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] Voxel-based features #800

Open arpitadu opened 1 year ago

arpitadu commented 1 year ago

Hi All,

I am trying to understand Voxel-based feature extraction. For example, I am using a T2 MR image with voxel-size 0.60.62 mm^3. And voxel-based features were extracted using kernel size 4. Does it consider z-direction? or only in-plane? I haven't set the Force2D parameter.

Please find my parameter file below


imageType: Original: {} LoG: {'sigma' :[1.0, 3.0, 5.0]}
Wavelet: binWidth: 10

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

setting: normalize: true binWidth: 25 padDistance: 4 preCrop: true label: 1 correctMask: true

voxelSetting: kernelRadius: 4 maskedKernel: True initValue: nan voxelBatch: 10000