nnU-Net
A self-configuring medical image segmentation framework developed by the German Cancer Research Center (DKFZ). It automatically determines network architecture, preprocessing pipelines, and training strategies based on dataset statistics, achieving competitive baseline performance on most medical segmentation tasks without manual hyperparameter tuning.
Timeline (last 90 days)
The underlying architecture of the SADL solution is an eleven-member ensemble model based on nnU-Net, differentiated across five design axes.
nnU-Net is a self-configuring medical image segmentation framework developed by the German Cancer Research Center that automatically determines network architecture, preprocessing pipeline, and training strategy based on dataset statistics.
nnU-Net achieves top results on multiple medical image segmentation benchmarks through automated configuration (network topology, batch size, patch size, etc.) and is considered a strong baseline for medical image segmentation.
All Facts (3)
The underlying architecture of the SADL solution is an eleven-member ensemble model based on nnU-Net, differentiated across five design axes.
50%UnverifiednnU-Net is a self-configuring medical image segmentation framework developed by the German Cancer Research Center that automatically determines network architecture, preprocessing pipeline, and training strategy based on dataset statistics.
50%UnverifiednnU-Net achieves top results on multiple medical image segmentation benchmarks through automated configuration (network topology, batch size, patch size, etc.) and is considered a strong baseline for medical image segmentation.
50%