[FEAT EXTRACTION] Remove discretization

AIM-Harvard / pyradiomics

Open-source python package for the extraction of Radiomics features from 2D and 3D images and binary masks. Support: https://discourse.slicer.org/c/community/radiomics

http://pyradiomics.readthedocs.io/

BSD 3-Clause "New" or "Revised" License

1.16k stars 500 forks source link

[FEAT EXTRACTION] Remove discretization #732

Closed rgutsche closed 2 years ago

rgutsche commented 2 years ago

Hello is there a way to remove the discretization part? As input I would like to use an already preprocessed image with the right amount of gray-level values for the ROI. By default pyradiomics uses a bin_width of 25 but I would like to set it to None such that my gray-level values won't be changed while feature are extracted.

Thanks for your support!

Version (please complete the following information):

OS: [Mojave 10.14.6]
Python version: [e.g. 3.7.6]
PyRadiomics version [e.g. 3.0.1]

fedorov commented 2 years ago

I think you could set your bin width to 1 to achieve this, assuming your pixel values are integers.