# Lung tumour segmentation

**URL:** <https://discourse.slicer.org/t/lung-tumour-segmentation/22111>\
**Category:** Support\
**Created:** [February 22, 2022, 12:09pm UTC](https://discourse.slicer.org/t/lung-tumour-segmentation/22111 "2022-02-22T12:09:14Z")\
**Posts on this page:** 5\
**Page:** 1

<div class="post-metadata">

**Author:** ![ni5h](https://avatars.discourse-cdn.com/v4/letter/n/839c29/32.png) [@ni5h](https://discourse.slicer.org/u/ni5h)\
**Post date:** [February 22, 2022, 12:09pm UTC](https://discourse.slicer.org/t/lung-tumour-segmentation/22111/1 "2022-02-22T12:09:14Z")

</div>

Hi, for complex lung tumours, other than grow from seeds and fill between slices etc, is there an extension that can annotate a lung tumours? I have found completing this via GfS as not very accurate - imaging dataset is routine but I was hoping there is an extension whereby it would assist in segmenting the tumour only

---

<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:** [February 22, 2022, 5:54pm UTC](https://discourse.slicer.org/t/lung-tumour-segmentation/22111/2 "2022-02-22T17:54:58Z")

</div>

Hi, there is no specialized extension for advanced lung tumor segmentation yet.  
Try the “Surface Cut” Segment Editor effect and settings like this (Slicer 4.13):

 ![image](https://us1.discourse-cdn.com/flex002/uploads/slicer/original/3X/d/a/dabab0c20505462fa30c4740fa04b45f8d6a8df1.png)

You would place your markups around the complex tumor _in the healthy lung tissue and along the chest wall, if the tumor is adjacent_, press “Apply” and get a reasonable/good result (can´t show the segmentation result for privacy reasons).

---

<div class="post-metadata">

**Author:** ![ni5h](https://avatars.discourse-cdn.com/v4/letter/n/839c29/32.png) [@ni5h](https://discourse.slicer.org/u/ni5h)\
**Post date:** [February 22, 2022, 7:48pm UTC](https://discourse.slicer.org/t/lung-tumour-segmentation/22111/3 "2022-02-22T19:48:40Z")

</div>

Thank you for your suggestion, however, for complex tumours where the tumour can be impeding into the aorta and adjacent areas, the process is particularly slow. I have tried nvidia ai assisted ct lung covid 19 to see if this offers a solution but it does not work, even the lung ct segmenter cuptures the lung well but not the tumour, maybe I can work out if I can integrate lung ct segmenter and see if i can find a way to threshold the tumour after this. I will try. Thanks

---

<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:** [February 22, 2022, 8:04pm UTC](https://discourse.slicer.org/t/lung-tumour-segmentation/22111/4 "2022-02-22T20:04:34Z")

</div>

I am planning to integrate lung lesion segmentation into the Lung CT Segmenter later this year. If you identify a good workflow please let me know.

---

<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:** [February 23, 2022, 12:57am UTC](https://discourse.slicer.org/t/lung-tumour-segmentation/22111/5 "2022-02-23T00:57:46Z")

</div>

@ni5h If you can share an anonymized data set (upload somewhere and post the link) then we can help developing a quick and accurate segmentation workflow for it.