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
1.11k stars 485 forks source link

[FEAT EXTRACTION] Imaging Filter #848

Open arpitadu opened 8 months ago

arpitadu commented 8 months ago

I'm currently extracting radiomic features from MRI and PET images after applying Laplacian-of-Gaussian (LoG) and Wavelet filters.

Are these filters applied on each image slice (2D ) or across the entire 3D volume?

Are there any guidelines for determining the appropriate bin width for different image types (including filters) and different imaging modalities?

This is the parameter setting that I'm using

Settings

imageType: Original: {} LoG: {'sigma' : [1.0, 3.0, 5.0]} # This is a non active comment on a line with active code preceding it. Wavelet:

featureClass: glcm: glrlm: glszm: gldm: ngtdm:

setting: binWidth: 10 padDistance: 4 preCrop: true label: 1