[ITK Community] Fwd: Points Cloud in C#

Luis Ibanez luis.ibanez at kitware.com
Sat Dec 14 09:22:03 EST 2013


Matias,

There are not many examples in C#.

One way to go is to write the process into a C++ class,
and then wrap it into C# using SWIG,
which is what SimpleITK does.

In this way you could still start from those examples.

   Thanks

        Luis


On Sat, Dec 14, 2013 at 6:46 AM, Matias Montroull <matimontg at gmail.com>wrote:

> Thank you Luis,
>
> I see it's written in C++, is there any examples in C#? I'm using this
> library: SimpleITK-0.6.1.post2-CSharp-win64-x64
>
> Regards,
>
> Matias.
>
>
> On Fri, Dec 13, 2013 at 1:30 PM, Luis Ibanez <luis.ibanez at kitware.com>wrote:
>
>> Matias,
>>
>> Open the DICOM stack in an image viewer (such as Slicer), and identify a
>> threshold
>> value of intensity that will separate the skin from the air outside the
>> patient.
>>
>>
>> With that number at hand,
>> you an try the following example:
>>
>> http://www.itk.org/Wiki/ITK/Examples/ImageProcessing/BinaryThresholdImageFilter
>> that you can follow with a BinaryMask3DMeshSource,
>> to finally grab the points out of the resulting Mesh.
>>
>>
>> Another option is to use a region growing filter,
>> and place the seed point in the air region:
>>
>> https://github.com/InsightSoftwareConsortium/ITKApps/blob/master/Auxiliary/vtk/itkReadITKImage3DSegmentShowVTK.cxx
>> That will be a segmentation of the "negative",
>> but since you are looking for the cloud of points,
>> the output will still be equivalent.
>>
>> There are many alternatives to achieve the equivalent process.
>>
>>
>>    Hope this helps,
>>
>>
>>        Luis
>>
>>
>>
>> On Fri, Dec 13, 2013 at 10:04 AM, Matias Montroull <matimontg at gmail.com>wrote:
>>
>>> Correct
>>>
>>>
>>> On Fri, Dec 13, 2013 at 11:53 AM, Luis Ibanez <luis.ibanez at kitware.com>wrote:
>>>
>>>> Matias,
>>>>
>>>> Are you looking for the point cloud on the surface of the patient's
>>>> skin ?
>>>>
>>>>   Thanks
>>>>
>>>>       Luis
>>>>
>>>>
>>>> On Fri, Dec 13, 2013 at 9:49 AM, Matias Montroull <matimontg at gmail.com>wrote:
>>>>
>>>>> Hi Luis,
>>>>>
>>>>> Thank you for the information, the DICOM Images are Head RMN, that's
>>>>> what we're trying to segment.
>>>>>
>>>>> If you could provide some sample code I will appreciate it.
>>>>>
>>>>> Regards,
>>>>>
>>>>> Matias.
>>>>>
>>>>>
>>>>> On Fri, Dec 13, 2013 at 11:25 AM, Luis Ibanez <luis.ibanez at kitware.com
>>>>> > wrote:
>>>>>
>>>>>> Hi Matias,
>>>>>>
>>>>>> In order to get a point cloud out of a stack of DICOM images, you
>>>>>> first have to run a segmentation method.
>>>>>>
>>>>>> There is a large number of methods available, and their applicability
>>>>>> depend strongly on the type of data
>>>>>> that you have.
>>>>>>
>>>>>> Could you please share more information about the nature and content
>>>>>> of your DICOM images,
>>>>>> and the specific anatomical structure that you are trying to segment ?
>>>>>>
>>>>>>    Thanks
>>>>>>
>>>>>>         Luis
>>>>>>
>>>>>>
>>>>>>
>>>>>> On Mon, Dec 9, 2013 at 6:42 PM, Matias Montroull <matimontg at gmail.com
>>>>>> > wrote:
>>>>>>
>>>>>>>
>>>>>>> Hi,
>>>>>>>
>>>>>>> Is there a way to obtain the points cloud from a stack of DICOM
>>>>>>> images using ITK? (I have a directory with the images). Can you help me
>>>>>>> with some code?
>>>>>>>
>>>>>>> I'm working on a VS2012 project written in C#. I downloaded the ITK
>>>>>>> C# DLLs..
>>>>>>>
>>>>>>> Thank you!
>>>>>>>
>>>>>>> Matias.
>>>>>>>
>>>>>>>
>>>>>>> _______________________________________________
>>>>>>> Community mailing list
>>>>>>> Community at itk.org
>>>>>>> http://public.kitware.com/cgi-bin/mailman/listinfo/community
>>>>>>>
>>>>>>>
>>>>>>
>>>>>
>>>>
>>>
>>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://public.kitware.com/pipermail/community/attachments/20131214/002f9a3e/attachment.html>


More information about the Community mailing list