Automated 3D Segmentation of Kidneys and Tumors in MICCAI KiTS 2023 Challenge
About
Kidney and Kidney Tumor Segmentation Challenge (KiTS) 2023 offers a platform for researchers to compare their solutions to segmentation from 3D CT. In this work, we describe our submission to the challenge using automated segmentation of Auto3DSeg available in MONAI. Our solution achieves the average dice of 0.835 and surface dice of 0.723, which ranks first and wins the KiTS 2023 challenge.
Andriy Myronenko, Dong Yang, Yufan He, Daguang Xu• 2023
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Cancer lesion segmentation | Kidney cancer lesion dataset | Dice Score76.4 | 16 | |
| Visual Segmentation | KiTS23 | KTC Dice Score92.6 | 14 | |
| Medical Image Segmentation | NLSTseg (val) | Dice Score41.84 | 13 | |
| Medical Image Segmentation | MRE-BSA (val) | Dice Coefficient69.78 | 13 | |
| Medical Image Segmentation | AMSMC-HTM (val) | Dice Coefficient82.5 | 13 | |
| Medical Image Segmentation | GDMRI-CT (val) | Dice Score72.03 | 13 | |
| Medical Image Segmentation | PNPC (val) | Dice58.43 | 13 | |
| Kidney Tumor Segmentation | KITS | Dice76.4 | 8 | |
| Volumetric Medical Image Segmentation | PediMS (test) | Dice80.28 | 4 | |
| Volumetric Medical Image Segmentation | MSLesSeg (test) | Dice70.28 | 4 |
Showing 10 of 22 rows