# Segmentation tool, Deep learning, Auditory ossicles

**URL:** <https://discourse.slicer.org/t/segmentation-tool-deep-learning-auditory-ossicles/16852>\
**Category:** Support\
**Created:** [March 30, 2021, 3:28pm UTC](https://discourse.slicer.org/t/segmentation-tool-deep-learning-auditory-ossicles/16852 "2021-03-30T15:28:34Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![j.v.d](https://avatars.discourse-cdn.com/v4/letter/j/8c91f0/32.png) [@j.v.d](https://discourse.slicer.org/u/j.v.d)\
**Post date:** [March 30, 2021, 3:28pm UTC](https://discourse.slicer.org/t/segmentation-tool-deep-learning-auditory-ossicles/16852/1 "2021-03-30T15:28:34Z")

</div>

Operating system: macOS Big Sur 11.2.1  
Slicer version: 4.11.20210226  
Expected behavior: Automatic segmentation of the auditory ossicles  
Actual behavior: Segmentation via thresholding and no segmentation for the stapes

Hey everyone!  
I´m working on a project about the 3D-segmentation of the middle ear with different CT modalities.  
I already segmented some of the auditory ossicles but until now I didn’t achieve a segmentation of the stapes and the tympanic membrane with the thresholding tool even with very high resolution images.  
Is there already a special tool for the segmentation of these anatomic structures ?  
And further I wanted to ask, if there is already a tool for the automatic segmentation of the auditory ossicles via deep learning ?

Thanks a lot in advance!  
Kind regards  
Jan

---

<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:** [April 3, 2021, 3:14am UTC](https://discourse.slicer.org/t/segmentation-tool-deep-learning-auditory-ossicles/16852/2 "2021-04-03T03:14:09Z")

</div>

You may find that representation of very thin membranes and curves requires very high resolution segmentation. If your computer cannot handle sufficiently high-resolution segmentations (it runs out of physical memory and starts swapping memory to disk, making everything extremely slow) then you can model them using curves and curved surfaces.

You can use Markups Curves to “segment” stapes and the newly added [Baffle planner module](https://discourse.slicer.org/t/new-module-baffle-planner-for-designing-surface-patches/16799) to create a model of the membrane.

> [@j.v.d](#):
>
> And further I wanted to ask, if there is already a tool for the automatic segmentation of the auditory ossicles via deep learning ?

I would think so. You may contact members of the [Auditory Medical Biophysics Lab at Western University](https://github.com/Auditory-Biophysics-Lab/Slicer-ABLTemporalBoneSegmentation) to get more information.