# TotalSegmentator for MRI dataset

**URL:** <https://discourse.slicer.org/t/totalsegmentator-for-mri-dataset/35080>\
**Category:** Support\
**Created:** [March 26, 2024, 1:26am UTC](https://discourse.slicer.org/t/totalsegmentator-for-mri-dataset/35080 "2024-03-26T01:26:34Z")\
**Posts on this page:** 4\
**Page:** 2

<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:** [June 23, 2024, 10:38pm UTC](https://discourse.slicer.org/t/totalsegmentator-for-mri-dataset/35080/21 "2024-06-23T22:38:43Z")

</div>

Extension builds for Slicer Stable Release are restored now.

---

<div class="post-metadata">

**Author:** ![Hasanb](https://avatars.discourse-cdn.com/v4/letter/h/91b2a8/32.png) [@Hasanb](https://discourse.slicer.org/u/Hasanb)\
**Post date:** [July 24, 2024, 12:23pm UTC](https://discourse.slicer.org/t/totalsegmentator-for-mri-dataset/35080/22 "2024-07-24T12:23:03Z")

</div>

Dear lassoan,  
I am new at this community, sorry if this question is answered another place. I wonder whether there is a way to use total\_MR to segment the spinal canal and not only the structures around it? I am working on a project to segment and measure the volume of the spinal canal.  
Bests!

---

<div class="post-metadata">

**Author:** ![Spiros\_Karkavitsas](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/spiros_karkavitsas/32/18224_2.png) [@Spiros\_Karkavitsas](https://discourse.slicer.org/u/Spiros_Karkavitsas)\
**Post date:** [August 5, 2024, 6:35pm UTC](https://discourse.slicer.org/t/totalsegmentator-for-mri-dataset/35080/23 "2024-08-05T18:35:53Z")

</div>

Hello from my side too!  
I just found out about the existence of TotalSegmentator for MR specifically and it seems amazing and very promising!  
I worked in the past with MONAI Label and I was quite satisfied with the results.

Was there any air segmentation in your training dataset?  
I am wondering since the MR slices I am working on is 10 mm slice thickness so I guess the accuracy would be low, correct?

---

<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:** [August 19, 2024, 1:38pm UTC](https://discourse.slicer.org/t/totalsegmentator-for-mri-dataset/35080/24 "2024-08-19T13:38:15Z")

</div>

> [@Spiros\_Karkavitsas](#):
>
> Was there any air segmentation in your training dataset?

MR task of TotalSegmentator currently does not include airways, but if you exclude all known segmented regions then you may be able to segment the air using Threshold or with “Grow from seeds” effect.

> [@Spiros\_Karkavitsas](#):
>
> I am wondering since the MR slices I am working on is 10 mm slice thickness so I guess the accuracy would be low, correct?

Yes, 10mm distance between slices is so huge that it is not really usable for 3D analysis.

[Previous page](https://discourse.slicer.org/t/totalsegmentator-for-mri-dataset/35080.md?page=1)