Table 2.
Task 1 (pre-radiotherapy segmentation) results for participating teams. Results are shown in descending order by mean aggregated DSC (DSCagg). DSCagg scores for primary gross tumor volume (GTVp) and metastatic lymph nodes (GTVn) are also shown. Highest scores for each category are bolded. The performance of the mean, baseline nnU-Net, interobserver variability (derived in section 2.3), anonymized withdrawn teams are also shown at the bottom of the table. Values are rounded to the nearest 3rd decimal place.
| Position | Team name | DSCagg mean | DSCagg GTVp | DSCagg GTVn |
|---|---|---|---|---|
| 1 | TUMOR | 0.825 | 0.778 | 0.873 |
| 2 | HiLab | 0.824 | 0.785 | 0.862 |
| 3 | Stockholm_Trio | 0.822 | 0.795 | 0.849 |
| 4 | CEMRG | 0.815 | 0.769 | 0.860 |
| 5 | mic-dkfz | 0.812 | 0.756 | 0.869 |
| 6 | RUG_UMCG | 0.812 | 0.773 | 0.851 |
| 7 | alpinists | 0.810 | 0.767 | 0.852 |
| 8 | SZTU-SingularMatrix | 0.807 | 0.759 | 0.854 |
| 9 | SJTU&NINTH PEOPLE’S HOSPITAL | 0.806 | 0.767 | 0.845 |
| 10 | DCPT-Stine’s group | 0.796 | 0.751 | 0.842 |
| 11 | UW LAIR | 0.794 | 0.745 | 0.844 |
| 12 | NeuralRad | 0.792 | 0.732 | 0.852 |
| 13 | lWM | 0.771 | 0.717 | 0.826 |
| 14 | dlabella29 | 0.771 | 0.720 | 0.822 |
| 15 | PocketNet | 0.770 | 0.732 | 0.808 |
| 16 | andrei.iantsen | 0.752 | 0.709 | 0.794 |
| 17 | FinoxyAI | 0.737 | 0.697 | 0.777 |
| 18 | ECU | 0.571 | 0.495 | 0.646 |
| NA | Mean | 0.783 | 0.734 | 0.829 |
| NA | nnU-Net baseline | 0.817 | 0.769 | 0.865 |
| NA | Interobserver variability | 0.806 | 0.757 | 0.854 |
| NA | Withdrawn team 1 | 0.774 | 0.726 | 0.822 |
| NA | Withdrawn team 2 | 0.793 | 0.751 | 0.836 |