# Otsu segmentation on Head and Neck PET image

**URL:** https://discourse.slicer.org/t/otsu-segmentation-on-head-and-neck-pet-image/21235
**Category:** Support
**Created:** [December 27, 2021, 12:22pm UTC](https://discourse.slicer.org/t/otsu-segmentation-on-head-and-neck-pet-image/21235 "2021-12-27T12:22:31Z")
**Posts on this page:** 2
**Page:** 1

<div class="post-metadata">

### Author: ![MPhilip](https://avatars.discourse-cdn.com/v4/letter/m/5f8ce5/32.png) [@MPhilip](https://discourse.slicer.org/u/MPhilip)
#### Post date: [December 27, 2021, 12:22pm UTC](https://discourse.slicer.org/t/otsu-segmentation-on-head-and-neck-pet-image/21235/1 "2021-12-27T12:22:31Z")

</div>

Operating system: Windows 11 home  
Slicer version:Slicer 4.13.0-2021-12-22  
Is it advisable to use otsu method to segment tumour (marked in blue) on PET images? If it is possible, please guide me to the relevant resources (a tutorial preferably) on how to apply the otsu method to this image. I tried otsu method, but not sure whether I did it right.  
 ![image](https://us1.discourse-cdn.com/flex002/uploads/slicer/original/3X/1/4/145b87c85f58d435fadba13eb71b9c064cb11e6b.png)

If there are any other methods that would work on this image please suggest that too pointing to relevant documents.

Thanks in advance.

---

<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: [December 27, 2021, 12:52pm UTC](https://discourse.slicer.org/t/otsu-segmentation-on-head-and-neck-pet-image/21235/2 "2021-12-27T12:52:15Z")

</div>

Otsu threshold is not typically used for this. 40-43% of maximum SUV value is used instead. There have been a few discussions about this, for example:

> [@Segmentation from curved plane by markup points](https://discourse.slicer.org/t/segmentation-from-curved-plane-by-markup-points/16629/6):
>
> For the first question is this something like what you are building @RafaelPalomar ? Regarding your second question, that’s a mode I also want to implement for a PET project I’m involved with. Probably it can just be a simple segment editor effect that would be used as follows: use the Paint (or any tool) to draw anything that is possibly lesion and then the effect would calculate the max value of the background in that segment and then only keep the places where the background are 41% of that…