# A very dumb question: how do I implement a voxel-based feature extraction?

**URL:** <https://discourse.slicer.org/t/a-very-dumb-question-how-do-i-implement-a-voxel-based-feature-extraction/26018>\
**Category:** Support\
**Tags:** radiomics\
**Created:** [November 2, 2022, 3:21am UTC](https://discourse.slicer.org/t/a-very-dumb-question-how-do-i-implement-a-voxel-based-feature-extraction/26018 "2022-11-02T03:21:53Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![blaze\_cipher](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/blaze_cipher/32/17141_2.png) [@blaze\_cipher](https://discourse.slicer.org/u/blaze_cipher)\
**Post date:** [November 2, 2022, 3:21am UTC](https://discourse.slicer.org/t/a-very-dumb-question-how-do-i-implement-a-voxel-based-feature-extraction/26018/1 "2022-11-02T03:21:53Z")

</div>

To anyone who can help:  
I’ve learnt that voxel based feature extraction would generate a .nrrd file, but I can only generate a generic csv file, though in the file it showd dimensionality was 3D and voxel numbers, so how can I correctly execute a voxel based feature extraction? Thanks!
