# gap filling of breaks between vessels

**URL:** https://discourse.itk.org/t/gap-filling-of-breaks-between-vessels/3925
**Category:** Algorithms
**Created:** [March 3, 2021, 3:35pm UTC](https://discourse.itk.org/t/gap-filling-of-breaks-between-vessels/3925 "2021-03-03T15:35:27Z")
**Posts on this page:** 3
**Page:** 1

<div class="post-metadata">

### Author: ![fuentesdt](https://discourse.itk.org/user_avatar/discourse.itk.org/fuentesdt/32/1964_2.png) [@fuentesdt](https://discourse.itk.org/u/fuentesdt)
#### Post date: [March 3, 2021, 3:35pm UTC](https://discourse.itk.org/t/gap-filling-of-breaks-between-vessels/3925/1 "2021-03-03T15:35:27Z")

</div>

Hi, Is there any functionality in itk for gap/hole filling specific to vessels? something like this tensor voting method: Risser, Laurent, Franck Plouraboué, and Xavier Descombes. “Gap filling of 3-D microvascular networks by tensor voting.” _IEEE transactions on medical imaging_ 27.5 (2008): 674-687.

We have pre-processed enhanced our imaging data and applied vesselness filters, but there are still some breaks in the vessel structure segmentations that need to be joined before generating the surface mesh for centerline extraction.

---

<div class="post-metadata">

### Author: ![dzenanz](https://discourse.itk.org/user_avatar/discourse.itk.org/dzenanz/32/1093_2.png) [@dzenanz](https://discourse.itk.org/u/dzenanz)
#### Post date: [March 4, 2021, 3:52pm UTC](https://discourse.itk.org/t/gap-filling-of-breaks-between-vessels/3925/2 "2021-03-04T15:52:46Z")

</div>

Perhaps @Stephen_Aylward could comment.

---

<div class="post-metadata">

### Author: ![Stephen\_Aylward](https://discourse.itk.org/user_avatar/discourse.itk.org/stephen_aylward/32/654_2.png) [@Stephen\_Aylward](https://discourse.itk.org/u/Stephen_Aylward)
#### Post date: [March 9, 2021, 3:41pm UTC](https://discourse.itk.org/t/gap-filling-of-breaks-between-vessels/3925/3 "2021-03-09T15:41:45Z")

</div>

You might want to consider using ITKTubeTK. It begins with a centerline extraction method that is perhaps less sensitive to small gaps in the data.

The best way to get started with it is to explore the examples:

> **[InsightSoftwareConsortium/ITKTubeTK](https://github.com/InsightSoftwareConsortium/ITKTubeTK/tree/master/examples)**
>
> master/examples

Let me know if you have any troubles.
