# Loading images and segmentation in Slicer v.s. ITKSNAP

**URL:** <https://discourse.slicer.org/t/loading-images-and-segmentation-in-slicer-v-s-itksnap/32441>\
**Category:** Support\
**Created:** [October 27, 2023, 4:39am UTC](https://discourse.slicer.org/t/loading-images-and-segmentation-in-slicer-v-s-itksnap/32441 "2023-10-27T04:39:37Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![Chenglin\_Zhu](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/chenglin_zhu/32/11031_2.png) [@Chenglin\_Zhu](https://discourse.slicer.org/u/Chenglin_Zhu)\
**Post date:** [October 27, 2023, 4:39am UTC](https://discourse.slicer.org/t/loading-images-and-segmentation-in-slicer-v-s-itksnap/32441/1 "2023-10-27T04:39:37Z")

</div>

![image](https://us1.discourse-cdn.com/flex002/uploads/slicer/original/3X/f/0/f07986c328c8dd48383bfe2c252a35400c036f58.jpeg)

Hi all,

I am wondering what is the differences between Slicer and ITKSNAP when loading images and segmentation. Here are the snapshot of dicom images and auto-segmentation based on the nifti image (using dcm2nii conversion) in Slicer (left image) and ITKSNAP (right image). There is a misalignment when I load images in ITKSNAP, I am wondering how Slicer read it correctly, so that I can avoid this misalignment issue when coding my own project. Thanks!

---

<div class="post-metadata">

**Author:** ![pieper](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/pieper/32/8_2.png) [@pieper](https://discourse.slicer.org/u/pieper)\
**Post date:** [October 27, 2023, 11:28am UTC](https://discourse.slicer.org/t/loading-images-and-segmentation-in-slicer-v-s-itksnap/32441/2 "2023-10-27T11:28:48Z")

</div>

Looks like an RAS/LPS issue.

[https://slicer.readthedocs.io/en/latest/user\_guide/coordinate\_systems.html](https://slicer.readthedocs.io/en/latest/user_guide/coordinate_systems.html)

---

<div class="post-metadata">

**Author:** ![jcfr](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/jcfr/32/17825_2.png) [@jcfr](https://discourse.slicer.org/u/jcfr)\
**Post date:** [October 27, 2023, 2:46pm UTC](https://discourse.slicer.org/t/loading-images-and-segmentation-in-slicer-v-s-itksnap/32441/3 "2023-10-27T14:46:42Z")

</div>

> ITKSNAP (right image)

To add to @pieper comment, based on the image you shared, the segmentation loaded in ITKSNAP does **not** align with the underlying structure visible on the loaded dicom image.

> Slicer (left image)

whereas the segmentation loaded in Slicer is properly aligned.

---

<div class="post-metadata">

**Author:** ![lassoan](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/lassoan/32/13_2.png) [@lassoan](https://discourse.slicer.org/u/lassoan)\
**Post date:** [October 27, 2023, 9:59pm UTC](https://discourse.slicer.org/t/loading-images-and-segmentation-in-slicer-v-s-itksnap/32441/4 "2023-10-27T21:59:39Z")

</div>

I would just add that definition of image orientation in NIFTI files can be ambiguous. Therefore sometimes the same files show up differently in different software. I would recommend to use NRRD file format instead of NIFTI to avoid such issues.