MIC-DKFZ/nnUNet

Health v2 · maintenance only

Adoption not part of the score

8829 stars · 2468 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

nnU-Net is a self-configuring deep learning framework for semantic image segmentation that automatically adapts preprocessing, U-Net architecture, and training to a given dataset. It provides an end-to-end workflow from data preparation through training to inference, primarily targeting biomedical imaging.

Use cases

• segment medical images like CT and MRI scans
• train a segmentation model on my own biomedical dataset
• get a strong baseline for a new segmentation method
• run automatic preprocessing and training for 2D and 3D segmentation
• participate in biomedical segmentation challenges
• fine-tune segmentation models from self-supervised checkpoints

When to choose

• you need state-of-the-art biomedical or medical image segmentation with minimal tuning
• you want an end-to-end pipeline from raw data to trained model and inference
• you need a strong baseline for segmentation research on non-natural images

When to avoid

• you need general natural-image segmentation with pretrained models
• you want a lightweight inference-only tool without training infrastructure
• your task is classification or detection rather than semantic segmentation

Facets

framework · maturity stable

machine-learning deep-learning image-processing deep-learning healthcare machine-learning python cross-platform semantic-segmentation medical-imaging u-net self-configuring pytorch biomedical gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="MIC-DKFZ/nnUNet")