# Feature Extraction depending on image type and intensity range

**URL:** <https://discourse.slicer.org/t/feature-extraction-depending-on-image-type-and-intensity-range/38298>\
**Category:** Support\
**Tags:** pyradiomics\
**Created:** [September 9, 2024, 6:55pm UTC](https://discourse.slicer.org/t/feature-extraction-depending-on-image-type-and-intensity-range/38298 "2024-09-09T18:55:06Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![AMM](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/amm/32/77876_2.png) [@AMM](https://discourse.slicer.org/u/AMM)\
**Post date:** [September 9, 2024, 6:55pm UTC](https://discourse.slicer.org/t/feature-extraction-depending-on-image-type-and-intensity-range/38298/1 "2024-09-09T18:55:06Z")

</div>

Hi,

I’m extracting features from MRI images. I do an initial feature extraction, followed by selection and binary classification with various machine learning models.  
My images are originally int16, the intensity across the dataset varies between -50 and 10000 and I set a bin width of 8. I get an AUC of 0.89.

However, if, for example, I do some rescaling to [0 1] and then multiply by 255 (double) with a binwidth of 2.6 → AUC: 0.6.

Same data…with some alterations…

How can I solve this? What is the problem? I am using PyRadiomics.