baker <gavinb+itk at antonym.org> wrote:

>
> Thanks, D?enan -
>
> I'll start with the N x 1:1 registration then.
>
> I can see how to resample the moving image, with the transform applied, as
> per the examples. However it is not clear how to _combine_ the N images
> together for the super-resolution resampling. Or would it be a two-step
> process, where each moving image is first resampled, and after that they
> are averaged together?
>
> Thanks -
>
>   :: Gavin
>
>
> On Tue, 6 Jun 2017, at 11:16 PM, D?enan Zuki? wrote:
>
> Hi Gavin,
>
> your plan sounds good! There is no 1:N registration, so you should proceed
> with N 1:1 registrations. Pick one as a reference (#0 is good), register
> all the other time points to it. You can initialize the k+1-st iteration by
> the resulting transform of k-th registration to speed things up.
>
> And yes, you can do super-resolution by resampling all these images onto a
> higher resolution grid, e.g. same origin and direction, 2x higher size and
> 2x smaller spacing.
>
> ITK has all the required classes for this process. Will you let us know
> how satisfactory the result was? Ideally with some images :)
>
> Regards,
> D?enan Zuki?, PhD, Senior R&D Engineer, Kitware (Carrboro, N.C.)
>
> On Tue, Jun 6, 2017 at 4:00 AM, Gavin Baker <gavinb+itk at antonym.org>
> wrote:
>
> Hello!
>
> I have a time series of 3D data (relatively low resolution), captured in
> sequence, with small positional changes (eg. translation). I would like
> to perform a super-resolution resampling by first co-registering each
> volumetric dataset (using rigid registration) in order to reduce noise
> and improve detail.
>
> Is there a registration process that is 1:N (fixed:moving)?
>
> Or is the recommended method to pick a fixed image (ie. #0) and register
> each 1..N individually to it?
>
> Given a set of transforms that map each of the 1..N moving images back
> to the fixed image for registration, is it possible to then resample the
> volume at a higher spatial resolution, combining all image data? IOW
> super-resolution resampling?
>
> I tried searching for the above and didn't have much luck finding
> relevant info.
>
> Thanks -
>
>   :: Gavin
> _____________________________________
> Powered by www.kitware.com
>
> Visit other Kitware open-source projects at
> http://www.kitware.com/opensource/opensource.html
>
> Kitware offers ITK Training Courses, for more information visit:
> http://www.kitware.com/products/protraining.php
>
> Please keep messages on-topic and check the ITK FAQ at:
> http://www.itk.org/Wiki/ITK_FAQ
>
> Follow this link to subscribe/unsubscribe:
> http://public.kitware.com/mailman/listinfo/insight-users
>
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://public.kitware.com/pipermail/insight-users/attachments/20170606/f219b94f/attachment.html>

From nicolas.courtial at univ-rennes1.fr  Wed Jun  7 05:46:17 2017
From: nicolas.courtial at univ-rennes1.fr (Nicolas Courtial)
Date: Wed, 7 Jun 2017 11:46:17 +0200
Subject: [ITK-users] MultiThreading, ImageRegionIterator crash
Message-ID: <13d4dc31-8fb8-40c1-ccd8-abe4e45555ef@univ-rennes1.fr>

Hello everyone,

I'm quite new in ITK world, and I'm currently doing few experiences in 
order to learn its logic.

After few easy exercices, I'm now at a step I want to multithread a method.
As I did in the past, I've been reading the ITK classes to get 
"inspiration", and e- mails from here in case of troubles.

I'm facing an issue at the moment, and I can't figure why, and how to 
solve it.

My filter works with

  * One 3D InputImage (of any pixel type)
  * Two "tool" 3D images, respectively of float and unsigned char pixel
    types

 From what I read, I've understood there are two main ways of 
multithreading:

  * The old fashioned one using
    BeforeThreadedGenerateData/ThreadedGenerateData/AfterThreadedGenerateData
  * the one using itk::DomainThreader member.

As I'm a bit old school, I used the first option.

My problem remains here: (I changed my variables' name to make it clearer)

ThreadedComputation(const OutputImageRegionType &outputRegionForThread, 
ThreadIdType threadId) {
         itk::ProgressReporter progress(this, threadId, 
outputRegionForThread.GetNumberOfPixels());
         typename TOutputImage::Pointer image = this->GetOutput(0);

         itk::ImageRegionIterator< TOutputImage > imgIt(image, 
outputRegionForThread);
         itk::ImageRegionIterator< FloatImageType> floatIt 
(m_MyFloatImage, outputRegionForThread);
     ....

When creating the floatIt iterator, I have a crash. Using a try catch 
block, the issue is due to out of bound region.
Everything is correct, but the index, for which it's completly crazy 
([156245468,0,156245468] or something approching).

I've tried different options to solve this, but rather than doing 
witchcraft and at some point getting something working, I'd prefer to 
improve my understanding thanks to your expertise.

Thanks all,

Nicolas Courtial




-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://public.kitware.com/pipermail/insight-users/attachments/20170607/b64aad92/attachment.html>

From xieyi4650 at 126.com  Wed Jun  7 07:45:00 2017
From: xieyi4650 at 126.com (XieYi)
Date: Wed, 7 Jun 2017 04:45:00 -0700 (MST)
Subject: [ITK-users] why jpg image that is converted from a mhd image is so
	weird ?
Message-ID: <1496835900201-38307.post@n7.nabble.com>

the mhd image in ParaView software is like this:
<http://itk-users.7.n7.nabble.com/file/n38307/gt1.png> 
after being converted to jpg image, it is like this 
<http://itk-users.7.n7.nabble.com/file/n38307/drr.jpg> 

here is my converting code:

typedef float PixelType;
const unsigned int Dimension = 3;
typedef itk::Matrix<double, 3, 3> MatrixType;
#ifdef RTK_USE_CUDA
	typedef itk::CudaImage< PixelType, Dimension > ImageType;
#else
	typedef itk::Image< PixelType, Dimension > ImageType;
#endif

typedef  itk::RGBPixel<unsigned char>	PixelType_2D;
#ifdef RTK_USE_CUDA
	typedef itk::CudaImage< PixelType_2D, 2 > ImageType;
#else
	typedef itk::Image<PixelType_2D, 2> ImageType2;
#endif
typedef itk::JPEGImageIO   ImageIOType;
ImageIOType::Pointer jpegIO = ImageIOType::New();

ImageType::Pointer drr1 = [a function get a image]

typedef itk::CastImageFilter <ImageType, ImageType2> ImageCastType;
ImageCastType::Pointer Imagecast = ImageCastType::New();
Imagecast->SetInput(drr1);
Imagecast->Update();
		
jpegIO->SetFileTypeToASCII();
typedef itk::ImageFileWriter<ImageType2> WriterType2;
WriterType2::Pointer writer_jpg = WriterType2::New();
writer_jpg->SetImageIO(jpegIO);
writer_jpg->SetFileName("drr.jpg");
writer_jpg->SetInput(Imagecast->GetOutput());
writer_jpg->Update();



--
View this message in context: http://itk-users.7.n7.nabble.com/why-jpg-image-that-is-converted-from-a-mhd-image-is-so-weird-tp38307.html
Sent from the ITK - Users mailing list archive at Nabble.com.

From tevain at telecom-paristech.fr  Wed Jun  7 08:01:38 2017
From: tevain at telecom-paristech.fr (Timothee Evain)
Date: Wed, 7 Jun 2017 14:01:38 +0200 (CEST)
Subject: [ITK-users] [ITK] why jpg image that is converted from a mhd
 image	is so	weird ?
In-Reply-To: <1496835900201-38307.post@n7.nabble.com>
References: <1496835900201-38307.post@n7.nabble.com>
Message-ID: <1953946665.3804674.1496836898409.JavaMail.zimbra@enst.fr>

Hello,

You can't just "cast" a 3D image into a RGB 2D one. Casting is for type only and cannot be used for dimension, see https://itk.org/Doxygen/html/classitk_1_1CastImageFilter.html
One basic solution would be to initialize an ImageType2D image, then parse the "3D" image along spatial dimensions, filling the rgb pixel of the second image with the values along the color dimension.

HTH,

Tim

----- Mail original -----
De: "XieYi" <xieyi4650 at 126.com>
?: insight-users at itk.org
Envoy?: Mercredi 7 Juin 2017 13:45:00
Objet: [ITK] [ITK-users] why jpg image that is converted from a mhd image	is so	weird ?

the mhd image in ParaView software is like this:
<http://itk-users.7.n7.nabble.com/file/n38307/gt1.png> 
after being converted to jpg image, it is like this 
<http://itk-users.7.n7.nabble.com/file/n38307/drr.jpg> 

here is my converting code:

typedef float PixelType;
const unsigned int Dimension = 3;
typedef itk::Matrix<double, 3, 3> MatrixType;
#ifdef RTK_USE_CUDA
	typedef itk::CudaImage< PixelType, Dimension > ImageType;
#else
	typedef itk::Image< PixelType, Dimension > ImageType;
#endif

typedef  itk::RGBPixel<unsigned char>	PixelType_2D;
#ifdef RTK_USE_CUDA
	typedef itk::CudaImage< PixelType_2D, 2 > ImageType;
#else
	typedef itk::Image<PixelType_2D, 2> ImageType2;
#endif
typedef itk::JPEGImageIO   ImageIOType;
ImageIOType::Pointer jpegIO = ImageIOType::New();

ImageType::Pointer drr1 = [a function get a image]

typedef itk::CastImageFilter <ImageType, ImageType2> ImageCastType;
ImageCastType::Pointer Imagecast = ImageCastType::New();
Imagecast->SetInput(drr1);
Imagecast->Update();
		
jpegIO->SetFileTypeToASCII();
typedef itk::ImageFileWriter<ImageType2> WriterType2;
WriterType2::Pointer writer_jpg = WriterType2::New();
writer_jpg->SetImageIO(jpegIO);
writer_jpg->SetFileName("drr.jpg");
writer_jpg->SetInput(Imagecast->GetOutput());
writer_jpg->Update();



--
View this message in context: http://itk-users.7.n7.nabble.com/why-jpg-image-that-is-converted-from-a-mhd-image-is-so-weird-tp38307.html
Sent from the ITK - Users mailing list archive at Nabble.com.
_____________________________________
Powered by www.kitware.com

Visit other Kitware open-source projects at
http://www.kitware.com/opensource/opensource.html

Kitware offers ITK Training Courses, for more information visit:
http://www.kitware.com/products/protraining.php

Please keep messages on-topic and check the ITK FAQ at:
http://www.itk.org/Wiki/ITK_FAQ

Follow this link to subscribe/unsubscribe:
http://public.kitware.com/mailman/listinfo/insight-users
_______________________________________________
Community mailing list
Community at itk.org
http://public.kitware.com/mailman/listinfo/community

From xieyi4650 at 126.com  Wed Jun  7 08:57:18 2017
From: xieyi4650 at 126.com (XieYi)
Date: Wed, 7 Jun 2017 05:57:18 -0700 (MST)
Subject: [ITK-users] [ITK] why jpg image that is converted from a mhd
 image	is so	weird ?
In-Reply-To: <1953946665.3804674.1496836898409.JavaMail.zimbra@enst.fr>
References: <1496835900201-38307.post@n7.nabble.com>
 <1953946665.3804674.1496836898409.JavaMail.zimbra@enst.fr>
Message-ID: <1496840238850-38309.post@n7.nabble.com>

Thank you very much Tim
There is one point not clear in my topic. The point is that the dimension of
image is 3, but infact it is a slice, i.e. it is a 2D image but store in a
3D image type. its size is 512x512x1

there are two strange things:
1, some ImageType can be cast into a 2D jpg image, and have no accident.
2, when I define the density ImageType as 
typedef  itk::RGBPixel<unsigned short>	PixelType_2D;
typedef itk::CudaImage< PixelType_2D, 2 > ImageType2;
typedef itk::PNGImageIO   ImageIOType;
the xxxxx.png look like normal.



--
View this message in context: http://itk-users.7.n7.nabble.com/why-jpg-image-that-is-converted-from-a-mhd-image-is-so-weird-tp38307p38309.html
Sent from the ITK - Users mailing list archive at Nabble.com.

From tevain at telecom-paristech.fr  Wed Jun  7 09:18:06 2017
From: tevain at telecom-paristech.fr (Timothee Evain)
Date: Wed, 7 Jun 2017 15:18:06 +0200 (CEST)
Subject: [ITK-users] [ITK] why jpg image that is converted from a mhd
 image	is so	weird ?
In-Reply-To: <1496840238850-38309.post@n7.nabble.com>
References: <1496835900201-38307.post@n7.nabble.com>
 <1953946665.3804674.1496836898409.JavaMail.zimbra@enst.fr>
 <1496840238850-38309.post@n7.nabble.com>
Message-ID: <1512850014.3888704.1496841486846.JavaMail.zimbra@enst.fr>

Ok, I don't see the advantage of storing a slice as a 3D image since it confuses the code quite a bit, but I guess you have some good reasons.
Same thing for the cast, even if it works, that is really not a standard way of doing it, and could be tricky in the long term.

About the png being normal: Jpeg is a compressed format with loss, that could impact the aspect. But if the image appears normal it is probably because you switched to unsigned short instead of unsigned char, and your original image intensity range overflowed the char one, giving false values.

HTH,

Tim

----- Mail original -----
De: "XieYi" <xieyi4650 at 126.com>
?: insight-users at itk.org
Envoy?: Mercredi 7 Juin 2017 14:57:18
Objet: Re: [ITK] [ITK-users] why jpg image that is converted from a mhd image	is so	weird ?

Thank you very much Tim
There is one point not clear in my topic. The point is that the dimension of
image is 3, but infact it is a slice, i.e. it is a 2D image but store in a
3D image type. its size is 512x512x1

there are two strange things:
1, some ImageType can be cast into a 2D jpg image, and have no accident.
2, when I define the density ImageType as 
typedef  itk::RGBPixel<unsigned short>	PixelType_2D;
typedef itk::CudaImage< PixelType_2D, 2 > ImageType2;
typedef itk::PNGImageIO   ImageIOType;
the xxxxx.png look like normal.



--
View this message in context: http://itk-users.7.n7.nabble.com/why-jpg-image-that-is-converted-from-a-mhd-image-is-so-weird-tp38307p38309.html
Sent from the ITK - Users mailing list archive at Nabble.com.
_____________________________________
Powered by www.kitware.com

Visit other Kitware open-source projects at
http://www.kitware.com/opensource/opensource.html

Kitware offers ITK Training Courses, for more information visit:
http://www.kitware.com/products/protraining.php

Please keep messages on-topic and check the ITK FAQ at:
http://www.itk.org/Wiki/ITK_FAQ

Follow this link to subscribe/unsubscribe:
http://public.kitware.com/mailman/listinfo/insight-users
_______________________________________________
Community mailing list
Community at itk.org
http://public.kitware.com/mailman/listinfo/community

From dzenanz at gmail.com  Wed Jun  7 09:34:38 2017
From: dzenanz at gmail.com (=?UTF-8?B?RMW+ZW5hbiBadWtpxIc=?=)
Date: Wed, 7 Jun 2017 09:34:38 -0400
Subject: [ITK-users] MultiThreading, ImageRegionIterator crash
In-Reply-To: <13d4dc31-8fb8-40c1-ccd8-abe4e45555ef@univ-rennes1.fr>
References: <13d4dc31-8fb8-40c1-ccd8-abe4e45555ef@univ-rennes1.fr>
Message-ID: <CAPf2UMTfPRJQ2Yxbj4C7N0nmhdU1ivqp0AM9xzseRNrDBnkLCA@mail.gmail.com>

Hi Nicolas,

ThreadedComputation should be called ThreadedGenerateData, otherwise the
code looks OK. If you overrode AllocateOutputs(), then you might not have
allocated the output (assuming index is wrong for imgIt). Can you provide a
runnable example <http://sscce.org/>?

Regards,
D?enan Zuki?, PhD, Senior R&D Engineer, Kitware (Carrboro, N.C.)

On Wed, Jun 7, 2017 at 5:46 AM, Nicolas Courtial <
nicolas.courtial at univ-rennes1.fr> wrote:

> Hello everyone,
>
> I'm quite new in ITK world, and I'm currently doing few experiences in
> order to learn its logic.
>
> After few easy exercices, I'm now at a step I want to multithread a method.
> As I did in the past, I've been reading the ITK classes to get
> "inspiration", and e- mails from here in case of troubles.
>
> I'm facing an issue at the moment, and I can't figure why, and how to
> solve it.
>
> My filter works with
>
>    - One 3D InputImage (of any pixel type)
>    - Two "tool" 3D images, respectively of float and unsigned char pixel
>    types
>
> From what I read, I've understood there are two main ways of
> multithreading:
>
>    - The old fashioned one using BeforeThreadedGenerateData/
>    ThreadedGenerateData/AfterThreadedGenerateData
>    - the one using itk::DomainThreader member.
>
> As I'm a bit old school, I used the first option.
> My problem remains here: (I changed my variables' name to make it clearer)
>
> ThreadedComputation(const OutputImageRegionType &outputRegionForThread,
> ThreadIdType threadId) {
>         itk::ProgressReporter progress(this, threadId,
> outputRegionForThread.GetNumberOfPixels());
>         typename TOutputImage::Pointer image = this->GetOutput(0);
>
>         itk::ImageRegionIterator< TOutputImage > imgIt(image,
> outputRegionForThread);
>         itk::ImageRegionIterator< FloatImageType> floatIt (m_MyFloatImage,
> outputRegionForThread);
>     ....
>
> When creating the floatIt iterator, I have a crash. Using a try catch
> block, the issue is due to out of bound region.
> Everything is correct, but the index, for which it's completly crazy
> ([156245468,0,156245468] or something approching).
>
> I've tried different options to solve this, but rather than doing
> witchcraft and at some point getting something working, I'd prefer to
> improve my understanding thanks to your expertise.
>
> Thanks all,
>
> Nicolas Courtial
>
>
>
>
>
> _____________________________________
> Powered by www.kitware.com
>
> Visit other Kitware open-source projects at
> http://www.kitware.com/opensource/opensource.html
>
> Kitware offers ITK Training Courses, for more information visit:
> http://www.kitware.com/products/protraining.php
>
> Please keep messages on-topic and check the ITK FAQ at:
> http://www.itk.org/Wiki/ITK_FAQ
>
> Follow this link to subscribe/unsubscribe:
> http://public.kitware.com/mailman/listinfo/insight-users
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://public.kitware.com/pipermail/insight-users/attachments/20170607/f01f896a/attachment.html>

From julien.jomier at kitware.com  Fri Jun  9 02:16:21 2017
From: julien.jomier at kitware.com (Julien Jomier)
Date: Fri, 9 Jun 2017 08:16:21 +0200
Subject: [ITK-users] [ANN] CMake Training Course - October 9
Message-ID: <2d50072b-a62a-a58a-19a2-dd2747a38b39@kitware.com>

Kitware will be holding a CMake training course on October 9, 2017 in 
Lyon, France. This one-day course will cover CMake, CTest, CPack and CDash.

Please visit our website for more information and registration details:

     https://training.kitware.fr/browse/153

Note that the course will be taught in English. If you have any
questions, please contact us at training at kitware.fr or email me directly.

We are looking forward to seeing you in Lyon,
Julien
-- 
Kitware SAS
26 rue Louis Gu?rin
69100 Villeurbanne, France
http://www.kitware.eu

From sidharta.gupta93 at gmail.com  Fri Jun  9 05:43:06 2017
From: sidharta.gupta93 at gmail.com (sidharta)
Date: Fri, 9 Jun 2017 02:43:06 -0700 (MST)
Subject: [ITK-users] Set different intensity values along a Spatial Object
Message-ID: <1497001386137-38313.post@n7.nabble.com>

Dear all,

I am trying to create a blank image with a Spatial Object in it. What I want
is to set different intensity values along a mask. Is this possible or do I
have to group multiple spatial objects together?



--
View this message in context: http://itk-users.7.n7.nabble.com/Set-different-intensity-values-along-a-Spatial-Object-tp38313.html
Sent from the ITK - Users mailing list archive at Nabble.com.

From coyarzunlaura at googlemail.com  Mon Jun 12 12:04:14 2017
From: coyarzunlaura at googlemail.com (Cristina Oyarzun)
Date: Mon, 12 Jun 2017 18:04:14 +0200
Subject: [ITK-users] Deadline extended!! MICCAI CLIP 2017 Workshop on
 Clinical Image-based Procedures: Translational Research in Medical Imaging
Message-ID: <CANuPjs0w5kiisUkWGRKrPC2kf8H9bUdi+Bjr69UyAU4Pw9Akgw@mail.gmail.com>

CALL FOR PAPERS
MICCAI 2017 Workshop on
Clinical Image-based Procedures: Translational Research in Medical Imaging


September 17, 2017
Quebec City, Canada

Website:http://miccai-clip.org/
==============================
==========================================

SCOPE

The outstanding proliferation of medical image applications has created a
need for greater study and scrutiny of the clinical application and
validation of such methods. New strategies are essential to ensure a smooth
and effective translation of computational image-based techniques into the
clinic. For these reasons CLIP 2017?s major focus is on translational
research filling the gaps between basic science and clinical applications.
A highlight of the workshop is the subject of strategies for personalized
medicine to enhance diagnosis, treatment and interventions. Authors are
encouraged to submit work centered on specific clinical applications,
including techniques and procedures based on comprehensive clinical image
data. Submissions related to applications already in use and evaluated by
clinical users are particularly encouraged. The event will bring together
world-class specialists to present ways to strengthen links between
computer scientists and engineers, and clinicians.


TOPICS

*Strategies for patient-specific and anatomical modeling to support
planning and interventions

*Clinical studies employing advanced image-guided methods

*Clinical translation and validation of image-guided systems

*Current challenges and emerging techniques in image-based procedures

*Identification of parameters and error analysis in image-based procedures

*Multimodal image integration for modeling, planning and guidance

*Clinical applications in open and minimally invasive procedures




PAPER SUBMISSION

Papers will be limited to ten pages following the MICCAI submission
guidelines. Prospective authors should refer to the Paper Submission
section on the workshop website for details on how to submit papers to be
presented at the workshop.
All submissions will be peer-reviewed by at least 2 members of the program
committee. The selection of the papers will be based on the significance of
results, novelty, technical merit, relevance and clarity of presentation.
Papers will be presented in a day long single track workshop starting with
plenary sessions.
Accepted papers will be published as a proceedings volume in the Springer
Lecture Notes in Computer Science (LNCS) series after the workshop.

WORKSHOP FORMAT

Accepted papers will be presented in a day long single track workshop. The
final program will consist of invited speakers and original papers with
time allocated for discussions. Electronic proceedings will be arranged for
all of the papers presented at the workshop.

IMPORTANT DATES

* June 18, 2017: Paper submission due date
* June 29, 2017: Notification of acceptance
* July 3, 2017: Final camera-ready paper submission deadline

CONTACT

Inquires about the workshop should be sent to the Information Desk (
info at miccai-clip.org).

ORGANIZERS (in alphabetical order)

Klaus Drechsler (Fraunhofer IGD, Germany)
Marius Erdt (Fraunhofer IDM at NTU, Singapore)
Miguel Gonz?lez Ballester (ICREA - Universitat Pompeu Fabra, Spain)
Marius George Linguraru (Children's National Medical Center, USA)
Cristina Oyarzun Laura (Fraunhofer IGD, Germany)
Raj Shekhar (Children's National Medical Center, USA)
Stefan Wesarg (Fraunhofer IGD, Germany)

========================================================================
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://public.kitware.com/pipermail/insight-users/attachments/20170612/5114f6c6/attachment.html>

From marc.boucher88 at gmail.com  Tue Jun 20 12:53:51 2017
From: marc.boucher88 at gmail.com (MAB12)
Date: Tue, 20 Jun 2017 09:53:51 -0700 (MST)
Subject: [ITK-users] ITK MESH
Message-ID: <1497977631780-38315.post@n7.nabble.com>

Hi 

I have a binary mask, (segmentation result) and I convert it to a an
itk::Mesh using BinaryMask3DMeshSource. I write the result into a byu Mesh
after. The outcome is a byu Mesh file but that lost all spatial
configuration and is far away in the spatial coordinate from my ground truth
segmentation. The binary mask before was fine I used it to convert it
manually with itk-SNAP.

Any idea was is the problem or insight into how itk Mesh works?



--
View this message in context: http://itk-users.7.n7.nabble.com/ITK-MESH-tp38315.html
Sent from the ITK - Users mailing list archive at Nabble.com.

From matt.mccormick at kitware.com  Tue Jun 20 13:12:19 2017
From: matt.mccormick at kitware.com (Matt McCormick)
Date: Tue, 20 Jun 2017 13:12:19 -0400
Subject: [ITK-users] ITK MESH
In-Reply-To: <1497977631780-38315.post@n7.nabble.com>
References: <1497977631780-38315.post@n7.nabble.com>
Message-ID: <CALzTN-QmHwCz31=0hj4JLBh5p3wOYUrGqp+GPV=sCw_1Ye0UWg@mail.gmail.com>

Hi,

Points in the itk::Mesh are in physical coordinates. So, it is important
that the metadata such as the Image Spacing and Origin are preserved, etc.
For more information see the Mesh section of the ITK Software Guide [1] and
the Image section [2].

Hope this helps,
Matt

[1]
https://itk.org/ITKSoftwareGuide/html/Book1/ITKSoftwareGuide-Book1ch4.html#x38-620004.3

[2]
https://itk.org/ITKSoftwareGuide/html/Book1/ITKSoftwareGuide-Book1ch4.html#x38-470004.1

On Tue, Jun 20, 2017 at 12:53 PM, MAB12 <marc.boucher88 at gmail.com> wrote:

> Hi
>
> I have a binary mask, (segmentation result) and I convert it to a an
> itk::Mesh using BinaryMask3DMeshSource. I write the result into a byu Mesh
> after. The outcome is a byu Mesh file but that lost all spatial
> configuration and is far away in the spatial coordinate from my ground
> truth
> segmentation. The binary mask before was fine I used it to convert it
> manually with itk-SNAP.
>
> Any idea was is the problem or insight into how itk Mesh works?
>
>
>
> --
> View this message in context: http://itk-users.7.n7.nabble.
> com/ITK-MESH-tp38315.html
> Sent from the ITK - Users mailing list archive at Nabble.com.
> _____________________________________
> Powered by www.kitware.com
>
> Visit other Kitware open-source projects at
> http://www.kitware.com/opensource/opensource.html
>
> Kitware offers ITK Training Courses, for more information visit:
> http://www.kitware.com/products/protraining.php
>
> Please keep messages on-topic and check the ITK FAQ at:
> http://www.itk.org/Wiki/ITK_FAQ
>
> Follow this link to subscribe/unsubscribe:
> http://public.kitware.com/mailman/listinfo/insight-users
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://public.kitware.com/pipermail/insight-users/attachments/20170620/85bd234e/attachment.html>

From marc.boucher88 at gmail.com  Tue Jun 20 14:44:09 2017
From: marc.boucher88 at gmail.com (MAB12)
Date: Tue, 20 Jun 2017 11:44:09 -0700 (MST)
Subject: [ITK-users] ITK MESH
In-Reply-To: <CALzTN-QmHwCz31=0hj4JLBh5p3wOYUrGqp+GPV=sCw_1Ye0UWg@mail.gmail.com>
References: <1497977631780-38315.post@n7.nabble.com>
 <CALzTN-QmHwCz31=0hj4JLBh5p3wOYUrGqp+GPV=sCw_1Ye0UWg@mail.gmail.com>
Message-ID: <1497984249177-38317.post@n7.nabble.com>

Hi

Thank for response. Since I simply use the itk::BinaryMask3DMeshSource
filter to convert to a mesh and I don't see parameters to set the spatial
parameters I assumed it should be done automatically... 

I write the mesh into a byu format, is it possible that byu format is not
well handle in itk? I saw a post saying that only vtk handle byu file...



--
View this message in context: http://itk-users.7.n7.nabble.com/ITK-MESH-tp38315p38317.html
Sent from the ITK - Users mailing list archive at Nabble.com.

From 438821082 at qq.com  Wed Jun 21 04:44:17 2017
From: 438821082 at qq.com (Tendy Fang)
Date: Wed, 21 Jun 2017 01:44:17 -0700 (MST)
Subject: [ITK-users] vnl_numeric_traits.h :Error C2413,
	C2510& FATAL error C1004
Message-ID: <1498034657374-38318.post@n7.nabble.com>

<http://itk-users.7.n7.nabble.com/file/n38318/error.png> 
I'm reeditting  a series of old MFC codes based on ITK in my lab which was
wrote in 2005 since there is some function that is useful for our lab's
present  work.
I download ITK 1.6.0 (released in January,2004) , Cmake2.4 and VC6.0 to
reappear the compile environment at that time since there are numerous
errors built in VS2010 or using latest ITK package.
In fact I've tried ITK  package from 1.2.0 to 2.0.0 and the results tell
there are least errors( 24 errors) when I use ITK 1.6.0 . But there are the
errors of vnl_numeric_traits.h as referred in topic and they are also shown
in pictures above. Part codes of vnl_numeric_traits.h are shown below.
<http://itk-users.7.n7.nabble.com/file/n38318/primitive_codes.png> 
Has anyone faced the errors like this before ?
I need your help.

Best regards 
Tendy




--
View this message in context: http://itk-users.7.n7.nabble.com/vnl-numeric-traits-h-Error-C2413-C2510-FATAL-error-C1004-tp38318.html
Sent from the ITK - Users mailing list archive at Nabble.com.

From thanosxania at gmail.com  Fri Jun 23 05:31:13 2017
From: thanosxania at gmail.com (Thanos)
Date: Fri, 23 Jun 2017 02:31:13 -0700 (MST)
Subject: [ITK-users] Conductance parameter on CurvatureAnisotropicDiffusion
	Filtering
Message-ID: <1498210273594-38319.post@n7.nabble.com>

Hello everyone,

I am using the algorithm for Curvature Anisotropic Diffusion where it uses
the algorithm from Whitaker MCDE. As it is also mentioned on the User's
guide the conductance modified curvature term is the divergence of the
normalized gradient. (I also had a look on the original paper) So, as far as
I understand the conductance, which is the curvature of the level set, is
defined by the level set function and therefore the image. Then why do we
have to set the value of the parameter in order to run the example? 
Please forgive me if I understood something wrong. 
Looking forward for your answers!

Best regards,
Thanos



--
View this message in context: http://itk-users.7.n7.nabble.com/Conductance-parameter-on-CurvatureAnisotropicDiffusion-Filtering-tp38319.html
Sent from the ITK - Users mailing list archive at Nabble.com.

From 787aditi at gmail.com  Sat Jun 24 10:31:12 2017
From: 787aditi at gmail.com (mojo_jojo)
Date: Sat, 24 Jun 2017 07:31:12 -0700 (MST)
Subject: [ITK-users] CUDA 7.5 compatibility with ITK 4.11.0
Message-ID: <1498314672496-7590021.post@n2.nabble.com>

Hello,

I am trying to optimize some image processes in ITK, using CUDA. I am using
ITK 4.11.0, built using gcc 4.9, and CUDA version 7.5 for the purpose.
I ended up getting a build error. Also I couldn't find anything much about
direct CUDA version and ITK version compatibility. I built the ITK and CUDA
using same gcc version successfully, and they work well separately.

It will be great if I could get some help with this.

Thanks.




--
View this message in context: http://itk-insight-users.2283740.n2.nabble.com/CUDA-7-5-compatibility-with-ITK-4-11-0-tp7590021.html
Sent from the ITK Insight Users mailing list archive at Nabble.com.

From andx_roo at live.com  Mon Jun 26 12:39:02 2017
From: andx_roo at live.com (Andaharoo)
Date: Mon, 26 Jun 2017 09:39:02 -0700 (MST)
Subject: [ITK-users] Recentering Output of fast marching
Message-ID: <1498495142874-7590022.post@n2.nabble.com>

I've been using the fast marching filter to segment out a particular piece of
a 3d image and now I would like to recenter this segmented part. Sometimes
the segmented part can be at the edge of the image which makes it hard to
rotate since it will only rotate around the center. I tried using fast
marchings getOutputOrigin but that doesn't do what I had hoped it would do.
If I were to write it would go something along the lines of this with a
binary image:
for every pixel
    if the pixel is 1
        if the pixels x val is greater than maxX
            maxX = the pixels x val
        if the pixels x val is smaller than minX
            minX = the pixels x val
        Do the same with the y and z and mins
Then after getting the extents I coudl just do (minX + maxX) / 2, (minY +
maxY) / 2, (minZ + maxZ) / 2



--
View this message in context: http://itk-insight-users.2283740.n2.nabble.com/Recentering-Output-of-fast-marching-tp7590022.html
Sent from the ITK Insight Users mailing list archive at Nabble.com.

From matt.mccormick at kitware.com  Mon Jun 26 13:03:52 2017
From: matt.mccormick at kitware.com (Matt McCormick)
Date: Mon, 26 Jun 2017 13:03:52 -0400
Subject: [ITK-users] Recentering Output of fast marching
In-Reply-To: <1498495142874-7590022.post@n2.nabble.com>
References: <1498495142874-7590022.post@n2.nabble.com>
Message-ID: <CALzTN-QMZ-wHweR4p5u46Of3oT0e0idQtWaOwp7EO17+Cftp4g@mail.gmail.com>

Hi,

This example shows how to find the bounding box of a binary image:

  https://itk.org/Insight/Doxygen/html/Examples_2SpatialObjects_2BoundingBoxFromImageMaskSpatialObject_8cxx-example.html

Hope this helps,
Matt

On Mon, Jun 26, 2017 at 12:39 PM, Andaharoo <andx_roo at live.com> wrote:
> I've been using the fast marching filter to segment out a particular piece of
> a 3d image and now I would like to recenter this segmented part. Sometimes
> the segmented part can be at the edge of the image which makes it hard to
> rotate since it will only rotate around the center. I tried using fast
> marchings getOutputOrigin but that doesn't do what I had hoped it would do.
> If I were to write it would go something along the lines of this with a
> binary image:
> for every pixel
>     if the pixel is 1
>         if the pixels x val is greater than maxX
>             maxX = the pixels x val
>         if the pixels x val is smaller than minX
>             minX = the pixels x val
>         Do the same with the y and z and mins
> Then after getting the extents I coudl just do (minX + maxX) / 2, (minY +
> maxY) / 2, (minZ + maxZ) / 2
>
>
>
> --
> View this message in context: http://itk-insight-users.2283740.n2.nabble.com/Recentering-Output-of-fast-marching-tp7590022.html
> Sent from the ITK Insight Users mailing list archive at Nabble.com.
> _____________________________________
> Powered by www.kitware.com
>
> Visit other Kitware open-source projects at
> http://www.kitware.com/opensource/opensource.html
>
> Kitware offers ITK Training Courses, for more information visit:
> http://www.kitware.com/products/protraining.php
>
> Please keep messages on-topic and check the ITK FAQ at:
> http://www.itk.org/Wiki/ITK_FAQ
>
> Follow this link to subscribe/unsubscribe:
> http://public.kitware.com/mailman/listinfo/insight-users

From blowekamp at mail.nih.gov  Mon Jun 26 13:06:13 2017
From: blowekamp at mail.nih.gov (Lowekamp, Bradley (NIH/NLM/LHC) [C])
Date: Mon, 26 Jun 2017 17:06:13 +0000
Subject: [ITK-users] Recentering Output of fast marching
In-Reply-To: <1498495142874-7590022.post@n2.nabble.com>
References: <1498495142874-7590022.post@n2.nabble.com>
Message-ID: <251F3CA8-2958-4F1D-9340-55D90492FBD6@mail.nih.gov>

Hello,

Have you looked at the LabelImageStatisticsImageFilter[1]? This should compute what you describe.

The ?GetRegion? methods returns a bounding ImageRegion, for a given label. In your case this would be for the label 1.

Brad

[1]https://itk.org/Doxygen/html/classitk_1_1LabelStatisticsImageFilter.html#aa0de894e901cf64495f5690f77b73efb


On 6/26/17, 12:39 PM, "Andaharoo" <andx_roo at live.com> wrote:

    I've been using the fast marching filter to segment out a particular piece of
    a 3d image and now I would like to recenter this segmented part. Sometimes
    the segmented part can be at the edge of the image which makes it hard to
    rotate since it will only rotate around the center. I tried using fast
    marchings getOutputOrigin but that doesn't do what I had hoped it would do.
    If I were to write it would go something along the lines of this with a
    binary image:
    for every pixel
        if the pixel is 1
            if the pixels x val is greater than maxX
                maxX = the pixels x val
            if the pixels x val is smaller than minX
                minX = the pixels x val
            Do the same with the y and z and mins
    Then after getting the extents I coudl just do (minX + maxX) / 2, (minY +
    maxY) / 2, (minZ + maxZ) / 2
    
    
    
    --
    View this message in context: http://itk-insight-users.2283740.n2.nabble.com/Recentering-Output-of-fast-marching-tp7590022.html
    Sent from the ITK Insight Users mailing list archive at Nabble.com.
    _____________________________________
    Powered by www.kitware.com
    
    Visit other Kitware open-source projects at
    http://www.kitware.com/opensource/opensource.html
    
    Kitware offers ITK Training Courses, for more information visit:
    http://www.kitware.com/products/protraining.php
    
    Please keep messages on-topic and check the ITK FAQ at:
    http://www.itk.org/Wiki/ITK_FAQ
    
    Follow this link to subscribe/unsubscribe:
    http://public.kitware.com/mailman/listinfo/insight-users
    


From matt.mccormick at kitware.com  Mon Jun 26 13:11:03 2017
From: matt.mccormick at kitware.com (Matt McCormick)
Date: Mon, 26 Jun 2017 13:11:03 -0400
Subject: [ITK-users] Conductance parameter on
 CurvatureAnisotropicDiffusion Filtering
In-Reply-To: <1498210273594-38319.post@n7.nabble.com>
References: <1498210273594-38319.post@n7.nabble.com>
Message-ID: <CALzTN-SSx2Nnzaeqyggk4t6jt+tn7fJP9or8s7eBY5=No0aNqA@mail.gmail.com>

Hello Thanos,

The Conductance parameter is a global scalar that controls the
sensitivity to the conductance term in the level set evolution
equation. For more information, see the Doxygen pages:

-  https://itk.org/Doxygen/html/classitk_1_1AnisotropicDiffusionFunction.html

-   https://itk.org/Insight/Doxygen/html/classitk_1_1AnisotropicDiffusionImageFilter.html#a14a5b3acabcd97c07645750bb735e251

- https://itk.org/Insight/Doxygen/html/classitk_1_1CurvatureAnisotropicDiffusionImageFilter.html

Hope this helps,
Matt

On Fri, Jun 23, 2017 at 5:31 AM, Thanos <thanosxania at gmail.com> wrote:
> Hello everyone,
>
> I am using the algorithm for Curvature Anisotropic Diffusion where it uses
> the algorithm from Whitaker MCDE. As it is also mentioned on the User's
> guide the conductance modified curvature term is the divergence of the
> normalized gradient. (I also had a look on the original paper) So, as far as
> I understand the conductance, which is the curvature of the level set, is
> defined by the level set function and therefore the image. Then why do we
> have to set the value of the parameter in order to run the example?
> Please forgive me if I understood something wrong.
> Looking forward for your answers!
>
> Best regards,
> Thanos
>
>
>
> --
> View this message in context: http://itk-users.7.n7.nabble.com/Conductance-parameter-on-CurvatureAnisotropicDiffusion-Filtering-tp38319.html
> Sent from the ITK - Users mailing list archive at Nabble.com.
> _____________________________________
> Powered by www.kitware.com
>
> Visit other Kitware open-source projects at
> http://www.kitware.com/opensource/opensource.html
>
> Kitware offers ITK Training Courses, for more information visit:
> http://www.kitware.com/products/protraining.php
>
> Please keep messages on-topic and check the ITK FAQ at:
> http://www.itk.org/Wiki/ITK_FAQ
>
> Follow this link to subscribe/unsubscribe:
> http://public.kitware.com/mailman/listinfo/insight-users

From matt.mccormick at kitware.com  Mon Jun 26 13:49:02 2017
From: matt.mccormick at kitware.com (Matt McCormick)
Date: Mon, 26 Jun 2017 13:49:02 -0400
Subject: [ITK-users] [ANN] Binary ITK Python Packages now available on PyPI!
Message-ID: <CALzTN-QWasMUyCp5fmnmJYZC1880hB-iUYe54yuy0mgjvnCWKQ@mail.gmail.com>

Hi folks,

Binary Python wheels are now available on PyPI for Linux, MacOS, and
Windows, for Python 2.7 and the recent Python 3.X. These binary wheels
are built to be compatible with Python distributions from Python.org,
system package managers like apt and Homebrew, and Anaconda. When a
binary package is not available for the current platform, an sdist is
provided that will guide a researcher through the steps to build the
packages from source code.

To install ITK from the command line, run:

  python -m pip install --upgrade pip
  python -m pip install itk

The itk metapackage will pull in the subpackages itk-segmentation,
itk-registration, itk-numerics, itk-io, itk-filtering, and itk-core.
These packages can also be installed independently if only a portion
of the toolkit is desired.

Enjoy ITK!

From Gordian.Kabelitz at medma.uni-heidelberg.de  Wed Jun 28 09:51:41 2017
From: Gordian.Kabelitz at medma.uni-heidelberg.de (Kabelitz, Gordian)
Date: Wed, 28 Jun 2017 13:51:41 +0000
Subject: [ITK-users] Writing from an external buffer to VectorImage
Message-ID: <81be8e27dd684f54944a7ff7b0d67c42@exch06.ad.uni-heidelberg.de>

Hello,

i computed a gradient with my own function and as a result a pointer to an image buffer is provided. I know the size, origin and spacing of the gradient component image.
I want to copy the gradient image into an itk::VectorImage with the components for the x,y,z gradients.

The way I copied the image to the GPU is that I retrieved the buffer pointer from my input image and use the pointer to copy the image data to the GPU.
I used the way proposed in [1]. The computeGradientImage method is listed at the end of this mail.

[...]
// get float pointer to image data
ImageType::Pointer image = reader->GetOutput();
Image->Update();

float* data = image.GetBufferPointer();
// copy image data to GPU texture memory (this works)
gpu_dev->setVoxels(dimension, voxelSize, data); 
[...]
computeGradientImage<<<n,m>>> (dev_gradientImage, dimension);

// copy resulting gradientImage to host variable
float4* host_gradientImage;
cudaMemcpy(host_gradient, dev_gradientImage, numberOfVoxels*sizeof(float4));

--> Pseudo Code <--
// Now I want to reverse the copy process. I have a float4 image and want to copy this into a itk::VectorImage with VariableVectorLength of 3 (skipping the magnitude value).
[...] -> size, spacing, origin, region definition
Itk::VectorImageType vecImage = VectorImageType::New();
vecImage->setRegion(region);
vecImage ->SetVectorLength(3);
vecImage->Allocate();

// copy image buffer to vecImage, component by component 
auto vecBuffer = vecImage->getBufferPointer();
auto j = 0;
for (i=0; i<totalVoxel; ++i)
{
	vecbuffer[j] = host_gradient[i].x; j++;
	vecbuffer[j] = host_gradient[i].y; j++;
	vecbuffer[j] = host_gradient[i].z; j++;
}

// save vecImage as nrrd image
[...]

I haven't found a way to achieve my idea. 
Are there any suggestions or examples?
As far I can see I cannot use the itk::ImportImageFilter.

Thank you for any suggestions.
With kind regards,
Gordian

[1]: https://itk.org/CourseWare/Training/GettingStarted-V.pdf

void computeGradientImage(float4* gradientImage, int* dimension)
{
	// every thread computes the float4 voxel with theta,phi,magnitude from gradient image
	int idx = blockIdx.x * blockDim.x + threadIdx.x;
	int idy = blockIdx.y * blockDim.y + threadIdx.y;
	int idz = blockIdx.z * blockDim.z + threadIdx.z;

	if (idx < dimension[0] && idy < dimension[1] && idz < dimension[2])
	{
		// define sobel filter for each direction
		[...]

		// run sobel on image in texture memory for each direction and put result into a float4 image
		gradientImage[idx + dimension[0] * (idy + idz * dimension[1])] = make_float4(sobelX, sobelY, sobelZ, magn);
	}
}



From dzenanz at gmail.com  Wed Jun 28 11:17:16 2017
From: dzenanz at gmail.com (=?UTF-8?B?RMW+ZW5hbiBadWtpxIc=?=)
Date: Wed, 28 Jun 2017 11:17:16 -0400
Subject: [ITK-users] Writing from an external buffer to VectorImage
In-Reply-To: <81be8e27dd684f54944a7ff7b0d67c42@exch06.ad.uni-heidelberg.de>
References: <81be8e27dd684f54944a7ff7b0d67c42@exch06.ad.uni-heidelberg.de>
Message-ID: <CAPf2UMTPZQnmx+xN94w9U2-qOr_3hsJfr9VmPOcDBofCNa=THg@mail.gmail.com>

Hi Gordian,

this approach looks like it should work. What is wrong with it?

Regards,
D?enan Zuki?, PhD, Senior R&D Engineer, Kitware (Carrboro, N.C.)

On Wed, Jun 28, 2017 at 9:51 AM, Kabelitz, Gordian <
Gordian.Kabelitz at medma.uni-heidelberg.de> wrote:

> Hello,
>
> i computed a gradient with my own function and as a result a pointer to an
> image buffer is provided. I know the size, origin and spacing of the
> gradient component image.
> I want to copy the gradient image into an itk::VectorImage with the
> components for the x,y,z gradients.
>
> The way I copied the image to the GPU is that I retrieved the buffer
> pointer from my input image and use the pointer to copy the image data to
> the GPU.
> I used the way proposed in [1]. The computeGradientImage method is listed
> at the end of this mail.
>
> [...]
> // get float pointer to image data
> ImageType::Pointer image = reader->GetOutput();
> Image->Update();
>
> float* data = image.GetBufferPointer();
> // copy image data to GPU texture memory (this works)
> gpu_dev->setVoxels(dimension, voxelSize, data);
> [...]
> computeGradientImage<<<n,m>>> (dev_gradientImage, dimension);
>
> // copy resulting gradientImage to host variable
> float4* host_gradientImage;
> cudaMemcpy(host_gradient, dev_gradientImage, numberOfVoxels*sizeof(float4))
> ;
>
> --> Pseudo Code <--
> // Now I want to reverse the copy process. I have a float4 image and want
> to copy this into a itk::VectorImage with VariableVectorLength of 3
> (skipping the magnitude value).
> [...] -> size, spacing, origin, region definition
> Itk::VectorImageType vecImage = VectorImageType::New();
> vecImage->setRegion(region);
> vecImage ->SetVectorLength(3);
> vecImage->Allocate();
>
> // copy image buffer to vecImage, component by component
> auto vecBuffer = vecImage->getBufferPointer();
> auto j = 0;
> for (i=0; i<totalVoxel; ++i)
> {
>         vecbuffer[j] = host_gradient[i].x; j++;
>         vecbuffer[j] = host_gradient[i].y; j++;
>         vecbuffer[j] = host_gradient[i].z; j++;
> }
>
> // save vecImage as nrrd image
> [...]
>
> I haven't found a way to achieve my idea.
> Are there any suggestions or examples?
> As far I can see I cannot use the itk::ImportImageFilter.
>
> Thank you for any suggestions.
> With kind regards,
> Gordian
>
> [1]: https://itk.org/CourseWare/Training/GettingStarted-V.pdf
>
> void computeGradientImage(float4* gradientImage, int* dimension)
> {
>         // every thread computes the float4 voxel with theta,phi,magnitude
> from gradient image
>         int idx = blockIdx.x * blockDim.x + threadIdx.x;
>         int idy = blockIdx.y * blockDim.y + threadIdx.y;
>         int idz = blockIdx.z * blockDim.z + threadIdx.z;
>
>         if (idx < dimension[0] && idy < dimension[1] && idz < dimension[2])
>         {
>                 // define sobel filter for each direction
>                 [...]
>
>                 // run sobel on image in texture memory for each direction
> and put result into a float4 image
>                 gradientImage[idx + dimension[0] * (idy + idz *
> dimension[1])] = make_float4(sobelX, sobelY, sobelZ, magn);
>         }
> }
>
>
> _____________________________________
> Powered by www.kitware.com
>
> Visit other Kitware open-source projects at
> http://www.kitware.com/opensource/opensource.html
>
> Kitware offers ITK Training Courses, for more information visit:
> http://www.kitware.com/products/protraining.php
>
> Please keep messages on-topic and check the ITK FAQ at:
> http://www.itk.org/Wiki/ITK_FAQ
>
> Follow this link to subscribe/unsubscribe:
> http://public.kitware.com/mailman/listinfo/insight-users
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://public.kitware.com/pipermail/insight-users/attachments/20170628/749c066f/attachment.html>

From matt.mccormick at kitware.com  Wed Jun 28 12:25:46 2017
From: matt.mccormick at kitware.com (Matt McCormick)
Date: Wed, 28 Jun 2017 12:25:46 -0400
Subject: [ITK-users] Writing from an external buffer to VectorImage
In-Reply-To: <81be8e27dd684f54944a7ff7b0d67c42@exch06.ad.uni-heidelberg.de>
References: <81be8e27dd684f54944a7ff7b0d67c42@exch06.ad.uni-heidelberg.de>
Message-ID: <CALzTN-SKu+L=mYzdNogQs0qUQ=jgxhROk61NSZSEAPVCN8_T_w@mail.gmail.com>

Hi Gordian,

Examining or using the code in ITKGPUCommon may be helpful. The
methods transfer data from CPU to GPU memory and back.

  https://github.com/InsightSoftwareConsortium/ITK/tree/master/Modules/Core/GPUCommon

Hope this helps,
Matt

On Wed, Jun 28, 2017 at 9:51 AM, Kabelitz, Gordian
<Gordian.Kabelitz at medma.uni-heidelberg.de> wrote:
> Hello,
>
> i computed a gradient with my own function and as a result a pointer to an image buffer is provided. I know the size, origin and spacing of the gradient component image.
> I want to copy the gradient image into an itk::VectorImage with the components for the x,y,z gradients.
>
> The way I copied the image to the GPU is that I retrieved the buffer pointer from my input image and use the pointer to copy the image data to the GPU.
> I used the way proposed in [1]. The computeGradientImage method is listed at the end of this mail.
>
> [...]
> // get float pointer to image data
> ImageType::Pointer image = reader->GetOutput();
> Image->Update();
>
> float* data = image.GetBufferPointer();
> // copy image data to GPU texture memory (this works)
> gpu_dev->setVoxels(dimension, voxelSize, data);
> [...]
> computeGradientImage<<<n,m>>> (dev_gradientImage, dimension);
>
> // copy resulting gradientImage to host variable
> float4* host_gradientImage;
> cudaMemcpy(host_gradient, dev_gradientImage, numberOfVoxels*sizeof(float4));
>
> --> Pseudo Code <--
> // Now I want to reverse the copy process. I have a float4 image and want to copy this into a itk::VectorImage with VariableVectorLength of 3 (skipping the magnitude value).
> [...] -> size, spacing, origin, region definition
> Itk::VectorImageType vecImage = VectorImageType::New();
> vecImage->setRegion(region);
> vecImage ->SetVectorLength(3);
> vecImage->Allocate();
>
> // copy image buffer to vecImage, component by component
> auto vecBuffer = vecImage->getBufferPointer();
> auto j = 0;
> for (i=0; i<totalVoxel; ++i)
> {
>         vecbuffer[j] = host_gradient[i].x; j++;
>         vecbuffer[j] = host_gradient[i].y; j++;
>         vecbuffer[j] = host_gradient[i].z; j++;
> }
>
> // save vecImage as nrrd image
> [...]
>
> I haven't found a way to achieve my idea.
> Are there any suggestions or examples?
> As far I can see I cannot use the itk::ImportImageFilter.
>
> Thank you for any suggestions.
> With kind regards,
> Gordian
>
> [1]: https://itk.org/CourseWare/Training/GettingStarted-V.pdf
>
> void computeGradientImage(float4* gradientImage, int* dimension)
> {
>         // every thread computes the float4 voxel with theta,phi,magnitude from gradient image
>         int idx = blockIdx.x * blockDim.x + threadIdx.x;
>         int idy = blockIdx.y * blockDim.y + threadIdx.y;
>         int idz = blockIdx.z * blockDim.z + threadIdx.z;
>
>         if (idx < dimension[0] && idy < dimension[1] && idz < dimension[2])
>         {
>                 // define sobel filter for each direction
>                 [...]
>
>                 // run sobel on image in texture memory for each direction and put result into a float4 image
>                 gradientImage[idx + dimension[0] * (idy + idz * dimension[1])] = make_float4(sobelX, sobelY, sobelZ, magn);
>         }
> }
>
>
> _____________________________________
> Powered by www.kitware.com
>
> Visit other Kitware open-source projects at
> http://www.kitware.com/opensource/opensource.html
>
> Kitware offers ITK Training Courses, for more information visit:
> http://www.kitware.com/products/protraining.php
>
> Please keep messages on-topic and check the ITK FAQ at:
> http://www.itk.org/Wiki/ITK_FAQ
>
> Follow this link to subscribe/unsubscribe:
> http://public.kitware.com/mailman/listinfo/insight-users

From aharr8 at uwo.ca  Wed Jun 28 15:14:51 2017
From: aharr8 at uwo.ca (Andrew Harris)
Date: Wed, 28 Jun 2017 15:14:51 -0400
Subject: [ITK-users] [ITK] applying a transform to an ITK Point object
 results in it moving the opposite direction from the image
Message-ID: <CAJ0LxQ+6Vu14Lb3bPU12trnfc7UFn+EZhSzgdqxu6gEscyQByA@mail.gmail.com>

Hi there,
I have been trying for a while to get this working: I want to be able to
select corresponding points in a fixed and moving image, and determine how
well the moving image is transformed to overlay the fixed image by using
target registration error.  The problem is, using the same transform I
applied to a moving image that translated it to the left, the point
selected in the moving image gets translated to the right for example.

--

AH


Andrew Harris, Honours BSc (Medical Physics)

PhD (CAMPEP) & MClSc Candidate

-----------------------------------------------------------------------------------------------

*This email and any attachments thereto may contain private,
confidential, and privileged materials for the sole use of the intended
recipient. Any reviewing, copying, or distribution of this email (or any
attachments thereto) by other than the intended recipient is strictly
prohibited. If you are not the intended recipient, please contact the
sender immediately and permanently destroy this email and any attachments
thereto.*
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://public.kitware.com/pipermail/insight-users/attachments/20170628/85bde6b1/attachment.html>

From zivrafael.yaniv at nih.gov  Wed Jun 28 16:50:04 2017
From: zivrafael.yaniv at nih.gov (Yaniv, Ziv Rafael (NIH/NLM/LHC) [C])
Date: Wed, 28 Jun 2017 20:50:04 +0000
Subject: [ITK-users] [ITK] applying a transform to an ITK Point object
 results in it moving the opposite direction from the image
In-Reply-To: <CAJ0LxQ+6Vu14Lb3bPU12trnfc7UFn+EZhSzgdqxu6gEscyQByA@mail.gmail.com>
References: <CAJ0LxQ+6Vu14Lb3bPU12trnfc7UFn+EZhSzgdqxu6gEscyQByA@mail.gmail.com>
Message-ID: <6ABFBEEB-EBE8-478C-BEEB-747A5373FBE9@mail.nih.gov>

Hello Andrew,

In ITK the result of a registration maps points from the fixed image coordinate system to the moving coordinate system, so T(p_f) = p_m and the TRE is || T(p_f) ? p_m||. I suspect you just need to use the inverse transform.

You may be interested in this SimpleITK notebook (http://insightsoftwareconsortium.github.io/SimpleITK-Notebooks/Python_html/67_Registration_Semiautomatic_Homework.html) which has a linked cursor GUI (gui. RegistrationPointDataAquisition). The source code for the UI is here: https://github.com/InsightSoftwareConsortium/SimpleITK-Notebooks/blob/master/Python/gui.py .

      hope this helps
             Ziv




From: Andrew Harris <aharr8 at uwo.ca>
Date: Wednesday, June 28, 2017 at 3:14 PM
To: Insight-users <insight-users at itk.org>
Subject: [ITK-users] [ITK] applying a transform to an ITK Point object results in it moving the opposite direction from the image

Hi there,
I have been trying for a while to get this working: I want to be able to select corresponding points in a fixed and moving image, and determine how well the moving image is transformed to overlay the fixed image by using target registration error.  The problem is, using the same transform I applied to a moving image that translated it to the left, the point selected in the moving image gets translated to the right for example.

--

AH



Andrew Harris, Honours BSc (Medical Physics)

PhD (CAMPEP) & MClSc Candidate

-----------------------------------------------------------------------------------------------

This email and any attachments thereto may contain private, confidential, and privileged materials for the sole use of the intended recipient. Any reviewing, copying, or distribution of this email (or any attachments thereto) by other than the intended recipient is strictly prohibited. If you are not the intended recipient, please contact the sender immediately and permanently destroy this email and any attachments thereto.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://public.kitware.com/pipermail/insight-users/attachments/20170628/b1fc2322/attachment.html>

From aharr8 at uwo.ca  Thu Jun 29 13:21:11 2017
From: aharr8 at uwo.ca (Andrew Harris)
Date: Thu, 29 Jun 2017 13:21:11 -0400
Subject: [ITK-users] [ITK] applying a transform to an ITK Point object
 results in it moving the opposite direction from the image
In-Reply-To: <6ABFBEEB-EBE8-478C-BEEB-747A5373FBE9@mail.nih.gov>
References: <CAJ0LxQ+6Vu14Lb3bPU12trnfc7UFn+EZhSzgdqxu6gEscyQByA@mail.gmail.com>
 <6ABFBEEB-EBE8-478C-BEEB-747A5373FBE9@mail.nih.gov>
Message-ID: <CAJ0LxQLy7tkLUdVfaPHdO=O2cM7NU8SOodiPfY58OLkV_1i8Bw@mail.gmail.com>

Thanks for getting back to me. Using the inverse transform on the point
selected in the moving image works to transform the point within a
reasonable amount to the homologous feature selected in the fixed image
when I use two identical images with a known offset of 100 voxels in each
direction.  However, upon testing identical images with a known rotation
the selected points again fail to line up.  The transform I have been using
is the Rigid3DVersorTransform, and the lines of code I'm using to set the
inverse are:

newTransform->SetCenter(oldTransform->GetCenter());
oldTransform->GetInverse(newTransform);

Any idea why translation would work but rotation causes a problem?

--

AH


Andrew Harris, Honours BSc (Medical Physics)

PhD (CAMPEP) & MClSc Candidate

-----------------------------------------------------------------------------------------------

*This email and any attachments thereto may contain private,
confidential, and privileged materials for the sole use of the intended
recipient. Any reviewing, copying, or distribution of this email (or any
attachments thereto) by other than the intended recipient is strictly
prohibited. If you are not the intended recipient, please contact the
sender immediately and permanently destroy this email and any attachments
thereto.*

On Wed, Jun 28, 2017 at 4:50 PM, Yaniv, Ziv Rafael (NIH/NLM/LHC) [C] <
zivrafael.yaniv at nih.gov> wrote:

> Hello Andrew,
>
>
>
> In ITK the result of a registration maps points from the fixed image
> coordinate system to the moving coordinate system, so T(p_f) = p_m and the
> TRE is || T(p_f) ? p_m||. I suspect you just need to use the inverse
> transform.
>
>
>
> You may be interested in this SimpleITK notebook (http://
> insightsoftwareconsortium.github.io/SimpleITK-Notebooks/
> Python_html/67_Registration_Semiautomatic_Homework.html) which has a
> linked cursor GUI (gui. RegistrationPointDataAquisition). The source code
> for the UI is here: https://github.com/InsightSoftwareConsortium/
> SimpleITK-Notebooks/blob/master/Python/gui.py .
>
>
>
>       hope this helps
>
>              Ziv
>
>
>
>
>
>
>
>
>
> *From: *Andrew Harris <aharr8 at uwo.ca>
> *Date: *Wednesday, June 28, 2017 at 3:14 PM
> *To: *Insight-users <insight-users at itk.org>
> *Subject: *[ITK-users] [ITK] applying a transform to an ITK Point object
> results in it moving the opposite direction from the image
>
>
>
> Hi there,
>
> I have been trying for a while to get this working: I want to be able to
> select corresponding points in a fixed and moving image, and determine how
> well the moving image is transformed to overlay the fixed image by using
> target registration error.  The problem is, using the same transform I
> applied to a moving image that translated it to the left, the point
> selected in the moving image gets translated to the right for example.
>
> --
>
> AH
>
>
>
> Andrew Harris, Honours BSc (Medical Physics)
>
> PhD (CAMPEP) & MClSc Candidate
>
> ------------------------------------------------------------
> -----------------------------------
>
> *This email and any attachments thereto may contain private,
> confidential, and privileged materials for the sole use of the intended
> recipient. Any reviewing, copying, or distribution of this email (or any
> attachments thereto) by other than the intended recipient is strictly
> prohibited. If you are not the intended recipient, please contact the
> sender immediately and permanently destroy this email and any attachments
> thereto.*
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://public.kitware.com/pipermail/insight-users/attachments/20170629/f3a7e0ac/attachment.html>

From zivrafael.yaniv at nih.gov  Thu Jun 29 15:04:59 2017
From: zivrafael.yaniv at nih.gov (Yaniv, Ziv Rafael (NIH/NLM/LHC) [C])
Date: Thu, 29 Jun 2017 19:04:59 +0000
Subject: [ITK-users] [ITK] applying a transform to an ITK Point object
 results in it moving the opposite direction from the image
In-Reply-To: <CAJ0LxQLy7tkLUdVfaPHdO=O2cM7NU8SOodiPfY58OLkV_1i8Bw@mail.gmail.com>
References: <CAJ0LxQ+6Vu14Lb3bPU12trnfc7UFn+EZhSzgdqxu6gEscyQByA@mail.gmail.com>
 <6ABFBEEB-EBE8-478C-BEEB-747A5373FBE9@mail.nih.gov>
 <CAJ0LxQLy7tkLUdVfaPHdO=O2cM7NU8SOodiPfY58OLkV_1i8Bw@mail.gmail.com>
Message-ID: <A9017BA5-836A-4AA0-9CBC-ADEF83A81C84@mail.nih.gov>

The code snippet looks correct. I would advise that you print the transformations to see that you are getting what you expect. The relevant entries, Matrix, Center, Translation, Offset:

Original transform is:

T(x)=A(x?c)+t+c

Where:
A ? matrix
c ? center
t ? translation
t+c ?Ac ? offset

The inverse should have:
A^{-1} ? matrix
c ? center
-A^{-1} t ? translation
c - A^{-1} t - A^{-1} c - offset


        hope this helps
                  Ziv

p.s. When working with ITK always remember that you are dealing with physical space, distances are in mm/km?, volumes in mm^3?. Don?t be tempted to measure things in pixels/voxels.

From: Andrew Harris <aharr8 at uwo.ca>
Date: Thursday, June 29, 2017 at 1:21 PM
To: "Yaniv, Ziv Rafael (NIH/NLM/LHC) [C]" <zivrafael.yaniv at nih.gov>
Cc: Insight-users <insight-users at itk.org>
Subject: Re: [ITK-users] [ITK] applying a transform to an ITK Point object results in it moving the opposite direction from the image

Thanks for getting back to me. Using the inverse transform on the point selected in the moving image works to transform the point within a reasonable amount to the homologous feature selected in the fixed image when I use two identical images with a known offset of 100 voxels in each direction.  However, upon testing identical images with a known rotation the selected points again fail to line up.  The transform I have been using is the Rigid3DVersorTransform, and the lines of code I'm using to set the inverse are:

newTransform->SetCenter(oldTransform->GetCenter());
oldTransform->GetInverse(newTransform);

Any idea why translation would work but rotation causes a problem?


--

AH



Andrew Harris, Honours BSc (Medical Physics)

PhD (CAMPEP) & MClSc Candidate

-----------------------------------------------------------------------------------------------

This email and any attachments thereto may contain private, confidential, and privileged materials for the sole use of the intended recipient. Any reviewing, copying, or distribution of this email (or any attachments thereto) by other than the intended recipient is strictly prohibited. If you are not the intended recipient, please contact the sender immediately and permanently destroy this email and any attachments thereto.

On Wed, Jun 28, 2017 at 4:50 PM, Yaniv, Ziv Rafael (NIH/NLM/LHC) [C] <zivrafael.yaniv at nih.gov<mailto:zivrafael.yaniv at nih.gov>> wrote:
Hello Andrew,

In ITK the result of a registration maps points from the fixed image coordinate system to the moving coordinate system, so T(p_f) = p_m and the TRE is || T(p_f) ? p_m||. I suspect you just need to use the inverse transform.

You may be interested in this SimpleITK notebook (http://insightsoftwareconsortium.github.io/SimpleITK-Notebooks/Python_html/67_Registration_Semiautomatic_Homework.html) which has a linked cursor GUI (gui. RegistrationPointDataAquisition). The source code for the UI is here: https://github.com/InsightSoftwareConsortium/SimpleITK-Notebooks/blob/master/Python/gui.py .

      hope this helps
             Ziv




From: Andrew Harris <aharr8 at uwo.ca<mailto:aharr8 at uwo.ca>>
Date: Wednesday, June 28, 2017 at 3:14 PM
To: Insight-users <insight-users at itk.org<mailto:insight-users at itk.org>>
Subject: [ITK-users] [ITK] applying a transform to an ITK Point object results in it moving the opposite direction from the image

Hi there,
I have been trying for a while to get this working: I want to be able to select corresponding points in a fixed and moving image, and determine how well the moving image is transformed to overlay the fixed image by using target registration error.  The problem is, using the same transform I applied to a moving image that translated it to the left, the point selected in the moving image gets translated to the right for example.

--

AH



Andrew Harris, Honours BSc (Medical Physics)

PhD (CAMPEP) & MClSc Candidate

-----------------------------------------------------------------------------------------------

This email and any attachments thereto may contain private, confidential, and privileged materials for the sole use of the intended recipient. Any reviewing, copying, or distribution of this email (or any attachments thereto) by other than the intended recipient is strictly prohibited. If you are not the intended recipient, please contact the sender immediately and permanently destroy this email and any attachments thereto.

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://public.kitware.com/pipermail/insight-users/attachments/20170629/48ec717d/attachment.html>

From andx_roo at live.com  Thu Jun 29 22:19:36 2017
From: andx_roo at live.com (Andaharoo)
Date: Thu, 29 Jun 2017 19:19:36 -0700 (MST)
Subject: [ITK-users] Problems Using GPU Filters
Message-ID: <1498789176254-7590036.post@n2.nabble.com>

I've been looking to use some of the GPU filters provided by ITK recently.
Namely the GPU anisotropic filter and binary threshold filter. I downloaded
CUDA and ran cmake again with use gpu on flag and it found all my cuda stuff
automatically. Everything appeared to build fine. I then looked up some
implementation details and examples but couldn't really find any. There was
one itk powerpoint from a long while ago that seemed to suggest I'd be able
to just put a gpu filter in the pipeline like any other filter. I liked this
implementation but it didn't work. So right now I have a pipeline that looks
like the following in order to load images with vtk, process with itk, and
then render with vtk.

vtkToItkFilter -> array of ImageToImageFilters all connected ->
itkToVtkFilter

I tried to stick the GPUBinaryThresholdImageFilter in the array like I would
a normal filter connecting it appropriately and calling update but it broke
throwing a read access violation on line 46 of the GPUGenerateData function
in itkGPUUnaryFunctorImageFilter.hxx saying otPtr.m_Pointer was nullptr.

My code goes a little something like this:

typedef itk::Image<float, 3> Image;
typedef itk::GPUBinaryThresholdImageFilter<Image, Image>
GPUBinaryThresholdFilter;
GPUBinaryThresholdFilter::Pointer filter = GPUBinaryThresholdFilter::New();
double* range = pipe->GetOutput()->GetScalarRange();
filter->SetLowerThreshold(filterWidget->getDoubleFromSlider("Lower"));
filter->SetUpperThreshold(filterWidget->getDoubleFromSlider("Upper"));
filter->SetOutsideValue(range[0]);
filter->SetInsideValue(range[1]);
filters.push_back(filter);
if (filters.size() > 0)
	filter->SetInput(filters.back()->GetOutput());
else
	filter->SetInput(vtkToItkLoader->GetOutput());
itkToVtkFilter->SetInput(filters.back()->GetOutput());



--
View this message in context: http://itk-insight-users.2283740.n2.nabble.com/Problems-Using-GPU-Filters-tp7590036.html
Sent from the ITK Insight Users mailing list archive at Nabble.com.

From felix.burk at gmail.com  Fri Jun 30 06:58:40 2017
From: felix.burk at gmail.com (Felix Burk)
Date: Fri, 30 Jun 2017 12:58:40 +0200
Subject: [ITK-users]  Combining several segmenations
Message-ID: <CAE2K_nAB12VgCYRwep0u6z9Rj8wLphKrNBAq9GXUkr78dzYeJQ@mail.gmail.com>

Hello,

I'm using ITKs ScalarChanAndVeseDenseLevelSetImageFilter to segment parts
of a medical image file series. The problem is that the resolution is
pretty low. So far its working well, but I'd like to have more accurate
results.

The images in the file series are similar, but change more after each time
step. Some segmentations work really well but others differ quite a bit
from the desired result.
My idea is to combine segmentations from different time steps, like the
current and previous one. I think this might lead to better results,
because the segmentations should be similar too.
I'm quite new to ITK and image analysis in general, maybe that's why I
couldn't find something useful for this kind of problem.

I already tried to compare them using SquaredDifferenceImageFilter and
SimilarityIndexImageFilter, but I don't know if the results are of any use.
Is there any way to combine segmentations from several time steps to obtain
better results for a single time step?

I implemented the algorithm as a Paraview Plugin, if that matters. I could
provide some Screenshots too if this might help.

Thanks,
Felix
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://public.kitware.com/pipermail/insight-users/attachments/20170630/c79b5259/attachment.html>

From emilianoberonich at gmail.com  Fri Jun 30 07:52:48 2017
From: emilianoberonich at gmail.com (Emiliano Beronich)
Date: Fri, 30 Jun 2017 08:52:48 -0300
Subject: [ITK-users] Problems Using GPU Filters
In-Reply-To: <1498789176254-7590036.post@n2.nabble.com>
References: <1498789176254-7590036.post@n2.nabble.com>
Message-ID: <CAPXOEV3Z1nM5=oa7qr5ip2ME01XvWVRn6Ni-LHnrX+kZRf=EzA@mail.gmail.com>

Hi Andarahoo,

GPUBinaryThresholdImageFilter should be used with GPUImage.
Try defining:
typedef itk::GPUImage<float, 3> Image;

There is a cast in the method GPUUnaryFunctorImageFilter::GenerateData
(ancester of GPUBinaryThresholdImageFilter) which may be the cause of the
null pointer:

  typename GPUOutputImage::Pointer otPtr =  dynamic_cast< GPUOutputImage *
>( this->ProcessObject::GetOutput(0) );


Cheers,
Emiliano



2017-06-29 23:19 GMT-03:00 Andaharoo <andx_roo at live.com>:

> I've been looking to use some of the GPU filters provided by ITK recently.
> Namely the GPU anisotropic filter and binary threshold filter. I downloaded
> CUDA and ran cmake again with use gpu on flag and it found all my cuda
> stuff
> automatically. Everything appeared to build fine. I then looked up some
> implementation details and examples but couldn't really find any. There was
> one itk powerpoint from a long while ago that seemed to suggest I'd be able
> to just put a gpu filter in the pipeline like any other filter. I liked
> this
> implementation but it didn't work. So right now I have a pipeline that
> looks
> like the following in order to load images with vtk, process with itk, and
> then render with vtk.
>
> vtkToItkFilter -> array of ImageToImageFilters all connected ->
> itkToVtkFilter
>
> I tried to stick the GPUBinaryThresholdImageFilter in the array like I
> would
> a normal filter connecting it appropriately and calling update but it broke
> throwing a read access violation on line 46 of the GPUGenerateData function
> in itkGPUUnaryFunctorImageFilter.hxx saying otPtr.m_Pointer was nullptr.
>
> My code goes a little something like this:
>
> typedef itk::Image<float, 3> Image;
> typedef itk::GPUBinaryThresholdImageFilter<Image, Image>
> GPUBinaryThresholdFilter;
> GPUBinaryThresholdFilter::Pointer filter = GPUBinaryThresholdFilter::New(
> );
> double* range = pipe->GetOutput()->GetScalarRange();
> filter->SetLowerThreshold(filterWidget->getDoubleFromSlider("Lower"));
> filter->SetUpperThreshold(filterWidget->getDoubleFromSlider("Upper"));
> filter->SetOutsideValue(range[0]);
> filter->SetInsideValue(range[1]);
> filters.push_back(filter);
> if (filters.size() > 0)
>         filter->SetInput(filters.back()->GetOutput());
> else
>         filter->SetInput(vtkToItkLoader->GetOutput());
> itkToVtkFilter->SetInput(filters.back()->GetOutput());
>
>
>
> --
> View this message in context: http://itk-insight-users.
> 2283740.n2.nabble.com/Problems-Using-GPU-Filters-tp7590036.html
> Sent from the ITK Insight Users mailing list archive at Nabble.com.
> _____________________________________
> Powered by www.kitware.com
>
> Visit other Kitware open-source projects at
> http://www.kitware.com/opensource/opensource.html
>
> Kitware offers ITK Training Courses, for more information visit:
> http://www.kitware.com/products/protraining.php
>
> Please keep messages on-topic and check the ITK FAQ at:
> http://www.itk.org/Wiki/ITK_FAQ
>
> Follow this link to subscribe/unsubscribe:
> http://public.kitware.com/mailman/listinfo/insight-users
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://public.kitware.com/pipermail/insight-users/attachments/20170630/11d83c1a/attachment.html>

From matt.mccormick at kitware.com  Fri Jun 30 17:02:43 2017
From: matt.mccormick at kitware.com (Matt McCormick)
Date: Fri, 30 Jun 2017 17:02:43 -0400
Subject: [ITK-users] Combining several segmenations
In-Reply-To: <CAE2K_nAB12VgCYRwep0u6z9Rj8wLphKrNBAq9GXUkr78dzYeJQ@mail.gmail.com>
References: <CAE2K_nAB12VgCYRwep0u6z9Rj8wLphKrNBAq9GXUkr78dzYeJQ@mail.gmail.com>
Message-ID: <CALzTN-QbSgeP6UkqhnwpQoFCqJG+A9xKhd=6Bxt=mG_jGA4GGQ@mail.gmail.com>

Hello Felix,

Once approach is to use the LabelVotingImageFilter:

  https://itk.org/Doxygen/html/classitk_1_1LabelVotingImageFilter.html

Hope this helps,
Matt

On Fri, Jun 30, 2017 at 6:58 AM, Felix Burk <felix.burk at gmail.com> wrote:
> Hello,
>
> I'm using ITKs ScalarChanAndVeseDenseLevelSetImageFilter to segment parts of
> a medical image file series. The problem is that the resolution is pretty
> low. So far its working well, but I'd like to have more accurate results.
>
> The images in the file series are similar, but change more after each time
> step. Some segmentations work really well but others differ quite a bit from
> the desired result.
> My idea is to combine segmentations from different time steps, like the
> current and previous one. I think this might lead to better results, because
> the segmentations should be similar too.
> I'm quite new to ITK and image analysis in general, maybe that's why I
> couldn't find something useful for this kind of problem.
>
> I already tried to compare them using SquaredDifferenceImageFilter and
> SimilarityIndexImageFilter, but I don't know if the results are of any use.
> Is there any way to combine segmentations from several time steps to obtain
> better results for a single time step?
>
> I implemented the algorithm as a Paraview Plugin, if that matters. I could
> provide some Screenshots too if this might help.
>
> Thanks,
> Felix
>
> _____________________________________
> Powered by www.kitware.com
>
> Visit other Kitware open-source projects at
> http://www.kitware.com/opensource/opensource.html
>
> Kitware offers ITK Training Courses, for more information visit:
> http://www.kitware.com/products/protraining.php
>
> Please keep messages on-topic and check the ITK FAQ at:
> http://www.itk.org/Wiki/ITK_FAQ
>
> Follow this link to subscribe/unsubscribe:
> http://public.kitware.com/mailman/listinfo/insight-users
>