# SAM 2 from Meta (Segment Anything Model)

**URL:** <https://discourse.slicer.org/t/sam-2-from-meta-segment-anything-model/37794>\
**Category:** Support\
**Created:** [August 9, 2024, 7:29am UTC](https://discourse.slicer.org/t/sam-2-from-meta-segment-anything-model/37794 "2024-08-09T07:29:50Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![marcosncosta1](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/marcosncosta1/32/67665_2.png) [@marcosncosta1](https://discourse.slicer.org/u/marcosncosta1)\
**Post date:** [August 9, 2024, 7:29am UTC](https://discourse.slicer.org/t/sam-2-from-meta-segment-anything-model/37794/1 "2024-08-09T07:29:50Z")

</div>

Hello everyone,  
I just wanted to check if anyone has seen this and thought about implementing into the Total Segmentator. I feel like the Total Segmentator is really good already but when it comes to segmenting vertebrae with instrumentation it can get quite tricky.  
I was wondering if this new model from META (since it is open source) could be used to improve on what Slicer has already?