[Insight-users] Hints to create a known deformation image - Deformable Image registration?

[motes motes]

On Mon, Nov 2, 2009 at 12:54 AM, Luis Ibanez <luis.ibanez at kitware.com> wrote:
> Hi Motes,
>
> I thought that you were looking for an image to deform,
> by applying to it the deformation field resulting from
> a deformable registration process.


I would like to compare the deformation field resulting from the
deformable registration process with a known deformation field. As I
understand this is one way to analyse the quality of the registration
process. But maybe I can do something like this:


1) Make a known deformation of Lena.
2) Apply this known deformation to a regular grid resulting in GRID_KNOWN.
3) Use the known deformation of Lena as the moving image in the
registration process.
4) Apply the resulting deformation field to a regular grid resulting
in GRID_REGISTERED.
5) Compare GRID_KNOWN with GRID_REGISTERED.



>
> You are correct in that a grid image will be a poor input
> for a deformable registration process.
>      Regards,
>
>
>           Luis
>
>
> ---------------------------------------------------
> On Sun, Nov 1, 2009 at 6:27 PM, motes motes <mort.motes at gmail.com> wrote:
>> Thanks both of you. But should the optimizer not have something to
>> move in to find the peak of the cost function? I have previously used
>> a white image with a single black box and the result was very poor
>> when using eg. gradient based optimizer.
>>
>> I was thinking that the same problem would occur if I made a white
>> image with a black grid.
>>
>>
>>
>>
>> On Mon, Nov 2, 2009 at 12:17 AM, Nicholas Tustison <ntustison at gmail.com> wrote:
>>> Hi Luis, Motes,
>>>
>>> Another possibility you might want to consider
>>>
>>> http://public.kitware.com/Insight/Doxygen/html/classitk_1_1GridImageSource.html
>>>
>>> Nick
>>>
>>>
>>> On Nov 1, 2009, at 6:06 PM, Luis Ibanez wrote:
>>>
>>>> Hi Motes,
>>>>
>>>> 1) Lena is certainly not the best motif for evaluating a deformable
>>>>    registration process. You may want to use a grid image with
>>>>    about four time the density of lines of the BSpline grid, and
>>>>    lines that are more than 2 pixels apart.
>>>>
>>>>    The reason why you want lines to be more than 2 pixels apart
>>>>    is to avoid aliasing when you resample the image using the
>>>>    deformation field.
>>>>
>>>> 2) You could create such image by using GIMP
>>>>
>>>>      a) Open Gimp
>>>>      b) create a new image,
>>>>      c) Select Filters --> Render--> Pattern --> Grid
>>>>      d) save the image
>>>>
>>>>
>>>> 3)  Yes, you can make more detailed initial deformation...
>>>>      but you have to initialize all the coefficients.
>>>>
>>>>      It may be desirable to generate those initial numbers
>>>>       from a program...
>>>>
>>>>
>>>>   Regards,
>>>>
>>>>
>>>>         Luis
>>>>
>>>>
>>>> --------------------------------------------------------------------
>>>>
>>>> On Fri, Oct 30, 2009 at 2:25 PM, motes motes <mort.motes at gmail.com> wrote:
>>>>>
>>>>> I would like to test my BSplineDeformable registration method with a
>>>>> known deformation field. Currently I apply the BSplineWarping1.cxx
>>>>> example to the fixed image and use the output as the moving image. As
>>>>> input image I use lena:
>>>>>
>>>>> http://stochastix.files.wordpress.com/2008/07/lena-sjooblom.jpg
>>>>>
>>>>> But are there better motives that illustrate the deformation better
>>>>> (like a chess board, salt/pebber image etc)?
>>>>>
>>>>> And is it possible to create a more detailed know deformation instead
>>>>> of only changing the 8*8 deformation vectors in the text input file to
>>>>> the warper?
>>>>> _____________________________________
>>>>> 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.html
>>>>>
>>>>> 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://www.itk.org/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.html
>>>>
>>>> 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://www.itk.org/mailman/listinfo/insight-users
>>>
>>>
>>
>