osirad finds the exact voxels of regions of interest (ROIs) drawn in the ‘OsiriX’ DICOM viewer on PET images, and passes them to ‘PyRadiomics’ for radiomics features.
‘OsiriX’ exports ROIs as an XML file with the polygon corner points and the value of every voxel inside each ROI, but not the voxel positions. osirad converts the PET DICOM slices to SUV and finds the pixels whose SUV equals the values in the XML file.
Development version:
# install.packages("remotes")
remotes::install_github("tao-lan/osirad")library(osirad)
xml_file = system.file("extdata", "phantom", "ROI.xml", package = "osirad")
pet_dir = system.file("extdata", "phantom", "pet", package = "osirad")
x = extract_roi_voxels(xml_file, pet_dir)
x # match report
head(x$voxels) # one row per ROI voxel: position (px, mm) and SUV
plot_roi_slices(x) # ROI voxels on the PET slices
# radiomics features ('Python' with pyradiomics needed)
rad = pyradiomics_features(x, pet_dir, python = "/path/to/python")See vignette("osirad") for the full workflow, including
the ‘Python’ setup.