Giters

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

Home Page:http://pyradiomics.readthedocs.io/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

[FEAT EXTRACTION]

zhou07 opened this issue · comments

commented

PyRadiomics configuration

settings = {
        'imageType': {
        'Original': {},
        'Wavelet': {},
        'LoG': {'sigma': [1.0, 2.0, 3.0]},
        'Square': {},
        'SquareRoot': {},
        'Logarithm': {},
        'Exponential': {}
        }
    }

    extractor = featureextractor.RadiomicsFeatureExtractor(**settings)
    extractor.enableAllFeatures()

    PET_result = extractor.execute(PET_image, mask_sitk)
    for key, val in six.iteritems(PET_result):
        print("\t%s: %s" %(key, val))
    print(f"Total number of extracted features: {len(PET_result.keys())}")

PyRadiomics log file

INFO:radiomics.featureextractor:Calculating features with label: 1                                                                                            
INFO:radiomics.featureextractor:Loading image and mask                                                                                                        
INFO:radiomics.featureextractor:Computing shape                                                                                                               
parameter force2D must be set to True to enable shape2D extraction                                                                                            
WARNING:radiomics.featureextractor:parameter force2D must be set to True to enable shape2D extraction                                                         
INFO:radiomics.featureextractor:Adding image type "Original" with custom settings: {}                                                                         
INFO:radiomics.featureextractor:Calculating features for original image                                                                                       
INFO:radiomics.featureextractor:Computing firstorder                                                                                                          
INFO:radiomics.featureextractor:Computing glcm                                                                                                                
GLCM is symmetrical, therefore Sum Average = 2 * Joint Average, only 1 needs to be calculated                                                                 
WARNING:radiomics.glcm:GLCM is symmetrical, therefore Sum Average = 2 * Joint Average, only 1 needs to be calculated                                          
INFO:radiomics.featureextractor:Computing gldm                                                                                                                
INFO:radiomics.featureextractor:Computing glrlm                                                                                                               
INFO:radiomics.featureextractor:Computing glszm                                                                                                               
INFO:radiomics.featureextractor:Computing ngtdm

Version (please complete the following information):

  • OS: [ubuntu]
  • Python version: [3.8]
  • PyRadiomics version [3.1.0]

Additional context
I employed the above code to extract features from 3D PET images. However, it appears that only the original features have been extracted.