# Discontinuous ROI for radiomics

**URL:** <https://discourse.slicer.org/t/discontinuous-roi-for-radiomics/22483>\
**Category:** Radiomics\
**Created:** [March 13, 2022, 12:59pm UTC](https://discourse.slicer.org/t/discontinuous-roi-for-radiomics/22483 "2022-03-13T12:59:00Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Amir\_Zolal](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/amir_zolal/32/9423_2.png) [@Amir\_Zolal](https://discourse.slicer.org/u/Amir_Zolal)\
**Post date:** [March 13, 2022, 12:59pm UTC](https://discourse.slicer.org/t/discontinuous-roi-for-radiomics/22483/1 "2022-03-13T12:59:00Z")

</div>

Hello, this is rather a general question regarding the functioning of the algorithm.

I have some ROIs that I use to extract image pixel intensity from images and would like to re-use these ROIs in feature detection. However, the ROIs are discontinuous (meaning that the a specific tissue is marked on different places in the scan, without there being connection between those tissues).

The radiomics program (at least pyradiomics) does produce a csv when using this ROI.

Will the output be anyhow affected by the discontinuity, i mean does the ROI border affect the feature recognition somehow?

Thanks in advance for the answer,

Amir
