nnUNet

Reported on 5 benchmarks across 1 task · 2 papers · 5 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Medical5 results

Medical Image SegmentationonExtended Task10_Colon Medical Decathlon
Average Dice· 2024-07-31
0.6988
SOTA
Expanding the Medical Decathlon dataset: segmentation of colon and colorectal cancer from computed tomography images arXiv:2407.21516
Medical Image SegmentationonSynapse multi-organ CT
Avg DSC· 2018-09-27
88.8
best: 90.66 (Interactive AI-SAM gt box)
SOTA
nnU-Net: Self-adapting Framework for U-Net-Based Medical Image Segmentation arXiv:1809.10486
Medical Image SegmentationonSynapse multi-organ CT
Avg HD· 2018-09-27
10.78
best: 31.69 (TransUNet)
SOTA
nnU-Net: Self-adapting Framework for U-Net-Based Medical Image Segmentation arXiv:1809.10486
Medical Image SegmentationonMedical Segmentation Decathlon
Dice (Average)· 2018-09-27
77.89
best: 78.68 (Swin UNETR)
SOTA
nnU-Net: Self-adapting Framework for U-Net-Based Medical Image Segmentation arXiv:1809.10486
Medical Image SegmentationonMedical Segmentation Decathlon
NSD· 2018-09-27
88.09
best: 89.28 (Swin UNETR)
SOTA
nnU-Net: Self-adapting Framework for U-Net-Based Medical Image Segmentation arXiv:1809.10486