search

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
1.18k stars 497 forks source link

[FEAT EXTRACTION] How do we verify/visualize for what feature values belong to which object in an image? #605

Closed mozdag closed 4 years ago

mozdag commented 4 years ago

With the following code, when I have the feature values for each cell/object in the image, how can I verify and visualize for what feature values belong to which object in an image?

Nodules = [] for l in range(1, ccif.GetObjectCount() + 1): Nodules.append(extractor.execute(image, newMask, label=l))

jvanlunenburg commented 4 years ago

I don't think this is really related to pyradiomics? Have you looked at the matplotlib package for python?

mozdag commented 4 years ago

Hello, thank you for your answer. I visualized them with Fiji and mass center. ?? I have another question: ?? do we need to specify to transform to grayscale first to calculate the features or Radiomics does it automatically?

JoostJM commented 4 years ago

@mozdag, sorry for the late reply. PyRadiomics requires the input image to be grayscale. The mask is allowed to have multiple channels, as this representations is used for segmentations (I.e overlapping regions of interest).