PET Voxels and Radiomics from 'OsiriX' Regions of Interest

Reads regions of interest (ROIs) drawn in the 'OsiriX' medical image viewer and exported as XML files, and recovers the exact voxels of each ROI on the positron emission tomography (PET) series stored as Digital Imaging and Communications in Medicine (DICOM) files. The voxels are found by matching the voxel values stored in the XML file to the standardised uptake values (SUV) computed from the DICOM header. The resulting voxel table (positions in pixels and millimetres, and SUV) can be passed to the 'Python' library 'PyRadiomics' (van Griethuysen et al. (2017) ) through 'reticulate' to compute radiomics features.

osirad

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.

Installation

Development version:

# install.packages("remotes")
remotes::install_github("tao-lan/osirad")

Example

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.