# How to test my own data in TotalSegmentator

**URL:** <https://discourse.slicer.org/t/how-to-test-my-own-data-in-totalsegmentator/29136>\
**Category:** Support\
**Tags:** segmentation\
**Created:** [April 26, 2023, 11:04am UTC](https://discourse.slicer.org/t/how-to-test-my-own-data-in-totalsegmentator/29136 "2023-04-26T11:04:39Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![whu](https://avatars.discourse-cdn.com/v4/letter/w/7ab992/32.png) [@whu](https://discourse.slicer.org/u/whu)\
**Post date:** [April 26, 2023, 11:04am UTC](https://discourse.slicer.org/t/how-to-test-my-own-data-in-totalsegmentator/29136/1 "2023-04-26T11:04:39Z")

</div>

After installed the TotalSegmentator extensions successfully, the example dataset was good.  
But when using the WH-2019 dataset([Multi-Modality Whole Heart Segmentation Challenge](https://zmiclab.github.io/zxh/0/mmwhs/)), one of the test ct data,  
the result is like this:

 ![image](https://us1.discourse-cdn.com/flex002/uploads/slicer/original/3X/1/a/1ac368dc4dfb31da235b67aa59c6fa22f0f0a7e3.png)  
seemed not as the CTA example dataset in Slicer.  
Here, what about the common CT data loaded in Slicer, how to set the parameters in order to get the correct results?  
thanks.

---

<div class="post-metadata">

**Author:** ![whu](https://avatars.discourse-cdn.com/v4/letter/w/7ab992/32.png) [@whu](https://discourse.slicer.org/u/whu)\
**Post date:** [May 12, 2023, 12:58pm UTC](https://discourse.slicer.org/t/how-to-test-my-own-data-in-totalsegmentator/29136/2 "2023-05-12T12:58:58Z")

</div>

Nobody care this ? 😛

---

<div class="post-metadata">

**Author:** ![ATAKAN\_Isik](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/atakan_isik/32/65977_2.png) [@ATAKAN\_Isik](https://discourse.slicer.org/u/ATAKAN_Isik)\
**Post date:** [May 13, 2023, 1:15pm UTC](https://discourse.slicer.org/t/how-to-test-my-own-data-in-totalsegmentator/29136/3 "2023-05-13T13:15:34Z")

</div>

Hi,  
As far i know totalsegmentator use nn-UNET. You can use this network on pyhton for testing your own data  
[GitHub - MIC-DKFZ/nnUNet](https://github.com/MIC-DKFZ/nnUNet) is the github repo for this network .

---

<div class="post-metadata">

**Author:** ![rbumm](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/rbumm/32/9404_2.png) [@rbumm](https://discourse.slicer.org/u/rbumm)\
**Post date:** [May 14, 2023, 6:09pm UTC](https://discourse.slicer.org/t/how-to-test-my-own-data-in-totalsegmentator/29136/4 "2023-05-14T18:09:41Z")

</div>

Are all of the test data giving you a problem? Or just this single one from a bigger dataset?  
If it is just this only series you may want to find out the reason in what way these data are different. You could start in the Volume module under “Advanced” and compare.