# Segmentation of swim bladders in micro-CT scans

**URL:** <https://discourse.slicer.org/t/segmentation-of-swim-bladders-in-micro-ct-scans/43325>\
**Category:** Support\
**Tags:** segmentation\
**Created:** [June 11, 2025, 7:22pm UTC](https://discourse.slicer.org/t/segmentation-of-swim-bladders-in-micro-ct-scans/43325 "2025-06-11T19:22:38Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![BennyShoe](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/bennyshoe/32/78820_2.png) [@BennyShoe](https://discourse.slicer.org/u/BennyShoe)\
**Post date:** [June 11, 2025, 7:22pm UTC](https://discourse.slicer.org/t/segmentation-of-swim-bladders-in-micro-ct-scans/43325/1 "2025-06-11T19:22:38Z")

</div>

Hello everyone,

I’m new to the Slicer community and currently working on a project involving the segmentation of swim bladders(circled in blue) from fish micro-CT scans. However, I’m running into difficulty due to the low contrast between the swim bladder and the surrounding area.

So far, I’ve been using the paint tool to manually segment the swim bladder slice by slice. Unfortunately, the final segment often appears irregular or incomplete.

I want to improve the overall quality of the results, so I was wondering if there is a recommended approach for segmenting low contrast regions like this? Are there specific segmentation tools that you’ve found helpful in similar situations?

Any advice or suggestions would be greatly appreciated!

Thank you,  
-B

 ![SB1](https://us1.discourse-cdn.com/flex002/uploads/slicer/original/3X/9/0/90ad9471cc5c100396e71baecdda6142a6a80368.png)

---

<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:** [June 11, 2025, 7:29pm UTC](https://discourse.slicer.org/t/segmentation-of-swim-bladders-in-micro-ct-scans/43325/2 "2025-06-11T19:29:55Z")

</div>

That does look tough, but maybe nnInteractive would be worth trying.

---

<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 13, 2025, 12:54am UTC](https://discourse.slicer.org/t/segmentation-of-swim-bladders-in-micro-ct-scans/43325/3 "2025-06-13T00:54:04Z")

</div>

Since there is some contrast, there is a chance that “Grow from seeds” or “Watershed” (provided by SegmentEditorExtraEffects extension) effect can do it, too.