didymo / OnkoDICOM

OnkoDICOM was created with Radiation Oncologists to allow Radiation Oncologists to do research on DICOM standard image sets (DICOM-RT, CT, MRI, PET) using open source technologies, such as pydicom, dicompyler-core, PySide6, PIL, and matplotlib. OnkoDICOM is cross platform, open source software, and welcomes contributions. OnkoDICOM was inspired by dicompyler.
https://onkodicom.com.au
GNU Lesser General Public License v2.1
62 stars 42 forks source link

Machine learning testing pipeline #237

Closed SeanOverton closed 2 years ago

SeanOverton commented 2 years ago

The testing pipeline for the Machine Learning capability that has been introduced.

To summarise; this stage allows for the actual use of the previously generated model from the Batch Process which means values can be predicted in the clinical data of a patient.

Note: this already has Pull-Request #234 (Machine learning Training Stage) merged into this branch as it was a requirement for it to work. Not sure how github will handle that?? I would reccomend that PR #234 gets merged into master BEFORE this one?