Jakob Wasserthal
Jakob Wasserthal
This is a great idea. I did not know that you can upload unlimited number of files up to 2GB of size to github for free. I uploaded the files...
Sure. I am currently uploading them. Should be done in 10min.
Probably next week I will merge the v2 branch with the master branch and update the pip package. It will remain `pip install totalsegmentator`. If you want the old version...
This UserWarning happens all the time with nnU-Netv2==2.3.1 It is not the source of the problem. Can you reinstall in a new environment and also download the new weights?
We are currently working on adding support for MRI images and for subcortical structures. But it will take a bit more time.
Hello, the training data does not contain any MRI images, only CT images. We are currently working on building another TotalSegmentator for MRI. But this will take some more time....
Good questions. Can you send me the image so I can try to reproduce the issue?
I changed the code so now all header fields from the input are copied to the output file. Can you try it again with the latest master?
I would recommend the following solution: Overwrite the sform from the label map with the sform from the ct image. Thus they will be identical and Slicer should be happy....
I would like to remove the SimpleITK version restriction. However, at the moment this issue (https://github.com/SimpleITK/SimpleITK/issues/1433) is still existing in the most recent version (v 2.2.0) if I understand it...