[ITK] [ITK-users] Region Growing for huge data set

[Lowekamp, Bradley (NIH/NLM/LHC) [C]]

Hello,

Unfortunately, the region growing algorithms do not support streaming to my knowledge. But this certainly could help other parts of the pipeline, along with releasing unneeded data.

Firstly, what OS and architecture are you compiling for? Did you choose Win64 or ensure your using 64-bits architecture?

Next, many region grown algorithms are equivalent to running a binary threshold then a connected components algorithm these choosing the correct label(s). I have found for large data this is frequently more computational and memory efficient than the region growing methods. In addition, the BinaryThesholdImageFilter can be run “InPlace”, and the BinaryImageToLabelMapFilter is an implementation of the connected components algorithm to RLE labels is memory efficient as well.

HTH,
Brad


On Nov 14, 2016, at 9:29 AM, Dženan Zukić <dzenanz at gmail.com<mailto:dzenanz at gmail.com>> wrote:

Hi Abdelkhalek,

depending on the filters in your pipeline (whether all of them support streaming), it might be useful to use StreamingImageFilter<https://itk.org/Doxygen/html/classitk_1_1StreamingImageFilter.html>. If not, you could have all intermediate results deallocated before starting the main (most memory intensive) processing step:

ImageType::Pointer intermediate;
//open a block, so that all variables created in it are deallocated at the end of it
{
//read image
//do some processing
lastFilterInThisBlock->Update();
intermediate=lastFilterInThisBlock->GetOutput();
}
//everything except intermediate will be deallocated at this point, freeing memory
mainProcessingStep(intermediate);

Regards,
Dženan

On Sun, Nov 13, 2016 at 10:03 AM, Abdelkhalek Bakkari <bakkari.abdelkhalek at hotmail.fr<mailto:bakkari.abdelkhalek at hotmail.fr>> wrote:

Dear ITK users,


I am trying to evaluate my region growing ITK code. Unfortunately, for a huge data (more than 100 .dcm images), the application turn blocked and some errors appear (please find it in attachment)


Do you have any suggestion or help ?



Thank you in advance.


Best regards,



Abdelkhalek Bakkari
Ph.D candidate in Computer Science
Institute of Applied Computer Science
Lodz University of Technology, Poland



_____________________________________
Powered by www.kitware.com<http://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<http://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

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://public.kitware.com/pipermail/community/attachments/20161114/e4f72bef/attachment-0001.html>
-------------- next part --------------
_____________________________________
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