# Should CT images be windowed prior to feature extraction?

**URL:** <https://discourse.slicer.org/t/should-ct-images-be-windowed-prior-to-feature-extraction/26610>\
**Category:** Radiomics\
**Created:** [December 6, 2022, 5:08pm UTC](https://discourse.slicer.org/t/should-ct-images-be-windowed-prior-to-feature-extraction/26610 "2022-12-06T17:08:21Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Hansman](https://avatars.discourse-cdn.com/v4/letter/h/bb73d2/32.png) [@Hansman](https://discourse.slicer.org/u/Hansman)\
**Post date:** [December 6, 2022, 5:08pm UTC](https://discourse.slicer.org/t/should-ct-images-be-windowed-prior-to-feature-extraction/26610/1 "2022-12-06T17:08:21Z")

</div>

We’ve had a bit of debate in our group about whether CT images should be windowed from 16 bit grayscale to 8 bit grayscale values prior to extracting features, and I can’t find anything about it in the documentation. Does anyone have any insight into this? Thanks in advance!
