# Reproducibility of Radiomics Results with Pyradiomics and Parenchymal Analysis

**URL:** <https://discourse.slicer.org/t/reproducibility-of-radiomics-results-with-pyradiomics-and-parenchymal-analysis/22933>\
**Category:** Radiomics\
**Created:** [April 13, 2022, 12:03pm UTC](https://discourse.slicer.org/t/reproducibility-of-radiomics-results-with-pyradiomics-and-parenchymal-analysis/22933 "2022-04-13T12:03:39Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![chuawm](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/chuawm/32/11915_2.png) [@chuawm](https://discourse.slicer.org/u/chuawm)\
**Post date:** [April 13, 2022, 12:03pm UTC](https://discourse.slicer.org/t/reproducibility-of-radiomics-results-with-pyradiomics-and-parenchymal-analysis/22933/1 "2022-04-13T12:03:39Z")

</div>

Hi there,

I am trying to see if the Radiomics module analysis for the lung segmentation I performed using CIP is consistent with that derived from Parenchymal Analysis. This is partly because the Parenchymal Analysis is no longer available on the later versions of 3D Slicer. Thus far, most of the parameters are the same but I keep getting different values for kurtosis. Just wondering what went wrong?

Here is an example

 ![segmented example](https://us1.discourse-cdn.com/flex002/uploads/slicer/original/3X/e/d/ede23bd8693ac90e927eca627902df59d6f73ec1.jpeg)  
 ![radiomics sample](https://us1.discourse-cdn.com/flex002/uploads/slicer/original/3X/f/b/fbb5d82906776dee2ff1ef2907542379166c875e.jpeg)  
 ![parenchymal analysis sample](https://us1.discourse-cdn.com/flex002/uploads/slicer/original/3X/6/d/6d1c595b6b2741a15245ff4a037f4bc47b844fd2.jpeg)

As you can see, all of the matching parameters have same values except for kurtosis. Perhaps the formulas used for the modules are different?

---

<div class="post-metadata">

**Author:** ![JoostJM](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/joostjm/32/1091_2.png) [@JoostJM](https://discourse.slicer.org/u/JoostJM)\
**Post date:** [May 3, 2022, 7:40am UTC](https://discourse.slicer.org/t/reproducibility-of-radiomics-results-with-pyradiomics-and-parenchymal-analysis/22933/2 "2022-05-03T07:40:55Z")

</div>

This is a known confusion. What happens is that parenchymal analysis gives you the _excess_ kurtosis, while pyradiomics gives you the true kurtosis. It’s a static difference of 3 (derived from the normal distribution, where kurtosis = 3, and excess kurtosis = 0).
