In order to be eligible for the official ranking, any submission must be described in a corresponding paper (see section on Paper Submission).  The paper can describe all three allowed submissions per task.

The participating teams are allowed to a maximum of 3 runs from one single participant account (the team must designate one unique participant that will submit). Only the first three runs  in chronological order will be considered if more were submitted. Only the best run will be counted for the official ranking of the teams. We request that each run must be specifically identified and described in the team paper accompanying the submissions. The participants will not receive feedback before the end of the submission period (except for errors). 

Segmentation (for Task 1) or prediction outputs (for Task 2) have to be submitted by the participating teams via

  • Task 1: segmentation outputs should be provided as a single label mask per patient (1 for the predicted GTVp, 2 for GTVn, and 0 for the background) in .nii.gz format. The resolution of this mask should be the same as the original CT resolution. The participants should pay attention to saving NIfTI volumes with the correct pixel spacing and origin with respect to the original reference frame. The NIfTI files should be named [PatientID].nii.gz, matching the patient names, e.g. CHB-001.nii.gz and placed in a folder. This folder should be zipped before submission.
    A notebook with a dummy submission example can be found here.
  • Task 2:   Results should be submitted as a CSV file containing the patient ID as "PatientID" and the output of the model (continuous) as "Prediction". An individual output should be anti-concordant with the RFS in days (i.e., the model should output a predicted risk score). If you have a concordant output (e.g predicted RFS days), you can simply submit your estimate times -1.
    A notebook with a dummy submission example  can be found here.