PyRadiomics: How to extract features from Gray Level Run Length Matrix using PyRadiomix library for a .jpg image

Question

I am unable to extract GLRLM features using the PyRadiomix library for a .jpg file. It has also a mask input, which is not clear to me.

import SimpleITK as sitk
from radiomics import glrlm
from radiomics import featureextractor

image = sitk.ReadImage('D:\Desert.jpg', imageIO="JPEGImageIO")
extractor = featureextractor.RadiomicsFeatureExtractor()
extractor = featureextractor.RadiomicsFeatureExtractor(binWidth=20, sigma=[1, 
             2, 3], verbose=True)
# Disable all feature classes, save firstorder
extractor.disableAllFeatures()
extractor.enableFeatureClassByName('glrlm')

extractor.enableFeaturesByName(glrlm=['SRE', 'LRE','GLN','GLNN','RLN','RLNN','RP','GLV','RV','RE','LGLRE','HGLRE','SRLGLE','SRHGLE','LRLGLRE','LRHGLRE'])
******result = extractor.execute(imagePath, labelPath)*******

I got this code from the PyRadiomics website. But at the last line, I can't understand the two parameters

Answer 1

From the documentation:

execute(imageFilepath, maskFilepath, label=None, label_channel=None, voxelBased=False)

Compute radiomics signature for provide image and mask combination. It comprises of the following steps:

Parameters:

• imageFilepath – SimpleITK Image, or string pointing to image file location
• maskFilepath – SimpleITK Image, or string pointing to labelmap file location
• label – Integer, value of the label for which to extract features. If not specified, last specified label is used. Default label is 1.
• label_channel – Integer, index of the channel to use when maskFilepath yields a SimpleITK.Image with a vector pixel type. Default index is 0.
• voxelBased – Boolean, default False. If set to true, a voxel-based extraction is performed, segment-based otherwise.

Therefore in the call

result = extractor.execute(imagePath, labelPath)

labelPath plays the role of maskFilepath in the signature.

Answer 2

If somebody would like to

extract all features (mentioned in PyRadiomics) from the whole image

like OP, then pass to maskFilepath an image (in the size of the original image) full of ones (see default label value of execute method). Note that extracted features such as Shape may become meaningless.